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

feat(ai): add Cloudflare AI Gateway as a provider (#3856)

Browse Source 
* feat(ai): add Cloudflare AI Gateway as a provider

Routes through Cloudflare's Unified API (`/compat`) for Workers AI and
Anthropic models, and through the provider-specific `/openai` subpath
for OpenAI models so reasoning models (gpt-5.x, o-series) can hit
`/v1/responses` natively. Once `/compat` adds Responses-API support,
the OpenAI subpath can be folded back in.

Catalog layout:
  workers-ai/@cf/...  -> openai-completions, gateway/.../compat
  anthropic/...       -> openai-completions, gateway/.../compat
  <native-id>         -> openai-responses,   gateway/.../openai
                         (gpt-5.1, claude-... no, sorry: gpt-5.x and o-series only;
                          prefix stripped because the OpenAI SDK posts native ids)

Touches:
  packages/ai/src/types.ts                       add cloudflare-ai-gateway to KnownProvider
  packages/ai/src/env-api-keys.ts                map to CLOUDFLARE_API_KEY
  packages/ai/src/providers/cloudflare.ts        add CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL
                                                 and CLOUDFLARE_AI_GATEWAY_OPENAI_BASE_URL
  packages/ai/src/providers/openai-responses.ts  one-line dispatch through resolveCloudflareBaseUrl
                                                 (matches what openai-completions.ts already does)
  packages/ai/scripts/generate-models.ts         branch openai/* vs workers-ai/anthropic/*
  packages/ai/src/models.generated.ts            spliced 34 entries
  packages/ai/test/stream.test.ts                3 e2e blocks (one per upstream)
  packages/coding-agent/*                        defaultModelPerProvider, login, env docs,
                                                 README, providers.md

Verified end-to-end against a real Cloudflare account with unified
billing: 9/9 e2e tests pass across all three upstreams (Workers AI
Kimi K2.6, OpenAI gpt-5.1 reasoning, Anthropic claude-sonnet-4-5).

* refactor(ai): move AI Gateway User-Agent and per-route session-affinity flag to catalog

Mirrors the same per-model metadata refactor done for Workers AI in the
parent branch. All cloudflare-ai-gateway entries get the User-Agent
header. Only workers-ai/* gateway entries set
`compat.sendSessionAffinityHeaders: true` because the gateway
forwards that header to the underlying Workers AI runtime; anthropic/*
upstream and openai/* (openai-responses) don't use it.

  packages/ai/scripts/generate-models.ts: emit headers (always) and
  per-upstream compat (workers-ai only) on each cloudflare-ai-gateway
  entry.
  packages/ai/src/models.generated.ts: re-spliced 35 entries with
  headers + conditional compat.

Behavior unchanged - 9/9 e2e tests pass across all three upstream
families.

* fix(ai): align AI Gateway with telemetry-aware UA helper

Adapts to badlogic/pi-mono#3851's follow-up fix ("honor telemetry for
Cloudflare attribution headers", fbb5eed) which moved the
'User-Agent: pi-coding-agent' header out of per-model catalog metadata
and into a centralized telemetry-honoring helper
(coding-agent/src/core/sdk.ts:getAttributionHeaders).

- packages/coding-agent/src/core/sdk.ts: extend the cloudflare branch of
  getAttributionHeaders to also match cloudflare-ai-gateway and
  gateway.ai.cloudflare.com.

- packages/ai/scripts/generate-models.ts and src/models.generated.ts:
  drop 'headers' from the 35 cloudflare-ai-gateway entries (constant
  CLOUDFLARE_STATIC_HEADERS no longer exists). Per-route
  compat.sendSessionAffinityHeaders is unchanged.

End-to-end behavior unchanged: 9/9 tests still pass across all three
upstream families (Workers AI, Anthropic, OpenAI Responses).

---------

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
This commit is contained in:
MC
2026-04-30 22:29:37 +01:00
committed by GitHub
parent c9ddca1968
commit 24fb6b833b
13 changed files with 755 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/env-api-keys.ts
+1
View File
@@ -121,6 +121,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
"opencode-go": "OPENCODE_API_KEY",
"kimi-coding": "KIMI_API_KEY",
"cloudflare-workers-ai": "CLOUDFLARE_API_KEY",
"cloudflare-ai-gateway": "CLOUDFLARE_API_KEY",
};
const envVar = envMap[provider];
packages/ai/src/models.generated.ts
+601
View File
@@ -15654,4 +15654,605 @@ export const MODELS = {
maxTokens: 131072,
} satisfies Model<"openai-completions">,
},
"cloudflare-ai-gateway": {
"anthropic/claude-3-5-haiku": {
id: "anthropic/claude-3-5-haiku",
name: "Claude Haiku 3.5 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.8,
output: 4,
cacheRead: 0.08,
cacheWrite: 1,
},
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"anthropic/claude-3-haiku": {
id: "anthropic/claude-3-haiku",
name: "Claude Haiku 3",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.25,
output: 1.25,
cacheRead: 0.03,
cacheWrite: 0.3,
},
contextWindow: 200000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"anthropic/claude-3-opus": {
id: "anthropic/claude-3-opus",
name: "Claude Opus 3",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 15,
output: 75,
cacheRead: 1.5,
cacheWrite: 18.75,
},
contextWindow: 200000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"anthropic/claude-3-sonnet": {
id: "anthropic/claude-3-sonnet",
name: "Claude Sonnet 3",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 3,
output: 15,
cacheRead: 0.3,
cacheWrite: 0.3,
},
contextWindow: 200000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"anthropic/claude-3.5-haiku": {
id: "anthropic/claude-3.5-haiku",
name: "Claude Haiku 3.5 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.8,
output: 4,
cacheRead: 0.08,
cacheWrite: 1,
},
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"anthropic/claude-3.5-sonnet": {
id: "anthropic/claude-3.5-sonnet",
name: "Claude Sonnet 3.5 v2",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: false,
input: ["text", "image"],
cost: {
input: 3,
output: 15,
cacheRead: 0.3,
cacheWrite: 3.75,
},
contextWindow: 200000,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"anthropic/claude-haiku-4-5": {
id: "anthropic/claude-haiku-4-5",
name: "Claude Haiku 4.5 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1,
output: 5,
cacheRead: 0.1,
cacheWrite: 1.25,
},
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4": {
id: "anthropic/claude-opus-4",
name: "Claude Opus 4 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 15,
output: 75,
cacheRead: 1.5,
cacheWrite: 18.75,
},
contextWindow: 200000,
maxTokens: 32000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4-1": {
id: "anthropic/claude-opus-4-1",
name: "Claude Opus 4.1 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 15,
output: 75,
cacheRead: 1.5,
cacheWrite: 18.75,
},
contextWindow: 200000,
maxTokens: 32000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4-5": {
id: "anthropic/claude-opus-4-5",
name: "Claude Opus 4.5 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 25,
cacheRead: 0.5,
cacheWrite: 6.25,
},
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4-6": {
id: "anthropic/claude-opus-4-6",
name: "Claude Opus 4.6 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 25,
cacheRead: 0.5,
cacheWrite: 6.25,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-4-7": {
id: "anthropic/claude-opus-4-7",
name: "Claude Opus 4.7",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 25,
cacheRead: 0.5,
cacheWrite: 6.25,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"anthropic/claude-sonnet-4": {
id: "anthropic/claude-sonnet-4",
name: "Claude Sonnet 4 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 3,
output: 15,
cacheRead: 0.3,
cacheWrite: 3.75,
},
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"anthropic/claude-sonnet-4-5": {
id: "anthropic/claude-sonnet-4-5",
name: "Claude Sonnet 4.5 (latest)",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 3,
output: 15,
cacheRead: 0.3,
cacheWrite: 3.75,
},
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"anthropic/claude-sonnet-4-6": {
id: "anthropic/claude-sonnet-4-6",
name: "Claude Sonnet 4.6",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
reasoning: true,
input: ["text", "image"],
cost: {
input: 3,
output: 15,
cacheRead: 0.3,
cacheWrite: 3.75,
},
contextWindow: 1000000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"workers-ai/@cf/moonshotai/kimi-k2.5": {
id: "workers-ai/@cf/moonshotai/kimi-k2.5",
name: "Kimi K2.5",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.6,
output: 3,
cacheRead: 0.1,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
"workers-ai/@cf/moonshotai/kimi-k2.6": {
id: "workers-ai/@cf/moonshotai/kimi-k2.6",
name: "Kimi K2.6",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.95,
output: 4,
cacheRead: 0.16,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
"workers-ai/@cf/nvidia/nemotron-3-120b-a12b": {
id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
name: "Nemotron 3 Super 120B",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text"],
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 256000,
} satisfies Model<"openai-completions">,
"workers-ai/@cf/zai-org/glm-4.7-flash": {
id: "workers-ai/@cf/zai-org/glm-4.7-flash",
name: "GLM-4.7-Flash",
api: "openai-completions",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
compat: {"sendSessionAffinityHeaders":true},
reasoning: true,
input: ["text"],
cost: {
input: 0.06,
output: 0.4,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"gpt-4": {
id: "gpt-4",
name: "GPT-4",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: false,
input: ["text"],
cost: {
input: 30,
output: 60,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 8192,
maxTokens: 8192,
} satisfies Model<"openai-responses">,
"gpt-4-turbo": {
id: "gpt-4-turbo",
name: "GPT-4 Turbo",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: false,
input: ["text", "image"],
cost: {
input: 10,
output: 30,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-responses">,
"gpt-4o": {
id: "gpt-4o",
name: "GPT-4o",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: false,
input: ["text", "image"],
cost: {
input: 2.5,
output: 10,
cacheRead: 1.25,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"openai-responses">,
"gpt-4o-mini": {
id: "gpt-4o-mini",
name: "GPT-4o mini",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 16384,
} satisfies Model<"openai-responses">,
"gpt-5.1": {
id: "gpt-5.1",
name: "GPT-5.1",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.1-codex": {
id: "gpt-5.1-codex",
name: "GPT-5.1 Codex",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.25,
output: 10,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.2": {
id: "gpt-5.2",
name: "GPT-5.2",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.2-codex": {
id: "gpt-5.2-codex",
name: "GPT-5.2 Codex",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.3-codex": {
id: "gpt-5.3-codex",
name: "GPT-5.3 Codex",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.75,
output: 14,
cacheRead: 0.175,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.4": {
id: "gpt-5.4",
name: "GPT-5.4",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 2.5,
output: 15,
cacheRead: 0.25,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"gpt-5.5": {
id: "gpt-5.5",
name: "GPT-5.5",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 5,
output: 30,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
"o1": {
id: "o1",
name: "o1",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 15,
output: 60,
cacheRead: 7.5,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"openai-responses">,
"o3": {
id: "o3",
name: "o3",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 2,
output: 8,
cacheRead: 0.5,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"openai-responses">,
"o3-mini": {
id: "o3-mini",
name: "o3-mini",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text"],
cost: {
input: 1.1,
output: 4.4,
cacheRead: 0.55,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"openai-responses">,
"o3-pro": {
id: "o3-pro",
name: "o3-pro",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 20,
output: 80,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"openai-responses">,
"o4-mini": {
id: "o4-mini",
name: "o4-mini",
api: "openai-responses",
provider: "cloudflare-ai-gateway",
baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.1,
output: 4.4,
cacheRead: 0.28,
cacheWrite: 0,
},
contextWindow: 200000,
maxTokens: 100000,
} satisfies Model<"openai-responses">,
},
} as const;
packages/ai/src/providers/cloudflare.ts
+12 -4
View File
@@ -1,15 +1,23 @@
import type { Model } from "../types.js";
import type { Api, Model } from "../types.js";
/** Workers AI endpoint. `{CLOUDFLARE_ACCOUNT_ID}` is substituted at request time. */
/** Workers AI direct endpoint. */
export const CLOUDFLARE_WORKERS_AI_BASE_URL =
"https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1";
/** AI Gateway Unified API. https://developers.cloudflare.com/ai-gateway/usage/unified-api/ */
export const CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL =
"https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat";
/** AI Gateway → OpenAI passthrough. Used until /compat supports /v1/responses. */
export const CLOUDFLARE_AI_GATEWAY_OPENAI_BASE_URL =
"https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai";
export function isCloudflareProvider(provider: string): boolean {
return provider === "cloudflare-workers-ai";
return provider === "cloudflare-workers-ai" || provider === "cloudflare-ai-gateway";
}
/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from process.env. */
export function resolveCloudflareBaseUrl(model: Model<"openai-completions">): string {
export function resolveCloudflareBaseUrl(model: Model<Api>): string {
const url = model.baseUrl;
if (!url.includes("{")) return url;
return url.replace(/\{([A-Z_][A-Z0-9_]*)\}/g, (_match, name: string) => {
packages/ai/src/providers/openai-responses.ts
+2 -1
View File
@@ -16,6 +16,7 @@ import type {
} from "../types.js";
import { AssistantMessageEventStream } from "../utils/event-stream.js";
import { headersToRecord } from "../utils/headers.js";
import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.js";
import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.js";
import { buildBaseOptions, clampReasoning } from "./simple-options.js";
@@ -198,7 +199,7 @@ function createClient(
return new OpenAI({
apiKey,
baseURL: model.baseUrl,
baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
dangerouslyAllowBrowser: true,
defaultHeaders: headers,
});
packages/ai/src/types.ts
+2 -1
View File
@@ -41,7 +41,8 @@ export type KnownProvider =
| "opencode"
| "opencode-go"
| "kimi-coding"
| "cloudflare-workers-ai";
| "cloudflare-workers-ai"
| "cloudflare-ai-gateway";
export type Provider = KnownProvider | string;
export type ThinkingLevel = "minimal" | "low" | "medium" | "high" | "xhigh";