diff --git a/packages/ai/src/image-models.generated.ts b/packages/ai/src/image-models.generated.ts index 7545a9f1..bd6a1e0b 100644 --- a/packages/ai/src/image-models.generated.ts +++ b/packages/ai/src/image-models.generated.ts @@ -215,6 +215,51 @@ export const IMAGE_MODELS = { cacheWrite: 0, }, } satisfies ImagesModel<"openrouter-images">, + "openai/gpt-image-1": { + id: "openai/gpt-image-1", + name: "OpenAI: GPT Image 1", + api: "openrouter-images", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + input: ["text", "image"], + output: ["image"], + cost: { + input: 10, + output: 10, + cacheRead: 1.25, + cacheWrite: 0, + }, + } satisfies ImagesModel<"openrouter-images">, + "openai/gpt-image-1-mini": { + id: "openai/gpt-image-1-mini", + name: "OpenAI: GPT Image 1 Mini", + api: "openrouter-images", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + input: ["text", "image"], + output: ["image"], + cost: { + input: 2.5, + output: 2.5, + cacheRead: 0.25, + cacheWrite: 0, + }, + } satisfies ImagesModel<"openrouter-images">, + "openai/gpt-image-2": { + id: "openai/gpt-image-2", + name: "OpenAI: GPT Image 2", + api: "openrouter-images", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + input: ["text", "image"], + output: ["image"], + cost: { + input: 8, + output: 8, + cacheRead: 2, + cacheWrite: 0, + }, + } satisfies ImagesModel<"openrouter-images">, "openrouter/auto": { id: "openrouter/auto", name: "Auto Router", diff --git a/packages/ai/src/providers/huggingface.models.ts b/packages/ai/src/providers/huggingface.models.ts index ffdcdaf9..695b72d6 100644 --- a/packages/ai/src/providers/huggingface.models.ts +++ b/packages/ai/src/providers/huggingface.models.ts @@ -328,6 +328,24 @@ export const HUGGINGFACE_MODELS = { contextWindow: 262144, maxTokens: 65536, } satisfies Model<"openai-completions">, + "Qwen/Qwen3.6-27B": { + id: "Qwen/Qwen3.6-27B", + name: "Qwen3.6 27B", + api: "openai-completions", + provider: "huggingface", + baseUrl: "https://router.huggingface.co/v1", + compat: {"supportsDeveloperRole":false}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.47, + output: 3.19, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 65536, + } satisfies Model<"openai-completions">, "Qwen/Qwen3.6-35B-A3B": { id: "Qwen/Qwen3.6-35B-A3B", name: "Qwen3.6 35B-A3B", @@ -364,6 +382,24 @@ export const HUGGINGFACE_MODELS = { contextWindow: 262144, maxTokens: 4096, } satisfies Model<"openai-completions">, + "XiaomiMiMo/MiMo-V2.5-Pro": { + id: "XiaomiMiMo/MiMo-V2.5-Pro", + name: "MiMo-V2.5-Pro", + api: "openai-completions", + provider: "huggingface", + baseUrl: "https://router.huggingface.co/v1", + compat: {"supportsDeveloperRole":false}, + reasoning: true, + input: ["text"], + cost: { + input: 1, + output: 3, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1048576, + maxTokens: 131072, + } satisfies Model<"openai-completions">, "deepseek-ai/DeepSeek-R1": { id: "deepseek-ai/DeepSeek-R1", name: "DeepSeek-R1", @@ -634,6 +670,24 @@ export const HUGGINGFACE_MODELS = { contextWindow: 262144, maxTokens: 256000, } satisfies Model<"openai-completions">, + "stepfun-ai/Step-3.7-Flash": { + id: "stepfun-ai/Step-3.7-Flash", + name: "Step 3.7 Flash", + api: "openai-completions", + provider: "huggingface", + baseUrl: "https://router.huggingface.co/v1", + compat: {"supportsDeveloperRole":false}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.2, + output: 1.15, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 256000, + } satisfies Model<"openai-completions">, "zai-org/GLM-4.5": { id: "zai-org/GLM-4.5", name: "GLM-4.5", diff --git a/packages/ai/src/providers/minimax-cn.models.ts b/packages/ai/src/providers/minimax-cn.models.ts index d1f90c21..4a37d413 100644 --- a/packages/ai/src/providers/minimax-cn.models.ts +++ b/packages/ai/src/providers/minimax-cn.models.ts @@ -10,6 +10,7 @@ export const MINIMAX_CN_MODELS = { api: "anthropic-messages", provider: "minimax-cn", baseUrl: "https://api.minimaxi.com/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text"], cost: { @@ -27,6 +28,7 @@ export const MINIMAX_CN_MODELS = { api: "anthropic-messages", provider: "minimax-cn", baseUrl: "https://api.minimaxi.com/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text"], cost: { @@ -44,6 +46,7 @@ export const MINIMAX_CN_MODELS = { api: "anthropic-messages", provider: "minimax-cn", baseUrl: "https://api.minimaxi.com/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text", "image"], cost: { diff --git a/packages/ai/src/providers/minimax.models.ts b/packages/ai/src/providers/minimax.models.ts index 0ff346c7..85465b34 100644 --- a/packages/ai/src/providers/minimax.models.ts +++ b/packages/ai/src/providers/minimax.models.ts @@ -10,6 +10,7 @@ export const MINIMAX_MODELS = { api: "anthropic-messages", provider: "minimax", baseUrl: "https://api.minimax.io/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text"], cost: { @@ -27,6 +28,7 @@ export const MINIMAX_MODELS = { api: "anthropic-messages", provider: "minimax", baseUrl: "https://api.minimax.io/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text"], cost: { @@ -44,6 +46,7 @@ export const MINIMAX_MODELS = { api: "anthropic-messages", provider: "minimax", baseUrl: "https://api.minimax.io/anthropic", + compat: {"maxTokensSharesContextWindow":true}, reasoning: true, input: ["text", "image"], cost: { diff --git a/packages/ai/src/providers/openrouter.models.ts b/packages/ai/src/providers/openrouter.models.ts index 0dad51de..716afd5d 100644 --- a/packages/ai/src/providers/openrouter.models.ts +++ b/packages/ai/src/providers/openrouter.models.ts @@ -1807,7 +1807,7 @@ export const OPENROUTER_MODELS = { cost: { input: 0.6, output: 2.5, - cacheRead: 0, + cacheRead: 0.6, cacheWrite: 0, }, contextWindow: 262144, @@ -3799,11 +3799,11 @@ export const OPENROUTER_MODELS = { cost: { input: 0.14, output: 1, - cacheRead: 0, + cacheRead: 0.05, cacheWrite: 0, }, contextWindow: 262144, - maxTokens: 262144, + maxTokens: 81920, } satisfies Model<"openai-completions">, "qwen/qwen3.5-397b-a17b": { id: "qwen/qwen3.5-397b-a17b", @@ -4057,6 +4057,24 @@ export const OPENROUTER_MODELS = { contextWindow: 256000, maxTokens: 128000, } satisfies Model<"openai-completions">, + "sakana/fugu-ultra": { + id: "sakana/fugu-ultra", + name: "Sakana: Fugu Ultra", + api: "openai-completions", + provider: "openrouter", + baseUrl: "https://openrouter.ai/api/v1", + compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 5, + output: 30, + cacheRead: 0.5, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 128000, + } satisfies Model<"openai-completions">, "sao10k/l3.1-euryale-70b": { id: "sao10k/l3.1-euryale-70b", name: "Sao10K: Llama 3.1 Euryale 70B v2.2", @@ -4229,13 +4247,13 @@ export const OPENROUTER_MODELS = { reasoning: true, input: ["text", "image"], cost: { - input: 0.14, + input: 0.105, output: 0.28, - cacheRead: 0.0028, + cacheRead: 0, cacheWrite: 0, }, contextWindow: 1048576, - maxTokens: 131072, + maxTokens: 4096, } satisfies Model<"openai-completions">, "xiaomi/mimo-v2.5-pro": { id: "xiaomi/mimo-v2.5-pro", @@ -4429,11 +4447,11 @@ export const OPENROUTER_MODELS = { cost: { input: 0.98, output: 3.08, - cacheRead: 0.49, + cacheRead: 0.182, cacheWrite: 0, }, contextWindow: 202752, - maxTokens: 65535, + maxTokens: 4096, } satisfies Model<"openai-completions">, "z-ai/glm-5.2": { id: "z-ai/glm-5.2", @@ -4446,13 +4464,13 @@ export const OPENROUTER_MODELS = { thinkingLevelMap: {"xhigh":"xhigh"}, input: ["text"], cost: { - input: 0.98, - output: 3.08, - cacheRead: 0.182, + input: 0.95, + output: 3, + cacheRead: 0.18, cacheWrite: 0, }, contextWindow: 1048576, - maxTokens: 4096, + maxTokens: 32768, } satisfies Model<"openai-completions">, "z-ai/glm-5v-turbo": { id: "z-ai/glm-5v-turbo", diff --git a/packages/ai/src/providers/vercel-ai-gateway.models.ts b/packages/ai/src/providers/vercel-ai-gateway.models.ts index ea65e49c..ebd3ad45 100644 --- a/packages/ai/src/providers/vercel-ai-gateway.models.ts +++ b/packages/ai/src/providers/vercel-ai-gateway.models.ts @@ -112,7 +112,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text"], cost: { input: 1.5, @@ -129,7 +129,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text"], cost: { input: 0.15, @@ -146,7 +146,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text"], cost: { input: 0.5, @@ -259,6 +259,40 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 131072, maxTokens: 32768, } satisfies Model<"anthropic-messages">, + "alibaba/qwen3-vl-235b-a22b-instruct": { + id: "alibaba/qwen3-vl-235b-a22b-instruct", + name: "Qwen3 VL 235B A22B Instruct", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 129024, + } satisfies Model<"anthropic-messages">, + "alibaba/qwen3-vl-instruct": { + id: "alibaba/qwen3-vl-instruct", + name: "Qwen3 VL 235B A22B Instruct", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.4, + output: 1.6, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 129024, + } satisfies Model<"anthropic-messages">, "alibaba/qwen3-vl-thinking": { id: "alibaba/qwen3-vl-thinking", name: "Qwen3 VL 235B A22B Thinking", @@ -378,6 +412,74 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 1000000, maxTokens: 64000, } satisfies Model<"anthropic-messages">, + "amazon/nova-2-lite": { + id: "amazon/nova-2-lite", + name: "Nova 2 Lite", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.3, + output: 2.5, + cacheRead: 0.075, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 1000000, + } satisfies Model<"anthropic-messages">, + "amazon/nova-lite": { + id: "amazon/nova-lite", + name: "Nova Lite", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.06, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 300000, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, + "amazon/nova-micro": { + id: "amazon/nova-micro", + name: "Nova Micro", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 0.035, + output: 0.14, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, + "amazon/nova-pro": { + id: "amazon/nova-pro", + name: "Nova Pro", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.8, + output: 3.2, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 300000, + maxTokens: 8192, + } satisfies Model<"anthropic-messages">, "anthropic/claude-3-haiku": { id: "anthropic/claude-3-haiku", name: "Claude 3 Haiku", @@ -623,6 +725,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 262100, maxTokens: 80000, } satisfies Model<"anthropic-messages">, + "arcee-ai/trinity-mini": { + id: "arcee-ai/trinity-mini", + name: "Trinity Mini", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 0.045, + output: 0.15, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 131072, + } satisfies Model<"anthropic-messages">, "bytedance/seed-1.6": { id: "bytedance/seed-1.6", name: "Seed 1.6", @@ -630,7 +749,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text"], + input: ["text", "image"], cost: { input: 0.25, output: 2, @@ -640,6 +759,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 256000, maxTokens: 32000, } satisfies Model<"anthropic-messages">, + "bytedance/seed-1.8": { + id: "bytedance/seed-1.8", + name: "Bytedance Seed 1.8", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.25, + output: 2, + cacheRead: 0.05, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 64000, + } satisfies Model<"anthropic-messages">, "cohere/command-a": { id: "cohere/command-a", name: "Command A", @@ -731,8 +867,8 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, - input: ["text", "image"], + reasoning: false, + input: ["text"], cost: { input: 0.28, output: 0.42, @@ -749,7 +885,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text", "image"], + input: ["text"], cost: { input: 0.62, output: 1.85, @@ -766,7 +902,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text", "image"], + input: ["text"], cost: { input: 0.14, output: 0.28, @@ -969,7 +1105,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: false, + reasoning: true, input: ["text", "image"], cost: { input: 0.14, @@ -1014,6 +1150,40 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 32000, maxTokens: 16384, } satisfies Model<"anthropic-messages">, + "interfaze/interfaze-beta": { + id: "interfaze/interfaze-beta", + name: "Interfaze Beta", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 1.5, + output: 3.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 32000, + } satisfies Model<"anthropic-messages">, + "kwaipilot/kat-coder-pro-v1": { + id: "kwaipilot/kat-coder-pro-v1", + name: "KAT-Coder-Pro V1", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 0.3, + output: 1.2, + cacheRead: 0.06, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 32000, + } satisfies Model<"anthropic-messages">, "kwaipilot/kat-coder-pro-v2": { id: "kwaipilot/kat-coder-pro-v2", name: "Kat Coder Pro V2", @@ -1048,6 +1218,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 128000, maxTokens: 100000, } satisfies Model<"anthropic-messages">, + "meituan/longcat-flash-thinking-2601": { + id: "meituan/longcat-flash-thinking-2601", + name: "LongCat Flash Thinking 2601", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 32768, + maxTokens: 32768, + } satisfies Model<"anthropic-messages">, "meta/llama-3.1-70b": { id: "meta/llama-3.1-70b", name: "Llama 3.1 70B Instruct", @@ -1361,7 +1548,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0.1, output: 0.3, @@ -1371,6 +1558,57 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 256000, maxTokens: 256000, } satisfies Model<"anthropic-messages">, + "mistral/magistral-medium": { + id: "mistral/magistral-medium", + name: "Magistral Medium 2509", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 2, + output: 5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 64000, + } satisfies Model<"anthropic-messages">, + "mistral/magistral-small": { + id: "mistral/magistral-small", + name: "Magistral Small 2509", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text", "image"], + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 128000, + maxTokens: 64000, + } satisfies Model<"anthropic-messages">, + "mistral/ministral-14b": { + id: "mistral/ministral-14b", + name: "Ministral 14B", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.2, + output: 0.2, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 256000, + } satisfies Model<"anthropic-messages">, "mistral/ministral-3b": { id: "mistral/ministral-3b", name: "Ministral 3B", @@ -1405,6 +1643,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 128000, maxTokens: 4000, } satisfies Model<"anthropic-messages">, + "mistral/mistral-large-3": { + id: "mistral/mistral-large-3", + name: "Mistral Large 3", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text", "image"], + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 256000, + maxTokens: 256000, + } satisfies Model<"anthropic-messages">, "mistral/mistral-medium": { id: "mistral/mistral-medium", name: "Mistral Medium 3.1", @@ -1429,7 +1684,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text"], + input: ["text", "image"], cost: { input: 1.5, output: 7.5, @@ -1609,6 +1864,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 262144, maxTokens: 32768, } satisfies Model<"anthropic-messages">, + "nvidia/nemotron-3-nano-30b-a3b": { + id: "nvidia/nemotron-3-nano-30b-a3b", + name: "Nemotron 3 Nano 30B A3B", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 0.05, + output: 0.24, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"anthropic-messages">, "nvidia/nemotron-3-super-120b-a12b": { id: "nvidia/nemotron-3-super-120b-a12b", name: "NVIDIA Nemotron 3 Super 120B A12B", @@ -1677,6 +1949,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 131072, maxTokens: 131072, } satisfies Model<"anthropic-messages">, + "openai/gpt-3.5-turbo": { + id: "openai/gpt-3.5-turbo", + name: "GPT-3.5 Turbo", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: false, + input: ["text"], + cost: { + input: 0.5, + output: 1.5, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 16385, + maxTokens: 4096, + } satisfies Model<"anthropic-messages">, "openai/gpt-4-turbo": { id: "openai/gpt-4-turbo", name: "GPT-4 Turbo", @@ -1802,7 +2091,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text", "image"], cost: { input: 1.25, @@ -1938,7 +2227,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, input: ["text", "image"], cost: { input: 1.25, @@ -1990,7 +2279,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, thinkingLevelMap: {"xhigh":"xhigh"}, input: ["text", "image"], cost: { @@ -2044,7 +2333,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { api: "anthropic-messages", provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", - reasoning: true, + reasoning: false, thinkingLevelMap: {"xhigh":"xhigh"}, input: ["text", "image"], cost: { @@ -2335,40 +2624,6 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 200000, maxTokens: 100000, } satisfies Model<"anthropic-messages">, - "perplexity/sonar": { - id: "perplexity/sonar", - name: "Sonar", - api: "anthropic-messages", - provider: "vercel-ai-gateway", - baseUrl: "https://ai-gateway.vercel.sh", - reasoning: false, - input: ["text", "image"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 127000, - maxTokens: 8000, - } satisfies Model<"anthropic-messages">, - "perplexity/sonar-pro": { - id: "perplexity/sonar-pro", - name: "Sonar Pro", - api: "anthropic-messages", - provider: "vercel-ai-gateway", - baseUrl: "https://ai-gateway.vercel.sh", - reasoning: false, - input: ["text", "image"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 200000, - maxTokens: 8000, - } satisfies Model<"anthropic-messages">, "sakana/fugu-ultra": { id: "sakana/fugu-ultra", name: "Fugu Ultra", @@ -2648,7 +2903,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text", "image"], + input: ["text"], cost: { input: 0.435, output: 0.87, @@ -2852,7 +3107,7 @@ export const VERCEL_AI_GATEWAY_MODELS = { provider: "vercel-ai-gateway", baseUrl: "https://ai-gateway.vercel.sh", reasoning: true, - input: ["text", "image"], + input: ["text"], cost: { input: 1.4, output: 4.4, @@ -2879,6 +3134,23 @@ export const VERCEL_AI_GATEWAY_MODELS = { contextWindow: 1000000, maxTokens: 128000, } satisfies Model<"anthropic-messages">, + "zai/glm-5.2-fast": { + id: "zai/glm-5.2-fast", + name: "GLM 5.2 Fast", + api: "anthropic-messages", + provider: "vercel-ai-gateway", + baseUrl: "https://ai-gateway.vercel.sh", + reasoning: true, + input: ["text"], + cost: { + input: 3, + output: 10.25, + cacheRead: 0.5, + cacheWrite: 0, + }, + contextWindow: 1000000, + maxTokens: 128000, + } satisfies Model<"anthropic-messages">, "zai/glm-5v-turbo": { id: "zai/glm-5v-turbo", name: "GLM 5V Turbo",