ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge main into model-registry

Browse Source
This commit is contained in:
Mario Zechner
2026-06-22 14:00:18 +02:00
parent 019b022068 717a8f958a
commit abbd911693
220 changed files with 10488 additions and 4354 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/api/anthropic-messages.ts
+33 -16
View File
@@ -5,6 +5,7 @@ import type {
MessageCreateParamsStreaming,
MessageParam,
RawMessageStreamEvent,
RefusalStopDetails,
} from "@anthropic-ai/sdk/resources/messages.js";
import { calculateCost } from "../models.ts";
import type {
@@ -16,6 +17,7 @@ import type {
ImageContent,
Message,
Model,
ProviderEnv,
SimpleStreamOptions,
StopReason,
StreamFunction,
@@ -29,6 +31,7 @@ import type {
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { headersToRecord } from "../utils/headers.ts";
import { parseJsonWithRepair, parseStreamingJson } from "../utils/json-parse.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
import { resolveCloudflareBaseUrl } from "./cloudflare.ts";
@@ -40,11 +43,11 @@ import { transformMessages } from "./transform-messages.ts";
* Resolve cache retention preference.
* Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
*/
function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
if (cacheRetention) {
return cacheRetention;
}
if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
return "long";
}
return "short";
@@ -53,8 +56,9 @@ function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention
function getCacheControl(
model: Model<"anthropic-messages">,
cacheRetention?: CacheRetention,
env?: ProviderEnv,
): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {
const retention = resolveCacheRetention(cacheRetention);
const retention = resolveCacheRetention(cacheRetention, env);
if (retention === "none") {
return { retention };
}
@@ -493,7 +497,7 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
});
}
const cacheRetention = options?.cacheRetention ?? resolveCacheRetention();
const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
const created = createClient(
@@ -504,6 +508,7 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
options?.headers,
copilotDynamicHeaders,
cacheSessionId,
options?.env,
);
client = created.client;
isOAuth = created.isOAuthToken;
@@ -534,6 +539,7 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
output.usage.output = event.message.usage.output_tokens || 0;
output.usage.cacheRead = event.message.usage.cache_read_input_tokens || 0;
output.usage.cacheWrite = event.message.usage.cache_creation_input_tokens || 0;
output.usage.cacheWrite1h = event.message.usage.cache_creation?.ephemeral_1h_input_tokens || 0;
// Anthropic doesn't provide total_tokens, compute from components
output.usage.totalTokens =
output.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;
@@ -660,7 +666,11 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
}
} else if (event.type === "message_delta") {
if (event.delta.stop_reason) {
output.stopReason = mapStopReason(event.delta.stop_reason);
const stopReasonResult = mapStopReason(event.delta.stop_reason, event.delta.stop_details);
output.stopReason = stopReasonResult.stopReason;
if (stopReasonResult.errorMessage) {
output.errorMessage = stopReasonResult.errorMessage;
}
}
// Only update usage fields if present (not null).
// Preserves input_tokens from message_start when proxies omit it in message_delta.
@@ -688,7 +698,7 @@ export const stream: StreamFunction<"anthropic-messages", AnthropicOptions> = (
}
if (output.stopReason === "aborted" || output.stopReason === "error") {
throw new Error("An unknown error occurred");
throw new Error(output.errorMessage || "An unknown error occurred");
}
stream.push({ type: "done", reason: output.stopReason, message: output });
@@ -788,6 +798,7 @@ function createClient(
optionsHeaders?: Record<string, string>,
dynamicHeaders?: Record<string, string>,
sessionId?: string,
env?: ProviderEnv,
): { client: Anthropic; isOAuthToken: boolean } {
// Adaptive thinking models have interleaved thinking built in, so skip the beta header.
const needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;
@@ -803,7 +814,7 @@ function createClient(
const client = new Anthropic({
apiKey: null,
authToken: null,
baseURL: resolveCloudflareBaseUrl(model),
baseURL: resolveCloudflareBaseUrl(model, env),
dangerouslyAllowBrowser: true,
defaultHeaders: mergeHeaders(
{
@@ -896,7 +907,7 @@ function buildParams(
isOAuthToken: boolean,
options?: AnthropicOptions,
): MessageCreateParamsStreaming {
const { cacheControl } = getCacheControl(model, options?.cacheRetention);
const { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);
const compat = getAnthropicCompat(model);
const params: MessageCreateParamsStreaming = {
model: model.id,
@@ -1202,22 +1213,28 @@ function convertTools(
});
}
function mapStopReason(reason: Anthropic.Messages.StopReason | string): StopReason {
function mapStopReason(
reason: Anthropic.Messages.StopReason | string,
stopDetails?: RefusalStopDetails | null,
): { stopReason: StopReason; errorMessage?: string } {
switch (reason) {
case "end_turn":
return "stop";
return { stopReason: "stop" };
case "max_tokens":
return "length";
return { stopReason: "length" };
case "tool_use":
return "toolUse";
return { stopReason: "toolUse" };
case "refusal":
return "error";
return {
stopReason: "error",
errorMessage: stopDetails?.explanation || `The model refused to complete the request`,
};
case "pause_turn": // Stop is good enough -> resubmit
return "stop";
return { stopReason: "stop" };
case "stop_sequence":
return "stop"; // We don't supply stop sequences, so this should never happen
return { stopReason: "stop" }; // We don't supply stop sequences, so this should never happen
case "sensitive": // Content flagged by safety filters (not yet in SDK types)
return "error";
return { stopReason: "error" };
default:
// Handle unknown stop reasons gracefully (API may add new values)
throw new Error(`Unhandled stop reason: ${reason}`);
packages/ai/src/api/azure-openai-responses.ts
+11 -4
View File
@@ -12,6 +12,7 @@ import type {
} from "../types.ts";
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { headersToRecord } from "../utils/headers.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.ts";
import { buildBaseOptions } from "./simple-options.ts";
@@ -36,7 +37,9 @@ function resolveDeploymentName(model: Model<"azure-openai-responses">, options?:
if (options?.azureDeploymentName) {
return options.azureDeploymentName;
}
const mappedDeployment = parseDeploymentNameMap(process.env.AZURE_OPENAI_DEPLOYMENT_NAME_MAP).get(model.id);
const mappedDeployment = parseDeploymentNameMap(
getProviderEnvValue("AZURE_OPENAI_DEPLOYMENT_NAME_MAP", options?.env),
).get(model.id);
return mappedDeployment || model.id;
}
@@ -198,10 +201,14 @@ function resolveAzureConfig(
model: Model<"azure-openai-responses">,
options?: AzureOpenAIResponsesOptions,
): { baseUrl: string; apiVersion: string } {
const apiVersion = options?.azureApiVersion || process.env.AZURE_OPENAI_API_VERSION || DEFAULT_AZURE_API_VERSION;
const apiVersion =
options?.azureApiVersion ||
getProviderEnvValue("AZURE_OPENAI_API_VERSION", options?.env) ||
DEFAULT_AZURE_API_VERSION;
const baseUrl = options?.azureBaseUrl?.trim() || process.env.AZURE_OPENAI_BASE_URL?.trim() || undefined;
const resourceName = options?.azureResourceName || process.env.AZURE_OPENAI_RESOURCE_NAME;
const baseUrl =
options?.azureBaseUrl?.trim() || getProviderEnvValue("AZURE_OPENAI_BASE_URL", options?.env)?.trim() || undefined;
const resourceName = options?.azureResourceName || getProviderEnvValue("AZURE_OPENAI_RESOURCE_NAME", options?.env);
let resolvedBaseUrl = baseUrl;
packages/ai/src/api/bedrock-converse-stream.ts
+58 -34
View File
@@ -1,3 +1,4 @@
import type { Agent as HttpsAgent } from "node:https";
import {
BedrockRuntimeClient,
type BedrockRuntimeClientConfig,
@@ -23,6 +24,8 @@ import {
} from "@aws-sdk/client-bedrock-runtime";
import { NodeHttpHandler } from "@smithy/node-http-handler";
import type { BuildMiddleware, DocumentType, MetadataBearer } from "@smithy/types";
import { HttpProxyAgent } from "http-proxy-agent";
import { HttpsProxyAgent } from "https-proxy-agent";
import { calculateCost } from "../models.ts";
import type {
Api,
@@ -31,6 +34,7 @@ import type {
Context,
ImageContent,
Model,
ProviderEnv,
SimpleStreamOptions,
StopReason,
StreamFunction,
@@ -45,7 +49,8 @@ import type {
} from "../types.ts";
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { parseStreamingJson } from "../utils/json-parse.ts";
import { createHttpProxyAgentsForTarget } from "../utils/node-http-proxy.ts";
import { resolveHttpProxyUrlForTarget } from "../utils/node-http-proxy.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
import { adjustMaxTokensForThinking, buildBaseOptions, clampReasoning } from "./simple-options.ts";
import { transformMessages } from "./transform-messages.ts";
@@ -119,18 +124,18 @@ export const stream: StreamFunction<"bedrock-converse-stream", BedrockOptions> =
const blocks = output.content as Block[];
const config: BedrockRuntimeClientConfig = {
profile: options.profile,
profile: options.profile || getProviderEnvValue("AWS_PROFILE", options.env),
};
const configuredRegion = getConfiguredBedrockRegion(options);
const hasConfiguredProfile = hasConfiguredBedrockProfile();
const hasAmbientConfiguredProfile = Boolean(getProviderEnvValue("AWS_PROFILE"));
const endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);
const useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(
model.baseUrl,
configuredRegion,
hasConfiguredProfile,
hasAmbientConfiguredProfile,
);
// Only pin standard AWS Bedrock runtime endpoints when no region/profile is configured.
// Only pin standard AWS Bedrock runtime endpoints when no region or ambient AWS_PROFILE is configured.
// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in
// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.
if (useExplicitEndpoint) {
@@ -138,8 +143,10 @@ export const stream: StreamFunction<"bedrock-converse-stream", BedrockOptions> =
}
// Resolve bearer token for Bedrock API key auth.
const bearerToken = options.bearerToken || process.env.AWS_BEARER_TOKEN_BEDROCK || undefined;
const useBearerToken = bearerToken !== undefined && process.env.AWS_BEDROCK_SKIP_AUTH !== "1";
const skipAuth = getProviderEnvValue("AWS_BEDROCK_SKIP_AUTH", options.env) === "1";
const bearerToken =
options.bearerToken || getProviderEnvValue("AWS_BEARER_TOKEN_BEDROCK", options.env) || undefined;
const useBearerToken = bearerToken !== undefined && !skipAuth;
// in Node.js/Bun environment only
if (typeof process !== "undefined" && (process.versions?.node || process.versions?.bun)) {
@@ -153,25 +160,33 @@ export const stream: StreamFunction<"bedrock-converse-stream", BedrockOptions> =
config.region = configuredRegion;
} else if (endpointRegion && useExplicitEndpoint) {
config.region = endpointRegion;
} else if (!hasConfiguredProfile) {
} else if (!hasAmbientConfiguredProfile) {
config.region = "us-east-1";
}
// Support proxies that don't need authentication
if (process.env.AWS_BEDROCK_SKIP_AUTH === "1") {
if (skipAuth) {
config.credentials = {
accessKeyId: "dummy-access-key",
secretAccessKey: "dummy-secret-key",
};
}
const proxyAgents = createHttpProxyAgentsForTarget(model.baseUrl);
if (proxyAgents) {
const credentials = getConfiguredBedrockCredentials(options.env);
if (!skipAuth && credentials) {
config.credentials = credentials;
}
const proxyUrl = resolveHttpProxyUrlForTarget(model.baseUrl, options.env);
if (proxyUrl) {
// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based
// on `http2` module and has no support for http agent.
// Use NodeHttpHandler to support HTTP(S) proxy agents.
config.requestHandler = new NodeHttpHandler(proxyAgents);
} else if (process.env.AWS_BEDROCK_FORCE_HTTP1 === "1") {
config.requestHandler = new NodeHttpHandler({
httpAgent: new HttpProxyAgent(proxyUrl),
httpsAgent: new HttpsProxyAgent(proxyUrl) as unknown as HttpsAgent,
});
} else if (getProviderEnvValue("AWS_BEDROCK_FORCE_HTTP1", options.env) === "1") {
// Some custom endpoints require HTTP/1.1 instead of HTTP/2
config.requestHandler = new NodeHttpHandler();
}
@@ -192,12 +207,12 @@ export const stream: StreamFunction<"bedrock-converse-stream", BedrockOptions> =
if (options.headers && Object.keys(options.headers).length > 0) {
addCustomHeadersMiddleware(client, options.headers);
}
const cacheRetention = resolveCacheRetention(options.cacheRetention);
const cacheRetention = resolveCacheRetention(options.cacheRetention, options.env);
const inferenceMaxTokens = options.maxTokens ?? (isAnthropicClaudeModel(model) ? model.maxTokens : undefined);
let commandInput = {
modelId: model.id,
messages: convertMessages(context, model, cacheRetention),
system: buildSystemPrompt(context.systemPrompt, model, cacheRetention),
messages: convertMessages(context, model, cacheRetention, options.env),
system: buildSystemPrompt(context.systemPrompt, model, cacheRetention, options.env),
inferenceConfig: {
...(inferenceMaxTokens !== undefined && { maxTokens: inferenceMaxTokens }),
...(options.temperature !== undefined && { temperature: options.temperature }),
@@ -578,11 +593,11 @@ function mapThinkingLevelToEffort(
* Resolve cache retention preference.
* Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
*/
function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
if (cacheRetention) {
return cacheRetention;
}
if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
return "long";
}
return "short";
@@ -617,14 +632,14 @@ function isAnthropicClaudeModel(model: Model<"bedrock-converse-stream">): boolea
* As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.
* Amazon Nova models have automatic caching and don't need explicit cache points.
*/
function supportsPromptCaching(model: Model<"bedrock-converse-stream">): boolean {
function supportsPromptCaching(model: Model<"bedrock-converse-stream">, env?: ProviderEnv): boolean {
const candidates = getModelMatchCandidates(model.id, model.name);
const hasClaudeRef = candidates.some((s) => s.includes("claude"));
if (!hasClaudeRef) {
// Application inference profiles don't contain the model name in the ARN.
// Allow users to force cache points via environment variable.
if (typeof process !== "undefined" && process.env.AWS_BEDROCK_FORCE_CACHE === "1") return true;
if (getProviderEnvValue("AWS_BEDROCK_FORCE_CACHE", env) === "1") return true;
return false;
}
// Claude 4.x models (opus-4, sonnet-4, haiku-4)
@@ -652,13 +667,14 @@ function buildSystemPrompt(
systemPrompt: string | undefined,
model: Model<"bedrock-converse-stream">,
cacheRetention: CacheRetention,
env?: ProviderEnv,
): SystemContentBlock[] | undefined {
if (!systemPrompt) return undefined;
const blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];
// Add cache point for supported Claude models when caching is enabled
if (cacheRetention !== "none" && supportsPromptCaching(model)) {
if (cacheRetention !== "none" && supportsPromptCaching(model, env)) {
blocks.push({
cachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === "long" ? { ttl: CacheTTL.ONE_HOUR } : {}) },
});
@@ -699,6 +715,7 @@ function convertMessages(
context: Context,
model: Model<"bedrock-converse-stream">,
cacheRetention: CacheRetention,
env?: ProviderEnv,
): Message[] {
const result: Message[] = [];
const transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);
@@ -844,7 +861,7 @@ function convertMessages(
}
// Add cache point to the last user message for supported Claude models when caching is enabled
if (cacheRetention !== "none" && supportsPromptCaching(model) && result.length > 0) {
if (cacheRetention !== "none" && supportsPromptCaching(model, env) && result.length > 0) {
const lastMessage = result[result.length - 1];
if (lastMessage.role === ConversationRole.USER && lastMessage.content) {
(lastMessage.content as ContentBlock[]).push({
@@ -906,19 +923,26 @@ function mapStopReason(reason: string | undefined): StopReason {
}
function getConfiguredBedrockRegion(options: BedrockOptions): string | undefined {
if (typeof process === "undefined") {
return options.region;
}
return options.region || process.env.AWS_REGION || process.env.AWS_DEFAULT_REGION || undefined;
return (
options.region ||
getProviderEnvValue("AWS_REGION", options.env) ||
getProviderEnvValue("AWS_DEFAULT_REGION", options.env) ||
undefined
);
}
function hasConfiguredBedrockProfile(): boolean {
if (typeof process === "undefined") {
return false;
function getConfiguredBedrockCredentials(env?: ProviderEnv): BedrockRuntimeClientConfig["credentials"] | undefined {
const accessKeyId = getProviderEnvValue("AWS_ACCESS_KEY_ID", env);
const secretAccessKey = getProviderEnvValue("AWS_SECRET_ACCESS_KEY", env);
if (!accessKeyId || !secretAccessKey) {
return undefined;
}
return Boolean(process.env.AWS_PROFILE);
const sessionToken = getProviderEnvValue("AWS_SESSION_TOKEN", env);
return {
accessKeyId,
secretAccessKey,
...(sessionToken ? { sessionToken } : {}),
};
}
function getStandardBedrockEndpointRegion(baseUrl: string | undefined): string | undefined {
@@ -938,14 +962,14 @@ function getStandardBedrockEndpointRegion(baseUrl: string | undefined): string |
function shouldUseExplicitBedrockEndpoint(
baseUrl: string,
configuredRegion: string | undefined,
hasConfiguredProfile: boolean,
hasAmbientConfiguredProfile: boolean,
): boolean {
const endpointRegion = getStandardBedrockEndpointRegion(baseUrl);
if (!endpointRegion) {
return true;
}
return !configuredRegion && !hasConfiguredProfile;
return !configuredRegion && !hasAmbientConfiguredProfile;
}
function isGovCloudBedrockTarget(model: Model<"bedrock-converse-stream">, options: BedrockOptions): boolean {
packages/ai/src/api/cloudflare.ts
+5 -4
View File
@@ -1,4 +1,5 @@
import type { Api, Model } from "../types.ts";
import type { Api, Model, ProviderEnv } from "../types.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
/** Workers AI direct endpoint. */
export const CLOUDFLARE_WORKERS_AI_BASE_URL =
@@ -20,12 +21,12 @@ export function isCloudflareProvider(provider: string): boolean {
return provider === "cloudflare-workers-ai" || provider === "cloudflare-ai-gateway";
}
/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from process.env. */
export function resolveCloudflareBaseUrl(model: Model<Api>): string {
/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from provider env or process.env. */
export function resolveCloudflareBaseUrl(model: Model<Api>, env?: ProviderEnv): string {
const url = model.baseUrl;
if (!url.includes("{")) return url;
const baseUrl = url.replace(/\{([A-Z_][A-Z0-9_]*)\}/g, (_match, name: string) => {
const value = process.env[name];
const value = getProviderEnvValue(name, env);
if (!value) {
throw new Error(`${name} is required for provider ${model.provider} but is not set.`);
}
packages/ai/src/api/google-generative-ai.ts
+2 -1
View File
@@ -406,7 +406,8 @@ function isGemini3ProModel(model: Model<"google-generative-ai">): boolean {
}
function isGemini3FlashModel(model: Model<"google-generative-ai">): boolean {
return /gemini-3(?:\.\d+)?-flash/.test(model.id.toLowerCase());
const id = model.id.toLowerCase();
return /gemini-3(?:\.\d+)?-flash/.test(id) || id === "gemini-flash-latest" || id === "gemini-flash-lite-latest";
}
function getDisabledThinkingConfig(model: Model<"google-generative-ai">): ThinkingConfig {
packages/ai/src/api/google-vertex.ts
+18 -4
View File
@@ -14,6 +14,7 @@ import type {
Context,
Model,
ThinkingLevel as PiThinkingLevel,
ProviderEnv,
SimpleStreamOptions,
StreamFunction,
StreamOptions,
@@ -23,6 +24,7 @@ import type {
ToolCall,
} from "../types.ts";
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
import type { GoogleThinkingLevel } from "./google-shared.ts";
import {
@@ -91,7 +93,7 @@ export const stream: StreamFunction<"google-vertex", GoogleVertexOptions> = (
// Create the client using either a Vertex API key, if provided, or ADC with project and location
const client = apiKey
? createClientWithApiKey(model, apiKey, options?.headers)
: createClient(model, resolveProject(options), resolveLocation(options), options?.headers);
: createClient(model, resolveProject(options), resolveLocation(options), options?.headers, options?.env);
let params = buildParams(model, context, options);
const nextParams = await options?.onPayload?.(params, model);
if (nextParams !== undefined) {
@@ -333,12 +335,15 @@ function createClient(
project: string,
location: string,
optionsHeaders?: Record<string, string>,
env?: ProviderEnv,
): GoogleGenAI {
const googleAuthOptions = buildGoogleAuthOptions(env);
return new GoogleGenAI({
vertexai: true,
project,
location,
apiVersion: API_VERSION,
...(googleAuthOptions ? { googleAuthOptions } : {}),
httpOptions: buildHttpOptions(model, optionsHeaders),
});
}
@@ -394,6 +399,11 @@ function baseUrlIncludesApiVersion(baseUrl: string): boolean {
}
}
function buildGoogleAuthOptions(env?: ProviderEnv): { keyFilename: string } | undefined {
const keyFilename = getProviderEnvValue("GOOGLE_APPLICATION_CREDENTIALS", env);
return keyFilename ? { keyFilename } : undefined;
}
function resolveApiKey(options?: GoogleVertexOptions): string | undefined {
const apiKey = options?.apiKey?.trim();
if (!apiKey || apiKey === GCP_VERTEX_CREDENTIALS_MARKER || isPlaceholderApiKey(apiKey)) {
@@ -407,7 +417,10 @@ function isPlaceholderApiKey(apiKey: string): boolean {
}
function resolveProject(options?: GoogleVertexOptions): string {
const project = options?.project || process.env.GOOGLE_CLOUD_PROJECT || process.env.GCLOUD_PROJECT;
const project =
options?.project ||
getProviderEnvValue("GOOGLE_CLOUD_PROJECT", options?.env) ||
getProviderEnvValue("GCLOUD_PROJECT", options?.env);
if (!project) {
throw new Error(
"Vertex AI requires a project ID. Set GOOGLE_CLOUD_PROJECT/GCLOUD_PROJECT or pass project in options.",
@@ -417,7 +430,7 @@ function resolveProject(options?: GoogleVertexOptions): string {
}
function resolveLocation(options?: GoogleVertexOptions): string {
const location = options?.location || process.env.GOOGLE_CLOUD_LOCATION;
const location = options?.location || getProviderEnvValue("GOOGLE_CLOUD_LOCATION", options?.env);
if (!location) {
throw new Error("Vertex AI requires a location. Set GOOGLE_CLOUD_LOCATION or pass location in options.");
}
@@ -490,7 +503,8 @@ function isGemini3ProModel(model: Model<"google-generative-ai">): boolean {
}
function isGemini3FlashModel(model: Model<"google-generative-ai">): boolean {
return /gemini-3(?:\.\d+)?-flash/.test(model.id.toLowerCase());
const id = model.id.toLowerCase();
return /gemini-3(?:\.\d+)?-flash/.test(id) || id === "gemini-flash-latest" || id === "gemini-flash-lite-latest";
}
function getDisabledThinkingConfig(model: Model<"google-vertex">): ThinkingConfig {
packages/ai/src/api/mistral-conversations.ts
+35 -4
View File
@@ -226,7 +226,7 @@ function buildRequestOptions(model: Model<"mistral-conversations">, options?: Mi
// Mistral infrastructure uses `x-affinity` for KV-cache reuse (prefix caching).
// Respect explicit caller-provided header values.
if (options?.sessionId && !headers["x-affinity"]) {
if (shouldUsePromptCaching(options) && !headers["x-affinity"]) {
headers["x-affinity"] = options.sessionId;
}
@@ -255,6 +255,7 @@ function buildChatPayload(
if (options?.toolChoice) payload.toolChoice = mapToolChoice(options.toolChoice);
if (options?.promptMode) payload.promptMode = options.promptMode;
if (options?.reasoningEffort) payload.reasoningEffort = options.reasoningEffort;
if (shouldUsePromptCaching(options)) payload.promptCacheKey = options.sessionId;
if (context.systemPrompt) {
payload.messages.unshift({
@@ -266,6 +267,31 @@ function buildChatPayload(
return payload;
}
function shouldUsePromptCaching(options?: MistralOptions): options is MistralOptions & { sessionId: string } {
return options?.cacheRetention !== "none" && !!options?.sessionId;
}
function getMistralCachedPromptTokens(usage: unknown, promptTokens: number): number {
const rawUsage = usage as {
promptTokensDetails?: { cachedTokens?: unknown } | null;
prompt_tokens_details?: { cached_tokens?: unknown } | null;
promptTokenDetails?: { cachedTokens?: unknown } | null;
prompt_token_details?: { cached_tokens?: unknown } | null;
numCachedTokens?: unknown;
num_cached_tokens?: unknown;
};
const rawCachedTokens =
rawUsage.promptTokensDetails?.cachedTokens ??
rawUsage.prompt_tokens_details?.cached_tokens ??
rawUsage.promptTokenDetails?.cachedTokens ??
rawUsage.prompt_token_details?.cached_tokens ??
rawUsage.numCachedTokens ??
rawUsage.num_cached_tokens ??
0;
const cachedTokens = typeof rawCachedTokens === "number" && Number.isFinite(rawCachedTokens) ? rawCachedTokens : 0;
return Math.min(promptTokens, Math.max(0, cachedTokens));
}
async function consumeChatStream(
model: Model<"mistral-conversations">,
output: AssistantMessage,
@@ -305,11 +331,16 @@ async function consumeChatStream(
output.responseId ||= chunk.id;
if (chunk.usage) {
output.usage.input = chunk.usage.promptTokens || 0;
const promptTokens = chunk.usage.promptTokens || 0;
const cachedPromptTokens = getMistralCachedPromptTokens(chunk.usage, promptTokens);
output.usage.input = Math.max(0, promptTokens - cachedPromptTokens);
output.usage.output = chunk.usage.completionTokens || 0;
output.usage.cacheRead = 0;
output.usage.cacheRead = cachedPromptTokens;
output.usage.cacheWrite = 0;
output.usage.totalTokens = chunk.usage.totalTokens || output.usage.input + output.usage.output;
output.usage.totalTokens =
chunk.usage.totalTokens ||
output.usage.input + output.usage.output + output.usage.cacheRead + output.usage.cacheWrite;
calculateCost(model, output.usage);
}
packages/ai/src/api/openai-codex-responses.ts
+25 -18
View File
@@ -27,6 +27,7 @@ import type {
AssistantMessage,
Context,
Model,
ProviderEnv,
SimpleStreamOptions,
StreamFunction,
StreamOptions,
@@ -40,6 +41,7 @@ import {
} from "../utils/diagnostics.ts";
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { headersToRecord } from "../utils/headers.ts";
import { resolveHttpProxyUrlForTarget } from "../utils/node-http-proxy.ts";
import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.ts";
import { buildBaseOptions } from "./simple-options.ts";
@@ -53,7 +55,9 @@ const JWT_CLAIM_PATH = "https://api.openai.com/auth" as const;
const DEFAULT_MAX_RETRIES = 0;
const BASE_DELAY_MS = 1000;
const DEFAULT_MAX_RETRY_DELAY_MS = 60_000;
const DEFAULT_SSE_HEADER_TIMEOUT_MS = 10_000;
// Keep a bounded pre-header timeout so zero-event Codex SSE stalls fail instead of
// leaving callers stuck on "Working..." indefinitely. See #4945.
const DEFAULT_SSE_HEADER_TIMEOUT_MS = 20_000;
const DEFAULT_WEBSOCKET_CONNECT_TIMEOUT_MS = 15_000;
const CODEX_TOOL_CALL_PROVIDERS = new Set(["openai", "openai-codex", "opencode"]);
const WEBSOCKET_MESSAGE_TOO_BIG_CLOSE_CODE = 1009;
@@ -812,19 +816,13 @@ type WebSocketConstructor = new (
) => WebSocketLike;
let _cachedWebsocket: WebSocketConstructor | null = null;
async function getWebSocketConstructor(): Promise<WebSocketConstructor | null> {
if (_cachedWebsocket) return _cachedWebsocket;
async function getWebSocketConstructor(env?: ProviderEnv): Promise<WebSocketConstructor | null> {
if (!env && _cachedWebsocket) return _cachedWebsocket;
// bun doesn't respect http proxy envs, ref: https://github.com/oven-sh/bun/issues/15489
// TODO: remove this when bun supports proxy envs in websocket.
if (
process?.versions?.bun &&
(process.env.HTTP_PROXY || process.env.HTTPS_PROXY || process.env.http_proxy || process.env.https_proxy)
) {
const m = await dynamicImport("proxy-from-env");
const getProxyForUrl = (m as { getProxyForUrl: (url: string | object | URL) => string }).getProxyForUrl;
_cachedWebsocket = class extends WebSocket {
if (typeof process !== "undefined" && process.versions?.bun) {
const WebSocketWithProxy = class extends WebSocket {
constructor(url: string | URL, options?: string | string[] | Record<string, unknown>) {
let _opts: Record<string, unknown> = {};
if (Array.isArray(options) || typeof options === "string") {
@@ -833,11 +831,17 @@ async function getWebSocketConstructor(): Promise<WebSocketConstructor | null> {
_opts = { ...options };
}
const proxy = getProxyForUrl(url.toString().replace(/^wss:/, "https:").replace(/^ws:/, "http:"));
super(url, { ..._opts, ...(proxy ? { proxy } : {}) } as any);
const proxyUrl = resolveHttpProxyUrlForTarget(
url.toString().replace(/^wss:/, "https:").replace(/^ws:/, "http:"),
env,
);
super(url, { ..._opts, ...(proxyUrl ? { proxy: proxyUrl.toString() } : {}) } as any);
}
};
return _cachedWebsocket;
if (!env) {
_cachedWebsocket = WebSocketWithProxy;
}
return WebSocketWithProxy;
}
const ctor = (globalThis as { WebSocket?: unknown }).WebSocket;
@@ -892,8 +896,9 @@ async function connectWebSocket(
headers: Headers,
signal?: AbortSignal,
connectTimeoutMs = DEFAULT_WEBSOCKET_CONNECT_TIMEOUT_MS,
env?: ProviderEnv,
): Promise<WebSocketLike> {
const WebSocketCtor = await getWebSocketConstructor();
const WebSocketCtor = await getWebSocketConstructor(env);
if (!WebSocketCtor) {
throw new Error("WebSocket transport is not available in this runtime");
}
@@ -970,6 +975,7 @@ async function acquireWebSocket(
sessionId: string | undefined,
signal?: AbortSignal,
connectTimeoutMs?: number,
env?: ProviderEnv,
): Promise<{
socket: WebSocketLike;
entry?: CachedWebSocketConnection;
@@ -977,7 +983,7 @@ async function acquireWebSocket(
release: (options?: { keep?: boolean }) => void;
}> {
if (!sessionId) {
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
return {
socket,
reused: false,
@@ -1009,7 +1015,7 @@ async function acquireWebSocket(
};
}
if (cached.busy) {
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
return {
socket,
reused: false,
@@ -1024,7 +1030,7 @@ async function acquireWebSocket(
}
}
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
const entry: CachedWebSocketConnection = { socket, busy: true };
websocketSessionCache.set(sessionId, entry);
return {
@@ -1310,6 +1316,7 @@ async function processWebSocketStream(
options?.sessionId,
options?.signal,
websocketConnectTimeoutMs,
options?.env,
);
let keepConnection = true;
const useCachedContext = options?.transport === "websocket-cached" || options?.transport === "auto";
packages/ai/src/api/openai-completions.ts
+113 -15
View File
@@ -14,11 +14,13 @@ import { calculateCost, clampThinkingLevel } from "../models.ts";
import type {
AssistantMessage,
CacheRetention,
ChatTemplateKwargValue,
Context,
ImageContent,
Message,
Model,
OpenAICompletionsCompat,
ProviderEnv,
SimpleStreamOptions,
StopReason,
StreamFunction,
@@ -32,6 +34,7 @@ import type {
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { headersToRecord } from "../utils/headers.ts";
import { parseStreamingJson } from "../utils/json-parse.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.ts";
import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.ts";
@@ -74,6 +77,20 @@ function isImageContentBlock(block: { type: string }): block is ImageContent {
return block.type === "image";
}
function isEncryptedReasoningDetail(detail: unknown): detail is OpenAIEncryptedReasoningDetail {
if (typeof detail !== "object" || detail === null) {
return false;
}
const candidate = detail as Record<string, unknown>;
return (
candidate.type === "reasoning.encrypted" &&
typeof candidate.id === "string" &&
candidate.id.length > 0 &&
typeof candidate.data === "string" &&
candidate.data.length > 0
);
}
export interface OpenAICompletionsOptions extends StreamOptions {
toolChoice?: "auto" | "none" | "required" | { type: "function"; function: { name: string } };
reasoningEffort?: "minimal" | "low" | "medium" | "high" | "xhigh";
@@ -88,8 +105,16 @@ type ResolvedOpenAICompletionsCompat = Omit<Required<OpenAICompletionsCompat>, "
cacheControlFormat?: OpenAICompletionsCompat["cacheControlFormat"];
};
type ResolvedChatTemplateKwargValue = string | number | boolean | null;
type ChatCompletionInstructionMessageParam = ChatCompletionDeveloperMessageParam | ChatCompletionSystemMessageParam;
type OpenAIEncryptedReasoningDetail = {
type: "reasoning.encrypted";
id: string;
data: string;
};
type ChatCompletionTextPartWithCacheControl = ChatCompletionContentPartText & {
cache_control?: OpenAICompatCacheControl;
};
@@ -98,11 +123,11 @@ type ChatCompletionToolWithCacheControl = OpenAI.Chat.Completions.ChatCompletion
cache_control?: OpenAICompatCacheControl;
};
function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
if (cacheRetention) {
return cacheRetention;
}
if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
return "long";
}
return "short";
@@ -140,9 +165,9 @@ export const stream: StreamFunction<"openai-completions", OpenAICompletionsOptio
throw new Error(`No API key for provider: ${model.provider}`);
}
const compat = getCompat(model);
const cacheRetention = resolveCacheRetention(options?.cacheRetention);
const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, compat);
const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, compat, options?.env);
let params = buildParams(model, context, options, compat, cacheRetention);
const nextParams = await options?.onPayload?.(params, model);
if (nextParams !== undefined) {
@@ -171,6 +196,7 @@ export const stream: StreamFunction<"openai-completions", OpenAICompletionsOptio
let hasFinishReason = false;
const toolCallBlocksByIndex = new Map<number, StreamingToolCallBlock>();
const toolCallBlocksById = new Map<string, StreamingToolCallBlock>();
const pendingReasoningDetailsByToolCallId = new Map<string, string>();
const blocks = output.content as StreamingBlock[];
const getContentIndex = (block: StreamingBlock) => blocks.indexOf(block);
const finishBlock = (block: StreamingBlock) => {
@@ -226,6 +252,16 @@ export const stream: StreamFunction<"openai-completions", OpenAICompletionsOptio
}
return thinkingBlock;
};
const applyPendingReasoningDetail = (block: StreamingToolCallBlock) => {
if (!block.id) {
return;
}
const pendingReasoningDetail = pendingReasoningDetailsByToolCallId.get(block.id);
if (pendingReasoningDetail) {
block.thoughtSignature = pendingReasoningDetail;
pendingReasoningDetailsByToolCallId.delete(block.id);
}
};
const ensureToolCallBlock = (toolCall: StreamingToolCallDelta) => {
const streamIndex = typeof toolCall.index === "number" ? toolCall.index : undefined;
let block = streamIndex !== undefined ? toolCallBlocksByIndex.get(streamIndex) : undefined;
@@ -261,6 +297,7 @@ export const stream: StreamFunction<"openai-completions", OpenAICompletionsOptio
if (toolCall.id) {
toolCallBlocksById.set(toolCall.id, block);
}
applyPendingReasoningDetail(block);
return block;
};
@@ -370,15 +407,16 @@ export const stream: StreamFunction<"openai-completions", OpenAICompletionsOptio
}
}
const reasoningDetails = (choice.delta as any).reasoning_details;
if (reasoningDetails && Array.isArray(reasoningDetails)) {
const reasoningDetails = (choice.delta as { reasoning_details?: unknown }).reasoning_details;
if (Array.isArray(reasoningDetails)) {
for (const detail of reasoningDetails) {
if (detail.type === "reasoning.encrypted" && detail.id && detail.data) {
const matchingToolCall = output.content.find(
(b) => b.type === "toolCall" && b.id === detail.id,
) as ToolCall | undefined;
if (isEncryptedReasoningDetail(detail)) {
const serializedDetail = JSON.stringify(detail);
const matchingToolCall = toolCallBlocksById.get(detail.id);
if (matchingToolCall) {
matchingToolCall.thoughtSignature = JSON.stringify(detail);
matchingToolCall.thoughtSignature = serializedDetail;
} else {
pendingReasoningDetailsByToolCallId.set(detail.id, serializedDetail);
}
}
}
@@ -454,6 +492,7 @@ function createClient(
optionsHeaders?: Record<string, string>,
sessionId?: string,
compat: ResolvedOpenAICompletionsCompat = getCompat(model),
env?: ProviderEnv,
) {
const headers = { ...model.headers };
if (model.provider === "github-copilot") {
@@ -487,7 +526,7 @@ function createClient(
return new OpenAI({
apiKey,
baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model, env) : model.baseUrl,
dangerouslyAllowBrowser: true,
defaultHeaders,
});
@@ -498,7 +537,7 @@ function buildParams(
context: Context,
options?: OpenAICompletionsOptions,
compat: ResolvedOpenAICompletionsCompat = getCompat(model),
cacheRetention: CacheRetention = resolveCacheRetention(options?.cacheRetention),
cacheRetention: CacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env),
) {
const messages = convertMessages(model, context, compat);
const cacheControl = getCompatCacheControl(compat, cacheRetention);
@@ -554,8 +593,18 @@ function buildParams(
}
if (compat.thinkingFormat === "zai" && model.reasoning) {
const zaiParams = params as typeof params & { thinking?: { type: "enabled" | "disabled" } };
const zaiParams = params as Omit<typeof params, "reasoning_effort"> & {
thinking?: { type: "enabled" | "disabled" };
reasoning_effort?: string;
};
zaiParams.thinking = { type: options?.reasoningEffort ? "enabled" : "disabled" };
if (options?.reasoningEffort && compat.supportsReasoningEffort) {
const mappedEffort = model.thinkingLevelMap?.[options.reasoningEffort];
const effort = mappedEffort === undefined ? options.reasoningEffort : mappedEffort;
if (typeof effort === "string") {
zaiParams.reasoning_effort = effort;
}
}
} else if (compat.thinkingFormat === "qwen" && model.reasoning) {
(params as any).enable_thinking = !!options?.reasoningEffort;
} else if (compat.thinkingFormat === "qwen-chat-template" && model.reasoning) {
@@ -563,8 +612,17 @@ function buildParams(
enable_thinking: !!options?.reasoningEffort,
preserve_thinking: true,
};
} else if (compat.thinkingFormat === "chat-template" && model.reasoning) {
const chatTemplateKwargs = buildChatTemplateKwargs(model, options, compat);
if (chatTemplateKwargs) {
(params as any).chat_template_kwargs = chatTemplateKwargs;
}
} else if (compat.thinkingFormat === "deepseek" && model.reasoning) {
(params as any).thinking = { type: options?.reasoningEffort ? "enabled" : "disabled" };
if (options?.reasoningEffort) {
(params as any).thinking = { type: "enabled" };
} else if (model.thinkingLevelMap?.off !== null) {
(params as any).thinking = { type: "disabled" };
}
if (options?.reasoningEffort && compat.supportsReasoningEffort) {
(params as any).reasoning_effort =
model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort;
@@ -629,6 +687,44 @@ function buildParams(
return params;
}
function buildChatTemplateKwargs(
model: Model<"openai-completions">,
options: OpenAICompletionsOptions | undefined,
compat: ResolvedOpenAICompletionsCompat,
): Record<string, ResolvedChatTemplateKwargValue> | undefined {
const kwargs: Record<string, ResolvedChatTemplateKwargValue> = {};
for (const [key, value] of Object.entries(compat.chatTemplateKwargs)) {
const resolved = resolveChatTemplateKwargValue(model, options, value);
if (resolved !== undefined) {
kwargs[key] = resolved;
}
}
return Object.keys(kwargs).length > 0 ? kwargs : undefined;
}
function resolveChatTemplateKwargValue(
model: Model<"openai-completions">,
options: OpenAICompletionsOptions | undefined,
value: ChatTemplateKwargValue,
): ResolvedChatTemplateKwargValue | undefined {
if (typeof value !== "object" || value === null) {
return value;
}
const reasoningEffort = options?.reasoningEffort;
if (!reasoningEffort && value.omitWhenOff) {
return undefined;
}
if (value.$var === "thinking.enabled") {
return !!reasoningEffort;
}
const mappedValue = reasoningEffort ? model.thinkingLevelMap?.[reasoningEffort] : model.thinkingLevelMap?.off;
return mappedValue === undefined ? reasoningEffort : typeof mappedValue === "string" ? mappedValue : undefined;
}
function getCompatCacheControl(
compat: ResolvedOpenAICompletionsCompat,
cacheRetention: CacheRetention,
@@ -1141,6 +1237,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
: "openai",
openRouterRouting: {},
vercelGatewayRouting: {},
chatTemplateKwargs: {},
zaiToolStream: false,
supportsStrictMode: !isMoonshot && !isTogether && !isCloudflareAiGateway && !isNvidia,
cacheControlFormat,
@@ -1179,6 +1276,7 @@ function getCompat(model: Model<"openai-completions">): ResolvedOpenAICompletion
thinkingFormat: model.compat.thinkingFormat ?? detected.thinkingFormat,
openRouterRouting: model.compat.openRouterRouting ?? {},
vercelGatewayRouting: model.compat.vercelGatewayRouting ?? detected.vercelGatewayRouting,
chatTemplateKwargs: model.compat.chatTemplateKwargs ?? detected.chatTemplateKwargs,
zaiToolStream: model.compat.zaiToolStream ?? detected.zaiToolStream,
supportsStrictMode: model.compat.supportsStrictMode ?? detected.supportsStrictMode,
cacheControlFormat: model.compat.cacheControlFormat ?? detected.cacheControlFormat,
packages/ai/src/api/openai-responses-shared.ts
+2 -1
View File
@@ -456,7 +456,8 @@ export async function processResponsesStream<TApi extends Api>(
});
currentBlock = null;
} else if (item.type === "message" && currentBlock?.type === "text") {
currentBlock.text = item.content.map((c) => (c.type === "output_text" ? c.text : c.refusal)).join("");
currentBlock.text =
item.content?.map((c) => (c.type === "output_text" ? c.text : c.refusal)).join("") || "";
currentBlock.textSignature = encodeTextSignatureV1(item.id, item.phase ?? undefined);
stream.push({
type: "text_end",
packages/ai/src/api/openai-responses.ts
+9 -6
View File
@@ -8,6 +8,7 @@ import type {
Context,
Model,
OpenAIResponsesCompat,
ProviderEnv,
SimpleStreamOptions,
StreamFunction,
StreamOptions,
@@ -15,6 +16,7 @@ import type {
} from "../types.ts";
import { AssistantMessageEventStream } from "../utils/event-stream.ts";
import { headersToRecord } from "../utils/headers.ts";
import { getProviderEnvValue } from "../utils/provider-env.ts";
import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.ts";
import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.ts";
import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
@@ -27,11 +29,11 @@ const OPENAI_TOOL_CALL_PROVIDERS = new Set(["openai", "openai-codex", "opencode"
* Resolve cache retention preference.
* Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
*/
function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
if (cacheRetention) {
return cacheRetention;
}
if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
return "long";
}
return "short";
@@ -111,9 +113,9 @@ export const stream: StreamFunction<"openai-responses", OpenAIResponsesOptions>
if (!apiKey) {
throw new Error(`No API key for provider: ${model.provider}`);
}
const cacheRetention = resolveCacheRetention(options?.cacheRetention);
const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
const client = createClient(model, context, apiKey, options?.headers, cacheSessionId);
const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, options?.env);
let params = buildParams(model, context, options);
const nextParams = await options?.onPayload?.(params, model);
if (nextParams !== undefined) {
@@ -185,6 +187,7 @@ function createClient(
apiKey: string,
optionsHeaders?: Record<string, string>,
sessionId?: string,
env?: ProviderEnv,
) {
const compat = getCompat(model);
const headers = { ...model.headers };
@@ -220,7 +223,7 @@ function createClient(
return new OpenAI({
apiKey,
baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model, env) : model.baseUrl,
dangerouslyAllowBrowser: true,
defaultHeaders,
});
@@ -229,7 +232,7 @@ function createClient(
function buildParams(model: Model<"openai-responses">, context: Context, options?: OpenAIResponsesOptions) {
const messages = convertResponsesMessages(model, context, OPENAI_TOOL_CALL_PROVIDERS);
const cacheRetention = resolveCacheRetention(options?.cacheRetention);
const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
const compat = getCompat(model);
const params: ResponseCreateParamsStreaming = {
model: model.id,
packages/ai/src/api/simple-options.ts
+1
View File
@@ -17,6 +17,7 @@ export function buildBaseOptions(_model: Model<Api>, options?: SimpleStreamOptio
maxRetries: options?.maxRetries,
maxRetryDelayMs: options?.maxRetryDelayMs,
metadata: options?.metadata,
env: options?.env,
};
}
packages/ai/src/env-api-keys.ts
+27 -63
View File
@@ -23,44 +23,17 @@ if (typeof process !== "undefined" && (process.versions?.node || process.version
});
}
import type { KnownProvider } from "./types.ts";
let _procEnvCache: Map<string, string> | null = null;
/**
* Fallback for https://github.com/oven-sh/bun/issues/27802
* Bun compiled binaries have an empty `process.env` inside sandbox
* environments on Linux. We can recover the env from `/proc/self/environ`.
*/
function getProcEnv(key: string): string | undefined {
if (!process.versions?.bun) return undefined;
if (typeof process === "undefined") return undefined;
// If process.env already has entries, the bug is not triggered.
if (Object.keys(process.env).length > 0) return undefined;
if (_procEnvCache === null) {
_procEnvCache = new Map();
try {
const { readFileSync } = require("node:fs") as typeof import("node:fs");
const data = readFileSync("/proc/self/environ", "utf-8");
for (const entry of data.split("\0")) {
const idx = entry.indexOf("=");
if (idx > 0) {
_procEnvCache.set(entry.slice(0, idx), entry.slice(idx + 1));
}
}
} catch {
// /proc/self/environ may not be readable.
}
}
return _procEnvCache.get(key);
}
import type { KnownProvider, ProviderEnv } from "./types.ts";
import { getProviderEnvValue } from "./utils/provider-env.ts";
let cachedVertexAdcCredentialsExists: boolean | null = null;
function hasVertexAdcCredentials(): boolean {
function hasVertexAdcCredentials(env?: ProviderEnv): boolean {
const explicitCredentialsPath = env?.GOOGLE_APPLICATION_CREDENTIALS;
if (explicitCredentialsPath) {
return _existsSync ? _existsSync(explicitCredentialsPath) : false;
}
if (cachedVertexAdcCredentialsExists === null) {
// If node modules haven't loaded yet (async import race at startup),
// return false WITHOUT caching so the next call retries once they're ready.
@@ -75,7 +48,7 @@ function hasVertexAdcCredentials(): boolean {
}
// Check GOOGLE_APPLICATION_CREDENTIALS env var first (standard way)
const gacPath = process.env.GOOGLE_APPLICATION_CREDENTIALS || getProcEnv("GOOGLE_APPLICATION_CREDENTIALS");
const gacPath = getProviderEnvValue("GOOGLE_APPLICATION_CREDENTIALS", env);
if (gacPath) {
cachedVertexAdcCredentialsExists = _existsSync(gacPath);
} else {
@@ -143,13 +116,13 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
* credential sources such as AWS profiles, AWS IAM credentials, and Google
* Application Default Credentials.
*/
export function findEnvKeys(provider: KnownProvider): string[] | undefined;
export function findEnvKeys(provider: string): string[] | undefined;
export function findEnvKeys(provider: string): string[] | undefined {
export function findEnvKeys(provider: KnownProvider, env?: ProviderEnv): string[] | undefined;
export function findEnvKeys(provider: string, env?: ProviderEnv): string[] | undefined;
export function findEnvKeys(provider: string, env?: ProviderEnv): string[] | undefined {
const envVars = getApiKeyEnvVars(provider);
if (!envVars) return undefined;
const found = envVars.filter((envVar) => !!process.env[envVar] || !!getProcEnv(envVar));
const found = envVars.filter((envVar) => !!getProviderEnvValue(envVar, env));
return found.length > 0 ? found : undefined;
}
@@ -158,25 +131,22 @@ export function findEnvKeys(provider: string): string[] | undefined {
*
* Will not return API keys for providers that require OAuth tokens.
*/
export function getEnvApiKey(provider: KnownProvider): string | undefined;
export function getEnvApiKey(provider: string): string | undefined;
export function getEnvApiKey(provider: string): string | undefined {
const envKeys = findEnvKeys(provider);
export function getEnvApiKey(provider: KnownProvider, env?: ProviderEnv): string | undefined;
export function getEnvApiKey(provider: string, env?: ProviderEnv): string | undefined;
export function getEnvApiKey(provider: string, env?: ProviderEnv): string | undefined {
const envKeys = findEnvKeys(provider, env);
if (envKeys?.[0]) {
return process.env[envKeys[0]] || getProcEnv(envKeys[0]);
return getProviderEnvValue(envKeys[0], env);
}
// Vertex AI supports either an explicit API key or Application Default Credentials.
// Auth is configured via `gcloud auth application-default login`.
if (provider === "google-vertex") {
const hasCredentials = hasVertexAdcCredentials();
const hasCredentials = hasVertexAdcCredentials(env);
const hasProject = !!(
process.env.GOOGLE_CLOUD_PROJECT ||
process.env.GCLOUD_PROJECT ||
getProcEnv("GOOGLE_CLOUD_PROJECT") ||
getProcEnv("GCLOUD_PROJECT")
getProviderEnvValue("GOOGLE_CLOUD_PROJECT", env) || getProviderEnvValue("GCLOUD_PROJECT", env)
);
const hasLocation = !!(process.env.GOOGLE_CLOUD_LOCATION || getProcEnv("GOOGLE_CLOUD_LOCATION"));
const hasLocation = !!getProviderEnvValue("GOOGLE_CLOUD_LOCATION", env);
if (hasCredentials && hasProject && hasLocation) {
return "<authenticated>";
@@ -192,18 +162,12 @@ export function getEnvApiKey(provider: string): string | undefined {
// 5. AWS_CONTAINER_CREDENTIALS_FULL_URI - ECS task roles (full URI)
// 6. AWS_WEB_IDENTITY_TOKEN_FILE - IRSA (IAM Roles for Service Accounts)
if (
process.env.AWS_PROFILE ||
(process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
process.env.AWS_BEARER_TOKEN_BEDROCK ||
process.env.AWS_CONTAINER_CREDENTIALS_RELATIVE_URI ||
process.env.AWS_CONTAINER_CREDENTIALS_FULL_URI ||
process.env.AWS_WEB_IDENTITY_TOKEN_FILE ||
getProcEnv("AWS_PROFILE") ||
(getProcEnv("AWS_ACCESS_KEY_ID") && getProcEnv("AWS_SECRET_ACCESS_KEY")) ||
getProcEnv("AWS_BEARER_TOKEN_BEDROCK") ||
getProcEnv("AWS_CONTAINER_CREDENTIALS_RELATIVE_URI") ||
getProcEnv("AWS_CONTAINER_CREDENTIALS_FULL_URI") ||
getProcEnv("AWS_WEB_IDENTITY_TOKEN_FILE")
getProviderEnvValue("AWS_PROFILE", env) ||
(getProviderEnvValue("AWS_ACCESS_KEY_ID", env) && getProviderEnvValue("AWS_SECRET_ACCESS_KEY", env)) ||
getProviderEnvValue("AWS_BEARER_TOKEN_BEDROCK", env) ||
getProviderEnvValue("AWS_CONTAINER_CREDENTIALS_RELATIVE_URI", env) ||
getProviderEnvValue("AWS_CONTAINER_CREDENTIALS_FULL_URI", env) ||
getProviderEnvValue("AWS_WEB_IDENTITY_TOKEN_FILE", env)
) {
return "<authenticated>";
}
packages/ai/src/image-models.generated.ts
+30
View File
@@ -95,6 +95,21 @@ export const IMAGE_MODELS = {
cacheWrite: 0.08333333333333334,
},
} satisfies ImagesModel<"openrouter-images">,
"google/gemini-3-pro-image": {
id: "google/gemini-3-pro-image",
name: "Google: Nano Banana Pro (Gemini 3 Pro Image)",
api: "openrouter-images",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
input: ["image", "text"],
output: ["image", "text"],
cost: {
input: 2,
output: 12,
cacheRead: 0.19999999999999998,
cacheWrite: 0.375,
},
} satisfies ImagesModel<"openrouter-images">,
"google/gemini-3-pro-image-preview": {
id: "google/gemini-3-pro-image-preview",
name: "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
@@ -110,6 +125,21 @@ export const IMAGE_MODELS = {
cacheWrite: 0.375,
},
} satisfies ImagesModel<"openrouter-images">,
"google/gemini-3.1-flash-image": {
id: "google/gemini-3.1-flash-image",
name: "Google: Nano Banana 2 (Gemini 3.1 Flash Image)",
api: "openrouter-images",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
input: ["image", "text"],
output: ["image", "text"],
cost: {
input: 0.5,
output: 3,
cacheRead: 0,
cacheWrite: 0,
},
} satisfies ImagesModel<"openrouter-images">,
"google/gemini-3.1-flash-image-preview": {
id: "google/gemini-3.1-flash-image-preview",
name: "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)",
packages/ai/src/models.ts
+4 -1
View File
@@ -372,10 +372,13 @@ export function hasApi<TApi extends Api>(model: Model<Api>, api: TApi): model is
}
export function calculateCost<TApi extends Api>(model: Model<TApi>, usage: Usage): Usage["cost"] {
// Anthropic charges 2x base input for 1h cache writes.
const longWrite = usage.cacheWrite1h ?? 0;
const shortWrite = usage.cacheWrite - longWrite;
usage.cost.input = (model.cost.input / 1000000) * usage.input;
usage.cost.output = (model.cost.output / 1000000) * usage.output;
usage.cost.cacheRead = (model.cost.cacheRead / 1000000) * usage.cacheRead;
usage.cost.cacheWrite = (model.cost.cacheWrite / 1000000) * usage.cacheWrite;
usage.cost.cacheWrite = (model.cost.cacheWrite * shortWrite + model.cost.input * 2 * longWrite) / 1000000;
usage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;
return usage.cost;
}
packages/ai/src/providers/cerebras.models.ts
+5 -22
View File
@@ -13,30 +13,13 @@ export const CEREBRAS_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.25,
output: 0.69,
input: 0.35,
output: 0.75,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"llama3.1-8b": {
id: "llama3.1-8b",
name: "Llama 3.1 8B",
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: false,
input: ["text"],
cost: {
input: 0.1,
output: 0.1,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 32000,
maxTokens: 8000,
maxTokens: 40960,
} satisfies Model<"openai-completions">,
"zai-glm-4.7": {
id: "zai-glm-4.7",
@@ -44,7 +27,7 @@ export const CEREBRAS_MODELS = {
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: false,
reasoning: true,
input: ["text"],
cost: {
input: 2.25,
@@ -53,6 +36,6 @@ export const CEREBRAS_MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 40000,
maxTokens: 40960,
} satisfies Model<"openai-completions">,
} as const;
packages/ai/src/providers/cloudflare-workers-ai.models.ts
+36
View File
@@ -112,6 +112,24 @@ export const CLOUDFLARE_WORKERS_AI_MODELS = {
contextWindow: 262144,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
"@cf/moonshotai/kimi-k2.7-code": {
id: "@cf/moonshotai/kimi-k2.7-code",
name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "cloudflare-workers-ai",
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"@cf/nvidia/nemotron-3-120b-a12b": {
id: "@cf/nvidia/nemotron-3-120b-a12b",
name: "Nemotron 3 Super 120B",
@@ -202,4 +220,22 @@ export const CLOUDFLARE_WORKERS_AI_MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"@cf/zai-org/glm-5.2": {
id: "@cf/zai-org/glm-5.2",
name: "Glm 5.2",
api: "openai-completions",
provider: "cloudflare-workers-ai",
baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
} as const;
packages/ai/src/providers/fireworks.models.ts
+71 -34
View File
@@ -16,7 +16,7 @@ export const FIREWORKS_MODELS = {
cost: {
input: 0.14,
output: 0.28,
cacheRead: 0.03,
cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -58,6 +58,25 @@ export const FIREWORKS_MODELS = {
contextWindow: 202800,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/glm-5p2": {
id: "accounts/fireworks/models/glm-5p2",
name: "GLM 5.2",
api: "openai-completions",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false},
reasoning: true,
thinkingLevelMap: {"off":"none","minimal":null,"low":"high","medium":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"accounts/fireworks/models/gpt-oss-120b": {
id: "accounts/fireworks/models/gpt-oss-120b",
name: "GPT OSS 120B",
@@ -94,24 +113,6 @@ export const FIREWORKS_MODELS = {
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/kimi-k2p5": {
id: "accounts/fireworks/models/kimi-k2p5",
name: "Kimi K2.5",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.6,
output: 3,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/kimi-k2p6": {
id: "accounts/fireworks/models/kimi-k2p6",
name: "Kimi K2.6",
@@ -130,23 +131,23 @@ export const FIREWORKS_MODELS = {
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m2p5": {
id: "accounts/fireworks/models/minimax-m2p5",
name: "MiniMax-M2.5",
"accounts/fireworks/models/kimi-k2p7-code": {
id: "accounts/fireworks/models/kimi-k2p7-code",
name: "Kimi K2.7 Code",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
input: ["text", "image"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.03,
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 196608,
maxTokens: 196608,
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m2p7": {
id: "accounts/fireworks/models/minimax-m2p7",
@@ -166,9 +167,27 @@ export const FIREWORKS_MODELS = {
contextWindow: 196608,
maxTokens: 196608,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/qwen3p6-plus": {
id: "accounts/fireworks/models/qwen3p6-plus",
name: "Qwen 3.6 Plus",
"accounts/fireworks/models/minimax-m3": {
id: "accounts/fireworks/models/minimax-m3",
name: "MiniMax-M3",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 512000,
maxTokens: 512000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/qwen3p7-plus": {
id: "accounts/fireworks/models/qwen3p7-plus",
name: "Qwen 3.7 Plus",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
@@ -176,9 +195,9 @@ export const FIREWORKS_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.5,
output: 3,
cacheRead: 0.1,
input: 0.4,
output: 1.6,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -238,4 +257,22 @@ export const FIREWORKS_MODELS = {
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/routers/kimi-k2p7-code-fast": {
id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
name: "Kimi K2.7 Code Fast",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
compat: {"sendSessionAffinityHeaders":true,"supportsEagerToolInputStreaming":false,"supportsCacheControlOnTools":false,"supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
} as const;
packages/ai/src/providers/fireworks.ts
+6 -2
View File
@@ -1,15 +1,19 @@
import { anthropicMessagesApi } from "../api/anthropic-messages.lazy.ts";
import { openAICompletionsApi } from "../api/openai-completions.lazy.ts";
import { envApiKeyAuth } from "../auth/helpers.ts";
import { createProvider, type Provider } from "../models.ts";
import { FIREWORKS_MODELS } from "./fireworks.models.ts";
export function fireworksProvider(): Provider<"anthropic-messages"> {
export function fireworksProvider(): Provider<"anthropic-messages" | "openai-completions"> {
return createProvider({
id: "fireworks",
name: "Fireworks",
baseUrl: "https://api.fireworks.ai/inference",
auth: { apiKey: envApiKeyAuth("Fireworks API key", ["FIREWORKS_API_KEY"]) },
models: Object.values(FIREWORKS_MODELS),
api: anthropicMessagesApi(),
api: {
"anthropic-messages": anthropicMessagesApi(),
"openai-completions": openAICompletionsApi(),
},
});
}
packages/ai/src/providers/github-copilot.models.ts
+22 -21
View File
@@ -4,6 +4,25 @@
import type { Model } from "../types.ts";
export const GITHUB_COPILOT_MODELS = {
"claude-fable-5": {
id: "claude-fable-5",
name: "Claude Fable 5",
api: "openai-completions",
provider: "github-copilot",
baseUrl: "https://api.individual.githubcopilot.com",
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 10,
output: 50,
cacheRead: 1,
cacheWrite: 12.5,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"claude-haiku-4.5": {
id: "claude-haiku-4.5",
name: "Claude Haiku 4.5 (latest)",
@@ -70,7 +89,7 @@ export const GITHUB_COPILOT_MODELS = {
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
reasoning: true,
thinkingLevelMap: {"xhigh":"xhigh"},
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
input: ["text", "image"],
cost: {
input: 5,
@@ -90,7 +109,7 @@ export const GITHUB_COPILOT_MODELS = {
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
compat: {"forceAdaptiveThinking":true,"supportsTemperature":false},
reasoning: true,
thinkingLevelMap: {"xhigh":"xhigh"},
thinkingLevelMap: {"xhigh":"xhigh","minimal":"low"},
input: ["text", "image"],
cost: {
input: 5,
@@ -148,6 +167,7 @@ export const GITHUB_COPILOT_MODELS = {
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
compat: {"forceAdaptiveThinking":true},
reasoning: true,
thinkingLevelMap: {"minimal":"low","xhigh":"max"},
input: ["text", "image"],
cost: {
input: 3,
@@ -405,23 +425,4 @@ export const GITHUB_COPILOT_MODELS = {
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"raptor-mini": {
id: "raptor-mini",
name: "Raptor mini",
api: "openai-completions",
provider: "github-copilot",
baseUrl: "https://api.individual.githubcopilot.com",
headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.25,
output: 2,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
} as const;
packages/ai/src/providers/google-vertex.models.ts
+69 -117
View File
@@ -4,94 +4,9 @@
import type { Model } from "../types.ts";
export const GOOGLE_VERTEX_MODELS = {
"gemini-1.5-flash": {
id: "gemini-1.5-flash",
name: "Gemini 1.5 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.075,
output: 0.3,
cacheRead: 0.01875,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-1.5-flash-8b": {
id: "gemini-1.5-flash-8b",
name: "Gemini 1.5 Flash-8B (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.0375,
output: 0.15,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-1.5-pro": {
id: "gemini-1.5-pro",
name: "Gemini 1.5 Pro (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 1.25,
output: 5,
cacheRead: 0.3125,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-2.0-flash": {
id: "gemini-2.0-flash",
name: "Gemini 2.0 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.0375,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-2.0-flash-lite": {
id: "gemini-2.0-flash-lite",
name: "Gemini 2.0 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.075,
output: 0.3,
cacheRead: 0.01875,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-2.5-flash": {
id: "gemini-2.5-flash",
name: "Gemini 2.5 Flash (Vertex)",
name: "Gemini 2.5 Flash",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -108,24 +23,7 @@ export const GOOGLE_VERTEX_MODELS = {
} satisfies Model<"google-vertex">,
"gemini-2.5-flash-lite": {
id: "gemini-2.5-flash-lite",
name: "Gemini 2.5 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.1,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-2.5-flash-lite-preview-09-2025": {
id: "gemini-2.5-flash-lite-preview-09-2025",
name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
name: "Gemini 2.5 Flash-Lite",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -142,7 +40,7 @@ export const GOOGLE_VERTEX_MODELS = {
} satisfies Model<"google-vertex">,
"gemini-2.5-pro": {
id: "gemini-2.5-pro",
name: "Gemini 2.5 Pro (Vertex)",
name: "Gemini 2.5 Pro",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -159,7 +57,7 @@ export const GOOGLE_VERTEX_MODELS = {
} satisfies Model<"google-vertex">,
"gemini-3-flash-preview": {
id: "gemini-3-flash-preview",
name: "Gemini 3 Flash Preview (Vertex)",
name: "Gemini 3 Flash Preview",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -175,27 +73,27 @@ export const GOOGLE_VERTEX_MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3-pro-preview": {
id: "gemini-3-pro-preview",
name: "Gemini 3 Pro Preview (Vertex)",
"gemini-3.1-flash-lite": {
id: "gemini-3.1-flash-lite",
name: "Gemini 3.1 Flash Lite",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 2,
output: 12,
cacheRead: 0.2,
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 64000,
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3.1-pro-preview": {
id: "gemini-3.1-pro-preview",
name: "Gemini 3.1 Pro Preview (Vertex)",
name: "Gemini 3.1 Pro Preview",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -213,7 +111,7 @@ export const GOOGLE_VERTEX_MODELS = {
} satisfies Model<"google-vertex">,
"gemini-3.1-pro-preview-customtools": {
id: "gemini-3.1-pro-preview-customtools",
name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
name: "Gemini 3.1 Pro Preview Custom Tools",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -229,4 +127,58 @@ export const GOOGLE_VERTEX_MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3.5-flash": {
id: "gemini-3.5-flash",
name: "Gemini 3.5 Flash",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-flash-latest": {
id: "gemini-flash-latest",
name: "Gemini Flash Latest",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-flash-lite-latest": {
id: "gemini-flash-lite-latest",
name: "Gemini Flash-Lite Latest",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
} as const;
packages/ai/src/providers/google.models.ts
+7 -5
View File
@@ -222,11 +222,12 @@ export const GOOGLE_MODELS = {
provider: "google",
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.3,
output: 2.5,
cacheRead: 0.075,
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -239,10 +240,11 @@ export const GOOGLE_MODELS = {
provider: "google",
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.1,
output: 0.4,
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
packages/ai/src/providers/kimi-coding.models.ts
+18
View File
@@ -4,6 +4,24 @@
import type { Model } from "../types.ts";
export const KIMI_CODING_MODELS = {
"k2p7": {
id: "k2p7",
name: "Kimi K2.7 Code",
api: "anthropic-messages",
provider: "kimi-coding",
baseUrl: "https://api.kimi.com/coding",
headers: {"User-Agent":"KimiCLI/1.5"},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"kimi-for-coding": {
id: "kimi-for-coding",
name: "Kimi For Coding",
packages/ai/src/providers/mistral.models.ts
+28 -28
View File
@@ -15,7 +15,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.3,
output: 0.9,
cacheRead: 0,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -32,7 +32,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -49,7 +49,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -66,7 +66,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -83,7 +83,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -100,7 +100,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -117,7 +117,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -151,7 +151,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 2,
output: 5,
cacheRead: 0,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -168,7 +168,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -185,7 +185,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.04,
output: 0.04,
cacheRead: 0,
cacheRead: 0.004,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -202,7 +202,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.1,
output: 0.1,
cacheRead: 0,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -219,7 +219,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 2,
output: 6,
cacheRead: 0,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 131072,
@@ -236,7 +236,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -253,7 +253,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -270,7 +270,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 131072,
@@ -287,7 +287,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -304,7 +304,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 1.5,
output: 7.5,
cacheRead: 0,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -338,7 +338,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.4,
output: 2,
cacheRead: 0,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -355,7 +355,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -372,7 +372,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -389,7 +389,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -406,7 +406,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -423,7 +423,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.25,
output: 0.25,
cacheRead: 0,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 8000,
@@ -440,7 +440,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -457,7 +457,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 2,
output: 6,
cacheRead: 0,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 64000,
@@ -474,7 +474,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.7,
output: 0.7,
cacheRead: 0,
cacheRead: 0.07,
cacheWrite: 0,
},
contextWindow: 32000,
@@ -491,7 +491,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -508,7 +508,7 @@ export const MISTRAL_MODELS = {
cost: {
input: 2,
output: 6,
cacheRead: 0,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 128000,
packages/ai/src/providers/moonshotai-cn.models.ts
+38
View File
@@ -130,4 +130,42 @@ export const MOONSHOTAI_CN_MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code": {
id: "kimi-k2.7-code",
name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "moonshotai-cn",
baseUrl: "https://api.moonshot.cn/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code-highspeed": {
id: "kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code HighSpeed",
api: "openai-completions",
provider: "moonshotai-cn",
baseUrl: "https://api.moonshot.cn/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
} as const;
packages/ai/src/providers/moonshotai.models.ts
+38
View File
@@ -130,4 +130,42 @@ export const MOONSHOTAI_MODELS = {
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code": {
id: "kimi-k2.7-code",
name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code-highspeed": {
id: "kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code HighSpeed",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"deepseek"},
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
} as const;
packages/ai/src/providers/nvidia.models.ts
-19
View File
@@ -289,25 +289,6 @@ export const NVIDIA_MODELS = {
contextWindow: 131072,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder-480b-a35b-instruct": {
id: "qwen/qwen3-coder-480b-a35b-instruct",
name: "Qwen3 Coder 480B A35B Instruct",
api: "openai-completions",
provider: "nvidia",
baseUrl: "https://integrate.api.nvidia.com/v1",
headers: {"NVCF-POLL-SECONDS":"3600"},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 66536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-122b-a10b": {
id: "qwen/qwen3.5-122b-a10b",
name: "Qwen3.5 122B-A10B",
packages/ai/src/providers/opencode-go.models.ts
+32 -49
View File
@@ -42,24 +42,6 @@ export const OPENCODE_GO_MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"openai-completions">,
"glm-5": {
id: "glm-5",
name: "GLM-5",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"maxTokensField":"max_tokens"},
reasoning: true,
input: ["text"],
cost: {
input: 1,
output: 3.2,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"glm-5.1": {
id: "glm-5.1",
name: "GLM-5.1",
@@ -78,23 +60,23 @@ export const OPENCODE_GO_MODELS = {
contextWindow: 202752,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"kimi-k2.5": {
id: "kimi-k2.5",
name: "Kimi K2.5",
"glm-5.2": {
id: "glm-5.2",
name: "GLM-5.2",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"maxTokensField":"max_tokens"},
reasoning: true,
input: ["text", "image"],
input: ["text"],
cost: {
input: 0.6,
output: 3,
cacheRead: 0.1,
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"kimi-k2.6": {
id: "kimi-k2.6",
@@ -102,7 +84,7 @@ export const OPENCODE_GO_MODELS = {
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens"},
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
@@ -115,6 +97,24 @@ export const OPENCODE_GO_MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"kimi-k2.7-code": {
id: "kimi-k2.7-code",
name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"maxTokensField":"max_tokens"},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"mimo-v2.5": {
id: "mimo-v2.5",
name: "MiMo V2.5",
@@ -151,23 +151,6 @@ export const OPENCODE_GO_MODELS = {
contextWindow: 1048576,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"minimax-m2.5": {
id: "minimax-m2.5",
name: "MiniMax M2.5",
api: "anthropic-messages",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go",
reasoning: true,
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 65536,
} satisfies Model<"anthropic-messages">,
"minimax-m2.7": {
id: "minimax-m2.7",
name: "MiniMax M2.7",
@@ -188,16 +171,16 @@ export const OPENCODE_GO_MODELS = {
} satisfies Model<"openai-completions">,
"minimax-m3": {
id: "minimax-m3",
name: "MiniMax M3",
name: "MiniMax M3 (3x usage)",
api: "anthropic-messages",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
input: 0.1,
output: 0.4,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 512000,
packages/ai/src/providers/opencode.models.ts
+6 -25
View File
@@ -22,25 +22,6 @@ export const OPENCODE_MODELS = {
contextWindow: 200000,
maxTokens: 32000,
} satisfies Model<"openai-completions">,
"claude-fable-5": {
id: "claude-fable-5",
name: "Claude Fable 5",
api: "anthropic-messages",
provider: "opencode",
baseUrl: "https://opencode.ai/zen",
compat: {"forceAdaptiveThinking":true},
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 10,
output: 50,
cacheRead: 1,
cacheWrite: 12.5,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"claude-haiku-4-5": {
id: "claude-haiku-4-5",
name: "Claude Haiku 4.5",
@@ -207,7 +188,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -226,7 +207,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -245,7 +226,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -661,7 +642,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
@@ -679,7 +660,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens"},
compat: {"thinkingFormat":"deepseek","supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
reasoning: true,
input: ["text", "image"],
cost: {
@@ -733,7 +714,7 @@ export const OPENCODE_MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false},
reasoning: true,
input: ["text"],
cost: {
packages/ai/src/providers/openrouter.models.ts
+306 -203
View File
File diff suppressed because it is too large Load Diff
packages/ai/src/providers/together.models.ts
+107 -109
View File
@@ -4,25 +4,6 @@
import type { Model } from "../types.ts";
export const TOGETHER_MODELS = {
"MiniMaxAI/MiniMax-M2.5": {
id: "MiniMaxAI/MiniMax-M2.5",
name: "MiniMax-M2.5",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"MiniMaxAI/MiniMax-M2.7": {
id: "MiniMaxAI/MiniMax-M2.7",
name: "MiniMax-M2.7",
@@ -42,28 +23,28 @@ export const TOGETHER_MODELS = {
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
name: "Qwen3 235B A22B Instruct 2507 FP8",
"MiniMaxAI/MiniMax-M3": {
id: "MiniMaxAI/MiniMax-M3",
name: "MiniMax-M3",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.6,
cacheRead: 0,
input: 0.3,
output: 1.2,
cacheRead: 0.06,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 524288,
maxTokens: 250000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
name: "Qwen3 Coder 480B A35B Instruct",
"Qwen/Qwen2.5-7B-Instruct-Turbo": {
id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
name: "Qwen 2.5 7B Instruct Turbo",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
@@ -71,27 +52,26 @@ export const TOGETHER_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 2,
output: 2,
input: 0.3,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
contextWindow: 32768,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3-Coder-Next-FP8": {
id: "Qwen/Qwen3-Coder-Next-FP8",
name: "Qwen3 Coder Next FP8",
"Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
name: "Qwen3 235B A22B Instruct 2507 FP8",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 0.5,
output: 1.2,
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
},
@@ -117,6 +97,25 @@ export const TOGETHER_MODELS = {
contextWindow: 262144,
maxTokens: 130000,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.5-9B": {
id: "Qwen/Qwen3.5-9B",
name: "Qwen3.5 9B",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.17,
output: 0.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"Qwen/Qwen3.6-Plus": {
id: "Qwen/Qwen3.6-Plus",
name: "Qwen3.6 Plus",
@@ -142,57 +141,18 @@ export const TOGETHER_MODELS = {
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},
reasoning: false,
input: ["text"],
cost: {
input: 2.5,
output: 7.5,
input: 1.25,
output: 3.75,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 500000,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3": {
id: "deepseek-ai/DeepSeek-V3",
name: "DeepSeek-V3",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 1.25,
output: 1.25,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V3-1": {
id: "deepseek-ai/DeepSeek-V3-1",
name: "DeepSeek V3.1",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.6,
output: 1.7,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"deepseek-ai/DeepSeek-V4-Pro": {
id: "deepseek-ai/DeepSeek-V4-Pro",
name: "DeepSeek V4 Pro",
@@ -204,8 +164,8 @@ export const TOGETHER_MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null},
input: ["text"],
cost: {
input: 2.1,
output: 4.4,
input: 1.74,
output: 3.48,
cacheRead: 0.2,
cacheWrite: 0,
},
@@ -241,8 +201,8 @@ export const TOGETHER_MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.2,
output: 0.5,
input: 0.39,
output: 0.97,
cacheRead: 0,
cacheWrite: 0,
},
@@ -267,25 +227,6 @@ export const TOGETHER_MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.5": {
id: "moonshotai/Kimi-K2.5",
name: "Kimi K2.5",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text", "image"],
cost: {
input: 0.5,
output: 2.8,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.6": {
id: "moonshotai/Kimi-K2.6",
name: "Kimi K2.6",
@@ -305,6 +246,25 @@ export const TOGETHER_MODELS = {
contextWindow: 262144,
maxTokens: 131000,
} satisfies Model<"openai-completions">,
"moonshotai/Kimi-K2.7-Code": {
id: "moonshotai/Kimi-K2.7-Code",
name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b": {
id: "nvidia/nemotron-3-ultra-550b-a55b",
name: "Nemotron 3 Ultra 550B A55B",
@@ -343,6 +303,44 @@ export const TOGETHER_MODELS = {
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
name: "GPT OSS 20B",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null},
input: ["text"],
cost: {
input: 0.05,
output: 0.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5": {
id: "zai-org/GLM-5",
name: "GLM-5",
api: "openai-completions",
provider: "together",
baseUrl: "https://api.together.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false,"thinkingFormat":"together"},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null},
input: ["text"],
cost: {
input: 1,
output: 3.2,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"zai-org/GLM-5.1": {
id: "zai-org/GLM-5.1",
name: "GLM-5.1",
packages/ai/src/providers/vercel-ai-gateway.models.ts
+145 -130
View File
@@ -98,7 +98,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 4,
cacheRead: 0,
cacheWrite: 0,
@@ -168,7 +168,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -268,7 +268,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 4,
cacheRead: 0,
cacheWrite: 0,
@@ -285,8 +285,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
input: 0.1,
output: 0.4,
cacheRead: 0.001,
cacheWrite: 0.125,
},
@@ -302,7 +302,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2.4,
cacheRead: 0.04,
cacheWrite: 0.5,
@@ -320,7 +320,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.6,
output: 3.5999999999999996,
output: 3.6,
cacheRead: 0,
cacheWrite: 0,
},
@@ -338,7 +338,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.5,
output: 3,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 0.625,
},
contextWindow: 1000000,
@@ -370,8 +370,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
output: 1.5999999999999999,
input: 0.4,
output: 1.6,
cacheRead: 0.08,
cacheWrite: 0.5,
},
@@ -404,7 +404,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.7999999999999999,
input: 0.8,
output: 4,
cacheRead: 0.08,
cacheWrite: 1,
@@ -412,25 +412,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-fable-5": {
id: "anthropic/claude-fable-5",
name: "Claude Fable 5",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
compat: {"forceAdaptiveThinking":true},
reasoning: true,
thinkingLevelMap: {"off":null,"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 10,
output: 50,
cacheRead: 1,
cacheWrite: 12.5,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"anthropic/claude-haiku-4.5": {
id: "anthropic/claude-haiku-4.5",
name: "Claude Haiku 4.5",
@@ -442,7 +423,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 5,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 1.25,
},
contextWindow: 200000,
@@ -635,7 +616,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.25,
output: 0.8999999999999999,
output: 0.9,
cacheRead: 0,
cacheWrite: 0,
},
@@ -653,7 +634,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -838,8 +819,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
input: 0.1,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
@@ -874,7 +855,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.5,
output: 3,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -891,7 +872,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 2,
output: 12,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -942,7 +923,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 2,
output: 12,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -992,7 +973,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.14,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1010,7 +991,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 0.75,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -1162,7 +1143,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.24,
output: 0.9700000000000001,
output: 0.97,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1178,7 +1159,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.16999999999999998,
input: 0.17,
output: 0.66,
cacheRead: 0,
cacheWrite: 0,
@@ -1332,7 +1313,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.3,
output: 0.8999999999999999,
output: 0.9,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1348,7 +1329,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2,
cacheRead: 0,
cacheWrite: 0,
@@ -1365,7 +1346,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1382,7 +1363,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1399,8 +1380,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.09999999999999999,
output: 0.09999999999999999,
input: 0.1,
output: 0.1,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1433,7 +1414,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
input: 0.4,
output: 2,
cacheRead: 0,
cacheWrite: 0,
@@ -1467,13 +1448,13 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.02,
output: 0.04,
input: 0.15,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"mistral/mistral-small": {
id: "mistral/mistral-small",
@@ -1484,7 +1465,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1535,7 +1516,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text"],
cost: {
input: 0.5700000000000001,
input: 0.57,
output: 2.3,
cacheRead: 0,
cacheWrite: 0,
@@ -1560,40 +1541,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-thinking-turbo": {
id: "moonshotai/kimi-k2-thinking-turbo",
name: "Kimi K2 Thinking Turbo",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.15,
output: 8,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 262114,
maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2-turbo": {
id: "moonshotai/kimi-k2-turbo",
name: "Kimi K2 Turbo",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
input: ["text"],
cost: {
input: 1.15,
output: 8,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.5": {
id: "moonshotai/kimi-k2.5",
name: "Kimi K2.5",
@@ -1605,7 +1552,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.6,
output: 3,
cacheRead: 0.09999999999999999,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 262114,
@@ -1628,6 +1575,40 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 262000,
maxTokens: 262000,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.7-code": {
id: "moonshotai/kimi-k2.7-code",
name: "Kimi K2.7 Code",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.7-code-highspeed": {
id: "moonshotai/kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code High Speed",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"nvidia/nemotron-3-super-120b-a12b": {
id: "nvidia/nemotron-3-super-120b-a12b",
name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -1671,7 +1652,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.6,
cacheRead: 0,
cacheWrite: 0,
@@ -1689,7 +1670,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.06,
output: 0.22999999999999998,
output: 0.23,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1739,9 +1720,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
output: 1.5999999999999999,
cacheRead: 0.09999999999999999,
input: 0.4,
output: 1.6,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 1047576,
@@ -1756,9 +1737,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
cacheRead: 0.024999999999999998,
input: 0.1,
output: 0.4,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1047576,
@@ -1860,7 +1841,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -1875,8 +1856,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.049999999999999996,
output: 0.39999999999999997,
input: 0.05,
output: 0.4,
cacheRead: 0.005,
cacheWrite: 0,
},
@@ -1945,7 +1926,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.25,
output: 2,
cacheRead: 0.024999999999999998,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -2139,7 +2120,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
thinkingLevelMap: {"xhigh":"xhigh"},
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.25,
cacheRead: 0.02,
cacheWrite: 0,
@@ -2227,8 +2208,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.049999999999999996,
output: 0.19999999999999998,
input: 0.05,
output: 0.2,
cacheRead: 0,
cacheWrite: 0,
},
@@ -2388,6 +2369,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 200000,
maxTokens: 8000,
} satisfies Model<"anthropic-messages">,
"sakana/fugu-ultra": {
id: "sakana/fugu-ultra",
name: "Fugu Ultra",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 1000000,
} satisfies Model<"anthropic-messages">,
"stepfun/step-3.5-flash": {
id: "stepfun/step-3.5-flash",
name: "StepFun 3.5 Flash",
@@ -2399,8 +2397,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 0.09,
output: 0.3,
cacheRead: 0,
cacheWrite: 0.02,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 262114,
maxTokens: 262114,
@@ -2414,7 +2412,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.15,
cacheRead: 0.04,
cacheWrite: 0,
@@ -2431,9 +2429,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.5,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2448,9 +2446,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 0.5,
cacheRead: 0.049999999999999996,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2467,7 +2465,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2484,7 +2482,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2501,7 +2499,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2518,7 +2516,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2535,7 +2533,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2552,7 +2550,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 2000000,
@@ -2569,7 +2567,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1.25,
output: 2.5,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2586,7 +2584,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 2,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -2601,7 +2599,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.09999999999999999,
input: 0.1,
output: 0.3,
cacheRead: 0.01,
cacheWrite: 0,
@@ -2620,7 +2618,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
cost: {
input: 1,
output: 3,
cacheRead: 0.19999999999999998,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -2686,7 +2684,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.19999999999999998,
input: 0.2,
output: 1.1,
cacheRead: 0.03,
cacheWrite: 0,
@@ -2704,7 +2702,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.6,
output: 1.7999999999999998,
output: 1.8,
cacheRead: 0.11,
cacheWrite: 0,
},
@@ -2738,8 +2736,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text", "image"],
cost: {
input: 0.3,
output: 0.8999999999999999,
cacheRead: 0.049999999999999996,
output: 0.9,
cacheRead: 0.05,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -2789,7 +2787,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.07,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
@@ -2806,7 +2804,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 0.06,
output: 0.39999999999999997,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
@@ -2823,8 +2821,8 @@ export const VERCEL_AI_GATEWAY_MODELS = {
input: ["text"],
cost: {
input: 1,
output: 3.1999999999999997,
cacheRead: 0.19999999999999998,
output: 3.2,
cacheRead: 0.2,
cacheWrite: 0,
},
contextWindow: 202800,
@@ -2864,6 +2862,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
contextWindow: 202800,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"zai/glm-5.2": {
id: "zai/glm-5.2",
name: "GLM 5.2",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.5,
output: 4.5,
cacheRead: 0.3,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"zai/glm-5v-turbo": {
id: "zai/glm-5v-turbo",
name: "GLM 5V Turbo",
packages/ai/src/providers/zai-coding-cn.models.ts
+19
View File
@@ -76,6 +76,25 @@ export const ZAI_CODING_CN_MODELS = {
contextWindow: 200000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5.2": {
id: "glm-5.2",
name: "GLM-5.2",
api: "openai-completions",
provider: "zai-coding-cn",
baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5v-turbo": {
id: "glm-5v-turbo",
name: "GLM-5V-Turbo",
packages/ai/src/providers/zai.models.ts
+19
View File
@@ -76,6 +76,25 @@ export const ZAI_MODELS = {
contextWindow: 200000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5.2": {
id: "glm-5.2",
name: "GLM-5.2",
api: "openai-completions",
provider: "zai",
baseUrl: "https://api.z.ai/api/coding/paas/v4",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai","supportsReasoningEffort":true,"zaiToolStream":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":"high","medium":"high","high":"high","xhigh":"max"},
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"glm-5v-turbo": {
id: "glm-5v-turbo",
name: "GLM-5V-Turbo",
packages/ai/src/types.ts
+24 -1
View File
@@ -74,6 +74,15 @@ export type ImagesProviderId = KnownImagesProvider | string;
export type ThinkingLevel = "minimal" | "low" | "medium" | "high" | "xhigh";
export type ModelThinkingLevel = "off" | ThinkingLevel;
export type ThinkingLevelMap = Partial<Record<ModelThinkingLevel, string | null>>;
export type ChatTemplateKwargValue =
| string
| number
| boolean
| null
| {
$var: "thinking.enabled" | "thinking.effort";
omitWhenOff?: boolean;
};
/** Token budgets for each thinking level (token-based providers only) */
export interface ThinkingBudgets {
@@ -88,6 +97,9 @@ export type CacheRetention = "none" | "short" | "long";
export type Transport = "sse" | "websocket" | "websocket-cached" | "auto";
/** Provider-scoped environment overrides. Values take precedence over process.env. */
export type ProviderEnv = Record<string, string>;
export interface ProviderResponse {
status: number;
headers: Record<string, string>;
@@ -162,6 +174,12 @@ export interface StreamOptions {
* For example, Anthropic uses `user_id` for abuse tracking and rate limiting.
*/
metadata?: Record<string, unknown>;
/**
* Provider-scoped environment values. These take precedence over process.env for
* provider configuration such as regional settings, endpoint placeholders, and
* proxy variables.
*/
env?: ProviderEnv;
}
export type ProviderStreamOptions = StreamOptions & Record<string, unknown>;
@@ -328,6 +346,8 @@ export interface Usage {
output: number;
cacheRead: number;
cacheWrite: number;
/** Subset of `cacheWrite` written with 1h retention. Only Anthropic reports this split. */
cacheWrite1h?: number;
totalTokens: number;
cost: {
input: number;
@@ -453,7 +473,7 @@ export interface OpenAICompletionsCompat {
requiresThinkingAsText?: boolean;
/** Whether all replayed assistant messages must include an empty reasoning_content field when reasoning is enabled. Default: auto-detected from URL. */
requiresReasoningContentOnAssistantMessages?: boolean;
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort when supported, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses thinking: { type }, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking, "string-thinking" uses top-level thinking: string, and "ant-ling" uses reasoning: { effort } only when the mapped effort is non-null. Default: "openai". */
/** Format for reasoning/thinking parameter. "openai" uses reasoning_effort, "openrouter" uses reasoning: { effort }, "deepseek" uses thinking: { type } plus reasoning_effort when supported, "together" uses reasoning: { enabled } plus reasoning_effort when supported, "zai" uses thinking: { type }, "qwen" uses top-level enable_thinking: boolean, "qwen-chat-template" uses chat_template_kwargs.enable_thinking and preserve_thinking, "chat-template" uses configurable chat_template_kwargs, "string-thinking" uses top-level thinking: string, and "ant-ling" uses reasoning: { effort } only when the mapped effort is non-null. Default: "openai". */
thinkingFormat?:
| "openai"
| "openrouter"
@@ -461,9 +481,12 @@ export interface OpenAICompletionsCompat {
| "together"
| "zai"
| "qwen"
| "chat-template"
| "qwen-chat-template"
| "string-thinking"
| "ant-ling";
/** Kwargs to send as `chat_template_kwargs` when `thinkingFormat` is `chat-template`. Use `{ "$var": "thinking.enabled" }` or `{ "$var": "thinking.effort" }` for pi-controlled thinking values. */
chatTemplateKwargs?: Record<string, ChatTemplateKwargValue>;
/** OpenRouter-compatible routing preferences sent as the `provider` request field. */
openRouterRouting?: OpenRouterRouting;
/** Vercel AI Gateway routing preferences. Only used when baseUrl points to Vercel AI Gateway. */
packages/ai/src/utils/node-http-proxy.ts
+22 -33
View File
@@ -1,7 +1,5 @@
import type { Agent as HttpAgent } from "node:http";
import type { Agent as HttpsAgent } from "node:https";
import { HttpProxyAgent } from "http-proxy-agent";
import { HttpsProxyAgent } from "https-proxy-agent";
import type { ProviderEnv } from "../types.ts";
import { getProviderEnvValue } from "./provider-env.ts";
const DEFAULT_PROXY_PORTS: Record<string, number> = {
ftp: 21,
@@ -12,16 +10,16 @@ const DEFAULT_PROXY_PORTS: Record<string, number> = {
wss: 443,
};
export interface NodeHttpProxyAgents {
httpAgent: HttpAgent;
httpsAgent: HttpsAgent;
}
export const UNSUPPORTED_PROXY_PROTOCOL_MESSAGE =
"Unsupported proxy protocol. SOCKS and PAC proxy URLs are not supported; use an HTTP or HTTPS proxy URL.";
function getProxyEnv(key: string): string {
return process.env[key.toLowerCase()] || process.env[key.toUpperCase()] || "";
function getProxyEnv(key: string, env?: ProviderEnv): string {
const lowercaseKey = key.toLowerCase();
const uppercaseKey = key.toUpperCase();
return (
env?.[lowercaseKey] ||
env?.[uppercaseKey] ||
getProviderEnvValue(lowercaseKey) ||
getProviderEnvValue(uppercaseKey) ||
""
);
}
function parseProxyTargetUrl(targetUrl: string | URL): URL | undefined {
@@ -36,8 +34,8 @@ function parseProxyTargetUrl(targetUrl: string | URL): URL | undefined {
}
}
function shouldProxyHostname(hostname: string, port: number): boolean {
const noProxy = getProxyEnv("no_proxy").toLowerCase();
function shouldProxyHostname(hostname: string, port: number, env?: ProviderEnv): boolean {
const noProxy = getProxyEnv("no_proxy", env).toLowerCase();
if (!noProxy) {
return true;
}
@@ -68,7 +66,7 @@ function shouldProxyHostname(hostname: string, port: number): boolean {
});
}
function getProxyForUrl(targetUrl: string | URL): string {
function getProxyForUrl(targetUrl: string | URL, env?: ProviderEnv): string {
const parsedUrl = parseProxyTargetUrl(targetUrl);
if (!parsedUrl?.protocol || !parsedUrl.host) {
return "";
@@ -77,19 +75,22 @@ function getProxyForUrl(targetUrl: string | URL): string {
const protocol = parsedUrl.protocol.split(":", 1)[0]!;
const hostname = parsedUrl.host.replace(/:\d*$/, "");
const port = Number.parseInt(parsedUrl.port, 10) || DEFAULT_PROXY_PORTS[protocol] || 0;
if (!shouldProxyHostname(hostname, port)) {
if (!shouldProxyHostname(hostname, port, env)) {
return "";
}
let proxy = getProxyEnv(`${protocol}_proxy`) || getProxyEnv("all_proxy");
let proxy = getProxyEnv(`${protocol}_proxy`, env) || getProxyEnv("all_proxy", env);
if (proxy && !proxy.includes("://")) {
proxy = `${protocol}://${proxy}`;
}
return proxy;
}
export function resolveHttpProxyUrlForTarget(targetUrl: string | URL): URL | undefined {
const proxy = getProxyForUrl(targetUrl);
export const UNSUPPORTED_PROXY_PROTOCOL_MESSAGE =
"Unsupported proxy protocol. SOCKS and PAC proxy URLs are not supported; use an HTTP or HTTPS proxy URL.";
export function resolveHttpProxyUrlForTarget(targetUrl: string | URL, env?: ProviderEnv): URL | undefined {
const proxy = getProxyForUrl(targetUrl, env);
if (!proxy) {
return undefined;
}
@@ -109,15 +110,3 @@ export function resolveHttpProxyUrlForTarget(targetUrl: string | URL): URL | und
return proxyUrl;
}
export function createHttpProxyAgentsForTarget(targetUrl: string | URL): NodeHttpProxyAgents | undefined {
const proxyUrl = resolveHttpProxyUrlForTarget(targetUrl);
if (!proxyUrl) {
return undefined;
}
return {
httpAgent: new HttpProxyAgent(proxyUrl),
httpsAgent: new HttpsProxyAgent(proxyUrl) as unknown as HttpsAgent,
};
}
packages/ai/src/utils/oauth/anthropic.ts
+2 -1
View File
@@ -7,6 +7,7 @@
import type { Server } from "node:http";
import type { OAuthAuth } from "../../auth/types.ts";
import { getProviderEnvValue } from "../provider-env.ts";
import { oauthErrorHtml, oauthSuccessHtml } from "./oauth-page.ts";
import { generatePKCE } from "./pkce.ts";
import type { OAuthCredentials, OAuthLoginCallbacks, OAuthPrompt, OAuthProviderInterface } from "./types.ts";
@@ -29,7 +30,7 @@ const decode = (s: string) => atob(s);
const CLIENT_ID = decode("OWQxYzI1MGEtZTYxYi00NGQ5LTg4ZWQtNTk0NGQxOTYyZjVl");
const AUTHORIZE_URL = "https://claude.ai/oauth/authorize";
const TOKEN_URL = "https://platform.claude.com/v1/oauth/token";
const CALLBACK_HOST = process.env.PI_OAUTH_CALLBACK_HOST || "127.0.0.1";
const CALLBACK_HOST = getProviderEnvValue("PI_OAUTH_CALLBACK_HOST") || "127.0.0.1";
const CALLBACK_PORT = 53692;
const CALLBACK_PATH = "/callback";
const REDIRECT_URI = `http://localhost:${CALLBACK_PORT}${CALLBACK_PATH}`;
packages/ai/src/utils/oauth/github-copilot.ts
+76 -7
View File
@@ -10,6 +10,7 @@ import type { OAuthCredentials, OAuthDeviceCodeInfo, OAuthLoginCallbacks, OAuthP
type CopilotCredentials = OAuthCredentials & {
enterpriseUrl?: string;
availableModelIds: string[];
};
const decode = (s: string) => atob(s);
@@ -21,6 +22,7 @@ const COPILOT_HEADERS = {
"Editor-Plugin-Version": "copilot-chat/0.35.0",
"Copilot-Integration-Id": "vscode-chat",
} as const;
const COPILOT_API_VERSION = "2026-06-01";
type DeviceCodeResponse = {
device_code: string;
@@ -89,6 +91,48 @@ export function getGitHubCopilotBaseUrl(token?: string, enterpriseDomain?: strin
return "https://api.individual.githubcopilot.com";
}
function asRecord(value: unknown): Record<string, unknown> | undefined {
return value && typeof value === "object" ? (value as Record<string, unknown>) : undefined;
}
function isSelectableCopilotModel(item: Record<string, unknown>): boolean {
const policy = asRecord(item.policy);
const capabilities = asRecord(item.capabilities);
const supports = asRecord(capabilities?.supports);
return item.model_picker_enabled === true && policy?.state !== "disabled" && supports?.tool_calls !== false;
}
function parseAvailableCopilotModelIds(raw: unknown): string[] {
const data = asRecord(raw)?.data;
if (!Array.isArray(data)) {
throw new Error("Invalid Copilot models response");
}
const ids: string[] = [];
for (const rawItem of data) {
const item = asRecord(rawItem);
const id = item?.id;
if (typeof id === "string" && item && isSelectableCopilotModel(item)) {
ids.push(id);
}
}
return ids;
}
async function fetchAvailableGitHubCopilotModelIds(copilotToken: string, enterpriseDomain?: string): Promise<string[]> {
const baseUrl = getGitHubCopilotBaseUrl(copilotToken, enterpriseDomain);
const raw = await fetchJson(`${baseUrl}/models`, {
headers: {
Accept: "application/json",
Authorization: `Bearer ${copilotToken}`,
...COPILOT_HEADERS,
"X-GitHub-Api-Version": COPILOT_API_VERSION,
},
signal: AbortSignal.timeout(5000),
});
return parseAvailableCopilotModelIds(raw);
}
async function fetchJson(url: string, init: RequestInit): Promise<unknown> {
const response = await fetch(url, init);
if (!response.ok) {
@@ -202,10 +246,7 @@ async function pollForGitHubAccessToken(
});
}
/**
* Refresh GitHub Copilot token
*/
export async function refreshGitHubCopilotToken(
async function refreshGitHubCopilotAccessToken(
refreshToken: string,
enterpriseDomain?: string,
): Promise<OAuthCredentials> {
@@ -239,6 +280,20 @@ export async function refreshGitHubCopilotToken(
};
}
/**
* Refresh GitHub Copilot token
*/
export async function refreshGitHubCopilotToken(
refreshToken: string,
enterpriseDomain?: string,
): Promise<OAuthCredentials> {
const credentials = await refreshGitHubCopilotAccessToken(refreshToken, enterpriseDomain);
return {
...credentials,
availableModelIds: await fetchAvailableGitHubCopilotModelIds(credentials.access, enterpriseDomain),
};
}
/**
* Enable a model for the user's GitHub Copilot account.
* This is required for some models (like Claude, Grok) before they can be used.
@@ -323,12 +378,18 @@ export async function loginGitHubCopilot(options: {
});
const githubAccessToken = await pollForGitHubAccessToken(domain, device, options.signal);
const credentials = await refreshGitHubCopilotToken(githubAccessToken, enterpriseDomain ?? undefined);
const credentials = await refreshGitHubCopilotAccessToken(githubAccessToken, enterpriseDomain ?? undefined);
// Enable all models after successful login
options.onProgress?.("Enabling models...");
await enableAllGitHubCopilotModels(credentials.access, enterpriseDomain ?? undefined);
return credentials;
// Fetch availability after policy enable so newly enabled models are included,
// while unavailable models are still filtered out.
return {
...credentials,
availableModelIds: await fetchAvailableGitHubCopilotModelIds(credentials.access, enterpriseDomain ?? undefined),
};
}
function copilotEnterpriseDomain(credential: OAuthCredential): string | undefined {
@@ -393,6 +454,14 @@ export const githubCopilotOAuthProvider: OAuthProviderInterface = {
const creds = credentials as CopilotCredentials;
const domain = creds.enterpriseUrl ? (normalizeDomain(creds.enterpriseUrl) ?? undefined) : undefined;
const baseUrl = getGitHubCopilotBaseUrl(creds.access, domain);
return models.map((m) => (m.provider === "github-copilot" ? { ...m, baseUrl } : m));
// Older stored Pi auth entries do not have account-specific model IDs yet;
// keep their existing generated-catalog behavior until the next refresh/login.
const availableModelIds = "availableModelIds" in creds ? new Set(creds.availableModelIds) : undefined;
return models.flatMap((m) => {
if (m.provider !== "github-copilot") return [m];
if (availableModelIds && !availableModelIds.has(m.id)) return [];
return [{ ...m, baseUrl }];
});
},
};
packages/ai/src/utils/oauth/openai-codex.ts
+2 -1
View File
@@ -18,6 +18,7 @@ if (typeof process !== "undefined" && (process.versions?.node || process.version
}
import type { OAuthAuth } from "../../auth/types.ts";
import { getProviderEnvValue } from "../provider-env.ts";
import { pollOAuthDeviceCodeFlow } from "./device-code.ts";
import { oauthErrorHtml, oauthSuccessHtml } from "./oauth-page.ts";
import { generatePKCE } from "./pkce.ts";
@@ -48,7 +49,7 @@ type OAuthToken = { access: string; refresh: string; expires: number };
type TokenOperation = "exchange" | "refresh";
function getCallbackHost(): string {
return typeof process !== "undefined" ? process.env.PI_OAUTH_CALLBACK_HOST || "127.0.0.1" : "127.0.0.1";
return getProviderEnvValue("PI_OAUTH_CALLBACK_HOST") || "127.0.0.1";
}
type DeviceAuthInfo = {
packages/ai/src/utils/overflow.ts
+3 -2
View File
@@ -12,6 +12,7 @@ import type { AssistantMessage } from "../types.ts";
* - Anthropic: "413 {\"error\":{\"type\":\"request_too_large\",\"message\":\"Request exceeds the maximum size\"}}"
* - OpenAI: "Your input exceeds the context window of this model"
* - OpenAI/LiteLLM: "Requested token count exceeds the model's maximum context length of 131072 tokens"
* - OpenAI-compatible: "Input length (265330) exceeds model's maximum context length (262144)."
* - Google: "The input token count (1196265) exceeds the maximum number of tokens allowed (1048575)"
* - xAI: "This model's maximum prompt length is 131072 but the request contains 537812 tokens"
* - Groq: "Please reduce the length of the messages or completion"
@@ -36,7 +37,7 @@ const OVERFLOW_PATTERNS = [
/request_too_large/i, // Anthropic request byte-size overflow (HTTP 413)
/input is too long for requested model/i, // Amazon Bedrock
/exceeds the context window/i, // OpenAI (Completions & Responses API)
/exceeds (?:the )?(?:model'?s )?maximum context length of [\d,]+ tokens?/i, // OpenAI-compatible proxies (LiteLLM)
/exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i, // OpenAI-compatible proxies (LiteLLM)
/input token count.*exceeds the maximum/i, // Google (Gemini)
/maximum prompt length is \d+/i, // xAI (Grok)
/reduce the length of the messages/i, // Groq
@@ -85,7 +86,7 @@ const NON_OVERFLOW_PATTERNS = [
*
* **Reliable detection (returns error with detectable message):**
* - Anthropic: "prompt is too long: X tokens > Y maximum" or "request_too_large"
* - OpenAI (Completions & Responses): "exceeds the context window" or "exceeds the model's maximum context length of X tokens"
* - OpenAI (Completions & Responses): "exceeds the context window", "exceeds the model's maximum context length of X tokens", or "exceeds model's maximum context length (X)"
* - Google Gemini: "input token count exceeds the maximum"
* - xAI (Grok): "maximum prompt length is X but request contains Y"
* - Groq: "reduce the length of the messages"
packages/ai/src/utils/provider-env.ts
+52
View File
@@ -0,0 +1,52 @@
import type { ProviderEnv } from "../types.ts";
let procEnvCache: Map<string, string> | null = null;
/**
* Fallback for https://github.com/oven-sh/bun/issues/27802.
* Bun compiled binaries can expose an empty process.env inside Linux sandboxes
* even though /proc/self/environ contains the environment.
*
* This intentionally duplicates restoreSandboxEnv() in
* packages/coding-agent/src/bun/restore-sandbox-env.ts. The ai package can be
* used directly, without going through that entrypoint, so provider env lookup
* must not depend on process.env having been patched.
*/
function getBunSandboxEnvValue(name: string): string | undefined {
if (typeof process === "undefined" || !process.versions?.bun || Object.keys(process.env).length > 0) {
return undefined;
}
if (procEnvCache === null) {
procEnvCache = new Map();
try {
const { readFileSync } = require("node:fs") as {
readFileSync(path: string, encoding: BufferEncoding): string;
};
const data = readFileSync("/proc/self/environ", "utf-8");
for (const entry of data.split("\0")) {
const idx = entry.indexOf("=");
if (idx > 0) {
procEnvCache.set(entry.slice(0, idx), entry.slice(idx + 1));
}
}
} catch {
// /proc/self/environ may not exist or may not be readable.
}
}
return procEnvCache.get(name);
}
/**
* Resolve a provider env value from scoped overrides, normal process.env, then
* the duplicated Bun sandbox fallback for direct pi-ai consumers.
*/
export function getProviderEnvValue(name: string, env?: ProviderEnv): string | undefined {
return (
env?.[name] ||
(typeof process !== "undefined" ? process.env[name] : undefined) ||
getBunSandboxEnvValue(name) ||
undefined
);
}