From 3d6acb37b93d2ceedfcc170b2d212c34fedbf193 Mon Sep 17 00:00:00 2001 From: Vegard Stikbakke Date: Tue, 30 Jun 2026 08:33:18 +0200 Subject: [PATCH] fix(ai): regenerate model catalog Includes updated Xiaomi MiMo pricing from models.dev. Closes #6138 --- packages/ai/CHANGELOG.md | 1 + .../ai/src/providers/amazon-bedrock.models.ts | 33 ++++++-- packages/ai/src/providers/anthropic.models.ts | 34 -------- packages/ai/src/providers/fireworks.models.ts | 20 ++++- packages/ai/src/providers/groq.models.ts | 2 +- .../ai/src/providers/huggingface.models.ts | 18 +++++ .../ai/src/providers/minimax-cn.models.ts | 8 +- packages/ai/src/providers/minimax.models.ts | 8 +- packages/ai/src/providers/nvidia.models.ts | 19 +++++ .../ai/src/providers/opencode-go.models.ts | 2 +- .../ai/src/providers/openrouter.models.ts | 79 +++++++------------ packages/ai/src/providers/together.models.ts | 19 +++++ .../src/providers/vercel-ai-gateway.models.ts | 52 ++++++------ .../providers/xiaomi-token-plan-ams.models.ts | 24 +++--- .../providers/xiaomi-token-plan-cn.models.ts | 24 +++--- .../providers/xiaomi-token-plan-sgp.models.ts | 24 +++--- packages/ai/src/providers/xiaomi.models.ts | 30 +++---- 17 files changed, 218 insertions(+), 179 deletions(-) diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md index 707f112a..dc180c8d 100644 --- a/packages/ai/CHANGELOG.md +++ b/packages/ai/CHANGELOG.md @@ -12,6 +12,7 @@ ### Fixed +- Fixed generated Xiaomi MiMo model pricing to match current pay-as-you-go pricing from models.dev ([#6138](https://github.com/earendil-works/pi/issues/6138)). - Fixed `streamSimple()` to send a context-aware max-token cap so providers that count input and output against one context window do not reject long requests ([#5595](https://github.com/earendil-works/pi/issues/5595)). - Fixed OpenAI Responses streams to preserve reasoning replay state when output items finish out of order ([#6009](https://github.com/earendil-works/pi/issues/6009)). - Fixed retry classification for provider errors that explicitly tell callers to retry the request ([#6019](https://github.com/earendil-works/pi/issues/6019)). diff --git a/packages/ai/src/providers/amazon-bedrock.models.ts b/packages/ai/src/providers/amazon-bedrock.models.ts index 37c21dce..f30ad72e 100644 --- a/packages/ai/src/providers/amazon-bedrock.models.ts +++ b/packages/ai/src/providers/amazon-bedrock.models.ts @@ -376,10 +376,10 @@ export const AMAZON_BEDROCK_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 1, - output: 5, - cacheRead: 0.1, - cacheWrite: 1.25, + input: 1.1, + output: 5.5, + cacheRead: 0.11, + cacheWrite: 1.375, }, contextWindow: 200000, maxTokens: 64000, @@ -393,10 +393,10 @@ export const AMAZON_BEDROCK_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 5, - output: 25, - cacheRead: 0.5, - cacheWrite: 6.25, + input: 5.5, + output: 27.5, + cacheRead: 0.55, + cacheWrite: 6.875, }, contextWindow: 200000, maxTokens: 64000, @@ -1623,6 +1623,23 @@ export const AMAZON_BEDROCK_MODELS = { contextWindow: 1040000, maxTokens: 8192, } satisfies Model<"bedrock-converse-stream">, + "xai.grok-4.3": { + id: "xai.grok-4.3", + name: "Grok 4.3", + api: "bedrock-converse-stream", + provider: "amazon-bedrock", + baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com", + reasoning: true, + input: ["text", "image"], + cost: { + input: 1.25, + output: 2.5, + cacheRead: 0.2, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 131072, + } satisfies Model<"bedrock-converse-stream">, "zai.glm-4.7": { id: "zai.glm-4.7", name: "GLM-4.7", diff --git a/packages/ai/src/providers/anthropic.models.ts b/packages/ai/src/providers/anthropic.models.ts index 3db30f74..b95e2873 100644 --- a/packages/ai/src/providers/anthropic.models.ts +++ b/packages/ai/src/providers/anthropic.models.ts @@ -4,40 +4,6 @@ import type { Model } from "../types.ts"; export const ANTHROPIC_MODELS = { - "claude-3-5-haiku-20241022": { - id: "claude-3-5-haiku-20241022", - name: "Claude Haiku 3.5", - api: "anthropic-messages", - provider: "anthropic", - baseUrl: "https://api.anthropic.com", - reasoning: false, - input: ["text", "image"], - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - contextWindow: 200000, - maxTokens: 8192, - } satisfies Model<"anthropic-messages">, - "claude-3-5-haiku-latest": { - id: "claude-3-5-haiku-latest", - name: "Claude Haiku 3.5 (latest)", - api: "anthropic-messages", - provider: "anthropic", - baseUrl: "https://api.anthropic.com", - reasoning: false, - input: ["text", "image"], - cost: { - input: 0.8, - output: 4, - cacheRead: 0.08, - cacheWrite: 1, - }, - contextWindow: 200000, - maxTokens: 8192, - } satisfies Model<"anthropic-messages">, "claude-3-5-sonnet-20240620": { id: "claude-3-5-sonnet-20240620", name: "Claude Sonnet 3.5", diff --git a/packages/ai/src/providers/fireworks.models.ts b/packages/ai/src/providers/fireworks.models.ts index cb93d846..91d1115c 100644 --- a/packages/ai/src/providers/fireworks.models.ts +++ b/packages/ai/src/providers/fireworks.models.ts @@ -74,7 +74,7 @@ export const FIREWORKS_MODELS = { cacheRead: 0.26, cacheWrite: 0, }, - contextWindow: 1048576, + contextWindow: 1048575, maxTokens: 131072, } satisfies Model<"openai-completions">, "accounts/fireworks/models/gpt-oss-120b": { @@ -221,6 +221,24 @@ export const FIREWORKS_MODELS = { contextWindow: 202800, maxTokens: 131072, } satisfies Model<"anthropic-messages">, + "accounts/fireworks/routers/glm-5p2-fast": { + id: "accounts/fireworks/routers/glm-5p2-fast", + name: "GLM 5.2 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"], + cost: { + input: 2.1, + output: 6.6, + cacheRead: 0.21, + cacheWrite: 0, + }, + contextWindow: 1048575, + maxTokens: 131072, + } satisfies Model<"anthropic-messages">, "accounts/fireworks/routers/kimi-k2p6-fast": { id: "accounts/fireworks/routers/kimi-k2p6-fast", name: "Kimi K2.6 Fast", diff --git a/packages/ai/src/providers/groq.models.ts b/packages/ai/src/providers/groq.models.ts index 857048c7..6b0e3da2 100644 --- a/packages/ai/src/providers/groq.models.ts +++ b/packages/ai/src/providers/groq.models.ts @@ -100,7 +100,7 @@ export const GROQ_MODELS = { cost: { input: 0.075, output: 0.3, - cacheRead: 0.037, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 131072, diff --git a/packages/ai/src/providers/huggingface.models.ts b/packages/ai/src/providers/huggingface.models.ts index 695b72d6..4c4b6628 100644 --- a/packages/ai/src/providers/huggingface.models.ts +++ b/packages/ai/src/providers/huggingface.models.ts @@ -652,6 +652,24 @@ export const HUGGINGFACE_MODELS = { contextWindow: 262144, maxTokens: 262144, } satisfies Model<"openai-completions">, + "openai/gpt-oss-120b": { + id: "openai/gpt-oss-120b", + name: "GPT OSS 120B", + api: "openai-completions", + provider: "huggingface", + baseUrl: "https://router.huggingface.co/v1", + compat: {"supportsDeveloperRole":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0.25, + output: 0.69, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 32768, + } satisfies Model<"openai-completions">, "stepfun-ai/Step-3.5-Flash": { id: "stepfun-ai/Step-3.5-Flash", name: "Step 3.5 Flash", diff --git a/packages/ai/src/providers/minimax-cn.models.ts b/packages/ai/src/providers/minimax-cn.models.ts index d1f90c21..d6af804d 100644 --- a/packages/ai/src/providers/minimax-cn.models.ts +++ b/packages/ai/src/providers/minimax-cn.models.ts @@ -47,12 +47,12 @@ export const MINIMAX_CN_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.12, + input: 0.3, + output: 1.2, + cacheRead: 0.06, cacheWrite: 0, }, - contextWindow: 512000, + contextWindow: 1000000, maxTokens: 128000, } satisfies Model<"anthropic-messages">, } as const; diff --git a/packages/ai/src/providers/minimax.models.ts b/packages/ai/src/providers/minimax.models.ts index 0ff346c7..7ea1b014 100644 --- a/packages/ai/src/providers/minimax.models.ts +++ b/packages/ai/src/providers/minimax.models.ts @@ -47,12 +47,12 @@ export const MINIMAX_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.6, - output: 2.4, - cacheRead: 0.12, + input: 0.3, + output: 1.2, + cacheRead: 0.06, cacheWrite: 0, }, - contextWindow: 512000, + contextWindow: 1000000, maxTokens: 128000, } satisfies Model<"anthropic-messages">, } as const; diff --git a/packages/ai/src/providers/nvidia.models.ts b/packages/ai/src/providers/nvidia.models.ts index d0a0c713..9884e74f 100644 --- a/packages/ai/src/providers/nvidia.models.ts +++ b/packages/ai/src/providers/nvidia.models.ts @@ -99,6 +99,25 @@ export const NVIDIA_MODELS = { contextWindow: 128000, maxTokens: 4096, } satisfies Model<"openai-completions">, + "minimaxai/minimax-m3": { + id: "minimaxai/minimax-m3", + name: "MiniMax-M3", + 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: true, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 16384, + } satisfies Model<"openai-completions">, "mistralai/mistral-large-3-675b-instruct-2512": { id: "mistralai/mistral-large-3-675b-instruct-2512", name: "Mistral Large 3 675B Instruct 2512", diff --git a/packages/ai/src/providers/opencode-go.models.ts b/packages/ai/src/providers/opencode-go.models.ts index 6cf15918..cb51ed53 100644 --- a/packages/ai/src/providers/opencode-go.models.ts +++ b/packages/ai/src/providers/opencode-go.models.ts @@ -184,7 +184,7 @@ export const OPENCODE_GO_MODELS = { cacheRead: 0.02, cacheWrite: 0, }, - contextWindow: 512000, + contextWindow: 1000000, maxTokens: 131072, } satisfies Model<"anthropic-messages">, "qwen3.6-plus": { diff --git a/packages/ai/src/providers/openrouter.models.ts b/packages/ai/src/providers/openrouter.models.ts index 716afd5d..0b8bb914 100644 --- a/packages/ai/src/providers/openrouter.models.ts +++ b/packages/ai/src/providers/openrouter.models.ts @@ -239,25 +239,6 @@ export const OPENROUTER_MODELS = { contextWindow: 1000000, maxTokens: 128000, } satisfies Model<"openai-completions">, - "anthropic/claude-opus-4.6-fast": { - id: "anthropic/claude-opus-4.6-fast", - name: "Anthropic: Claude Opus 4.6 (Fast)", - api: "openai-completions", - provider: "openrouter", - baseUrl: "https://openrouter.ai/api/v1", - compat: {"thinkingFormat":"openrouter","cacheControlFormat":"anthropic"}, - reasoning: true, - thinkingLevelMap: {"xhigh":"max"}, - input: ["text", "image"], - cost: { - input: 30, - output: 150, - cacheRead: 3, - cacheWrite: 37.5, - }, - contextWindow: 1000000, - maxTokens: 128000, - } satisfies Model<"openai-completions">, "anthropic/claude-opus-4.7": { id: "anthropic/claude-opus-4.7", name: "Anthropic: Claude Opus 4.7", @@ -706,7 +687,7 @@ export const OPENROUTER_MODELS = { cost: { input: 0.2288, output: 0.3432, - cacheRead: 0, + cacheRead: 0.02288, cacheWrite: 0, }, contextWindow: 131072, @@ -1409,9 +1390,9 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.15, - output: 0.9, - cacheRead: 0.05, + input: 0.12, + output: 0.48, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 204800, @@ -1427,8 +1408,8 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.24, - output: 0.96, + input: 0.18, + output: 0.72, cacheRead: 0, cacheWrite: 0, }, @@ -1775,7 +1756,7 @@ export const OPENROUTER_MODELS = { cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 32768, + maxTokens: 100352, } satisfies Model<"openai-completions">, "moonshotai/kimi-k2-0905": { id: "moonshotai/kimi-k2-0905", @@ -1793,7 +1774,7 @@ export const OPENROUTER_MODELS = { cacheWrite: 0, }, contextWindow: 262144, - maxTokens: 262144, + maxTokens: 100352, } satisfies Model<"openai-completions">, "moonshotai/kimi-k2-thinking": { id: "moonshotai/kimi-k2-thinking", @@ -1841,9 +1822,9 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.66, - output: 3.41, - cacheRead: 0.144, + input: 0.55, + output: 3.2, + cacheRead: 0.11, cacheWrite: 0, }, contextWindow: 262144, @@ -1949,13 +1930,13 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.09, - output: 0.45, + input: 0.085, + output: 0.4, cacheRead: 0, cacheWrite: 0, }, contextWindow: 1000000, - maxTokens: 4096, + maxTokens: 16384, } satisfies Model<"openai-completions">, "nvidia/nemotron-3-super-120b-a12b:free": { id: "nvidia/nemotron-3-super-120b-a12b:free", @@ -2789,13 +2770,13 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.039, - output: 0.18, + input: 0.03, + output: 0.15, cacheRead: 0, cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 4096, + maxTokens: 131072, } satisfies Model<"openai-completions">, "openai/gpt-oss-120b:free": { id: "openai/gpt-oss-120b:free", @@ -3905,8 +3886,8 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.2885, - output: 3.17, + input: 0.2596, + output: 2.385, cacheRead: 0, cacheWrite: 0, }, @@ -4103,13 +4084,13 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.09, + input: 0.1, output: 0.3, - cacheRead: 0.02, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 262144, - maxTokens: 16384, + maxTokens: 65536, } satisfies Model<"openai-completions">, "stepfun/step-3.7-flash": { id: "stepfun/step-3.7-flash", @@ -4445,9 +4426,9 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.98, - output: 3.08, - cacheRead: 0.182, + input: 0.975, + output: 4.3, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 202752, @@ -4464,13 +4445,13 @@ export const OPENROUTER_MODELS = { thinkingLevelMap: {"xhigh":"xhigh"}, input: ["text"], cost: { - input: 0.95, + input: 0.94, output: 3, cacheRead: 0.18, cacheWrite: 0, }, contextWindow: 1048576, - maxTokens: 32768, + maxTokens: 4096, } satisfies Model<"openai-completions">, "z-ai/glm-5v-turbo": { id: "z-ai/glm-5v-turbo", @@ -4608,9 +4589,9 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.66, - output: 3.41, - cacheRead: 0.144, + input: 0.55, + output: 3.2, + cacheRead: 0.11, cacheWrite: 0, }, contextWindow: 262144, diff --git a/packages/ai/src/providers/together.models.ts b/packages/ai/src/providers/together.models.ts index 6a261484..5d1e0238 100644 --- a/packages/ai/src/providers/together.models.ts +++ b/packages/ai/src/providers/together.models.ts @@ -360,4 +360,23 @@ export const TOGETHER_MODELS = { contextWindow: 202752, maxTokens: 131072, } satisfies Model<"openai-completions">, + "zai-org/GLM-5.2": { + id: "zai-org/GLM-5.2", + name: "GLM-5.2", + api: "openai-completions", + provider: "together", + baseUrl: "https://api.together.ai/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","thinkingFormat":"together","supportsStrictMode":false,"supportsLongCacheRetention":false}, + reasoning: true, + thinkingLevelMap: {"minimal":null,"low":null,"medium":null}, + input: ["text"], + cost: { + input: 1.4, + output: 4.4, + cacheRead: 0.26, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 164000, + } satisfies Model<"openai-completions">, } as const; diff --git a/packages/ai/src/providers/vercel-ai-gateway.models.ts b/packages/ai/src/providers/vercel-ai-gateway.models.ts index ebd3ad45..55cd5031 100644 --- a/packages/ai/src/providers/vercel-ai-gateway.models.ts +++ b/packages/ai/src/providers/vercel-ai-gateway.models.ts @@ -836,13 +836,13 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.56, - output: 1.68, - cacheRead: 0.28, + input: 0.6, + output: 1.7, + cacheRead: 0, cacheWrite: 0, }, - contextWindow: 163840, - maxTokens: 8192, + contextWindow: 128000, + maxTokens: 128000, } satisfies Model<"anthropic-messages">, "deepseek/deepseek-v3.1-terminus": { id: "deepseek/deepseek-v3.1-terminus", @@ -1788,13 +1788,13 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.6, - output: 2.5, - cacheRead: 0.15, + input: 0.47, + output: 2, + cacheRead: 0.141, cacheWrite: 0, }, - contextWindow: 262114, - maxTokens: 262114, + contextWindow: 216144, + maxTokens: 216144, } satisfies Model<"anthropic-messages">, "moonshotai/kimi-k2.5": { id: "moonshotai/kimi-k2.5", @@ -2480,13 +2480,13 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.35, - output: 0.75, - cacheRead: 0.25, + input: 0.1, + output: 0.5, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 131000, + maxTokens: 131072, } satisfies Model<"anthropic-messages">, "openai/gpt-oss-20b": { id: "openai/gpt-oss-20b", @@ -2915,7 +2915,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { } satisfies Model<"anthropic-messages">, "zai/glm-4.5": { id: "zai/glm-4.5", - name: "GLM-4.5", + name: "GLM 4.5", api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", @@ -3024,13 +3024,13 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 2.25, - output: 2.75, - cacheRead: 2.25, + input: 0.6, + output: 2.2, + cacheRead: 0.12, cacheWrite: 0, }, - contextWindow: 131000, - maxTokens: 40000, + contextWindow: 200000, + maxTokens: 120000, } satisfies Model<"anthropic-messages">, "zai/glm-4.7-flash": { id: "zai/glm-4.7-flash", @@ -3075,8 +3075,8 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3.2, + input: 0.95, + output: 3.15, cacheRead: 0.2, cacheWrite: 0, }, @@ -3109,13 +3109,13 @@ export const VERCEL_AI_GATEWAY_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1.4, - output: 4.4, + input: 1.3, + output: 4.3, cacheRead: 0.26, cacheWrite: 0, }, - contextWindow: 202800, - maxTokens: 64000, + contextWindow: 202000, + maxTokens: 202000, } satisfies Model<"anthropic-messages">, "zai/glm-5.2": { id: "zai/glm-5.2", diff --git a/packages/ai/src/providers/xiaomi-token-plan-ams.models.ts b/packages/ai/src/providers/xiaomi-token-plan-ams.models.ts index fec90428..fad90ac4 100644 --- a/packages/ai/src/providers/xiaomi-token-plan-ams.models.ts +++ b/packages/ai/src/providers/xiaomi-token-plan-ams.models.ts @@ -14,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 262144, @@ -32,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, @@ -50,9 +50,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 1048576, @@ -68,9 +68,9 @@ export const XIAOMI_TOKEN_PLAN_AMS_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, diff --git a/packages/ai/src/providers/xiaomi-token-plan-cn.models.ts b/packages/ai/src/providers/xiaomi-token-plan-cn.models.ts index 9932fefa..a3a357da 100644 --- a/packages/ai/src/providers/xiaomi-token-plan-cn.models.ts +++ b/packages/ai/src/providers/xiaomi-token-plan-cn.models.ts @@ -14,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 262144, @@ -32,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, @@ -50,9 +50,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 1048576, @@ -68,9 +68,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, diff --git a/packages/ai/src/providers/xiaomi-token-plan-sgp.models.ts b/packages/ai/src/providers/xiaomi-token-plan-sgp.models.ts index dd248921..3f2d378c 100644 --- a/packages/ai/src/providers/xiaomi-token-plan-sgp.models.ts +++ b/packages/ai/src/providers/xiaomi-token-plan-sgp.models.ts @@ -14,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 262144, @@ -32,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, @@ -50,9 +50,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 1048576, @@ -68,9 +68,9 @@ export const XIAOMI_TOKEN_PLAN_SGP_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, diff --git a/packages/ai/src/providers/xiaomi.models.ts b/packages/ai/src/providers/xiaomi.models.ts index 23ec9d55..273a23f7 100644 --- a/packages/ai/src/providers/xiaomi.models.ts +++ b/packages/ai/src/providers/xiaomi.models.ts @@ -14,9 +14,9 @@ export const XIAOMI_MODELS = { reasoning: true, input: ["text"], cost: { - input: 0.1, - output: 0.3, - cacheRead: 0.01, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 262144, @@ -32,9 +32,9 @@ export const XIAOMI_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 262144, @@ -50,9 +50,9 @@ export const XIAOMI_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576, @@ -68,9 +68,9 @@ export const XIAOMI_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.4, - output: 2, - cacheRead: 0.08, + input: 0.14, + output: 0.28, + cacheRead: 0.0028, cacheWrite: 0, }, contextWindow: 1048576, @@ -86,9 +86,9 @@ export const XIAOMI_MODELS = { reasoning: true, input: ["text"], cost: { - input: 1, - output: 3, - cacheRead: 0.2, + input: 0.435, + output: 0.87, + cacheRead: 0.0036, cacheWrite: 0, }, contextWindow: 1048576,