From 132ae929444474276b8544bc2fe252b6546c087b Mon Sep 17 00:00:00 2001 From: Andriyansyah Nurrachman Date: Mon, 16 Mar 2026 11:22:29 +0700 Subject: [PATCH] feat: update ollama cloud provider models (#578) --- packages/pi-ai/src/models.generated.ts | 586 ++++++++++++++++++++----- 1 file changed, 473 insertions(+), 113 deletions(-) diff --git a/packages/pi-ai/src/models.generated.ts b/packages/pi-ai/src/models.generated.ts index 1a4d862a8..85eb1fa85 100644 --- a/packages/pi-ai/src/models.generated.ts +++ b/packages/pi-ai/src/models.generated.ts @@ -13523,9 +13523,63 @@ export const MODELS = { } satisfies Model<"anthropic-messages">, }, "ollama-cloud": { - "llama3.1:8b": { - id: "llama3.1:8b", - name: "Llama 3.1 8B", + "cogito-2.1:671b": { + id: "cogito-2.1:671b", + name: "Cogito 2.1 671B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 163840, + maxTokens: 32000, + } satisfies Model<"openai-completions">, + "deepseek-v3.1:671b": { + id: "deepseek-v3.1:671b", + name: "DeepSeek V3.1 671B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 163840, + maxTokens: 163840, + } satisfies Model<"openai-completions">, + "deepseek-v3.2": { + id: "deepseek-v3.2", + name: "DeepSeek V3.2", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 163840, + maxTokens: 65536, + } satisfies Model<"openai-completions">, + "devstral-2:123b": { + id: "devstral-2:123b", + name: "Devstral 2 123B", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", @@ -13538,48 +13592,30 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 262144, + maxTokens: 262144, } satisfies Model<"openai-completions">, - "llama3.1:70b": { - id: "llama3.1:70b", - name: "Llama 3.1 70B", + "devstral-small-2:24b": { + id: "devstral-small-2:24b", + name: "Devstral Small 2 24B", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 262144, + maxTokens: 262144, } satisfies Model<"openai-completions">, - "llama3.1:405b": { - id: "llama3.1:405b", - name: "Llama 3.1 405B", - api: "openai-completions", - provider: "ollama-cloud", - baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: false, - input: ["text"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 8192, - } satisfies Model<"openai-completions">, - "qwen3:8b": { - id: "qwen3:8b", - name: "Qwen 3 8B", + "gemini-3-flash-preview": { + id: "gemini-3-flash-preview", + name: "Gemini 3 Flash Preview", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", @@ -13592,62 +13628,8 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, - } satisfies Model<"openai-completions">, - "qwen3:32b": { - id: "qwen3:32b", - name: "Qwen 3 32B", - api: "openai-completions", - provider: "ollama-cloud", - baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: true, - input: ["text"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 8192, - } satisfies Model<"openai-completions">, - "deepseek-r1:8b": { - id: "deepseek-r1:8b", - name: "DeepSeek R1 8B", - api: "openai-completions", - provider: "ollama-cloud", - baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: true, - input: ["text"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 8192, - } satisfies Model<"openai-completions">, - "deepseek-r1:70b": { - id: "deepseek-r1:70b", - name: "DeepSeek R1 70B", - api: "openai-completions", - provider: "ollama-cloud", - baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: true, - input: ["text"], - cost: { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 1048576, + maxTokens: 65536, } satisfies Model<"openai-completions">, "gemma3:12b": { id: "gemma3:12b", @@ -13657,7 +13639,7 @@ export const MODELS = { baseUrl: "https://ollama.com/v1", compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0, output: 0, @@ -13665,7 +13647,7 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 8192, + maxTokens: 131072, } satisfies Model<"openai-completions">, "gemma3:27b": { id: "gemma3:27b", @@ -13675,7 +13657,7 @@ export const MODELS = { baseUrl: "https://ollama.com/v1", compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0, output: 0, @@ -13683,17 +13665,17 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 8192, + maxTokens: 131072, } satisfies Model<"openai-completions">, - "mistral:7b": { - id: "mistral:7b", - name: "Mistral 7B", + "gemma3:4b": { + id: "gemma3:4b", + name: "Gemma 3 4B", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, reasoning: false, - input: ["text"], + input: ["text", "image"], cost: { input: 0, output: 0, @@ -13701,16 +13683,16 @@ export const MODELS = { cacheWrite: 0, }, contextWindow: 131072, - maxTokens: 8192, + maxTokens: 131072, } satisfies Model<"openai-completions">, - "phi4:14b": { - id: "phi4:14b", - name: "Phi-4 14B", + "glm-4.6": { + id: "glm-4.6", + name: "GLM 4.6", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: false, + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, input: ["text"], cost: { input: 0, @@ -13718,17 +13700,17 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 202752, + maxTokens: 131072, } satisfies Model<"openai-completions">, - "gpt-oss:20b": { - id: "gpt-oss:20b", - name: "GPT-OSS 20B", + "glm-4.7": { + id: "glm-4.7", + name: "GLM 4.7", api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", - compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, - reasoning: false, + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, input: ["text"], cost: { input: 0, @@ -13736,8 +13718,26 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 202752, + maxTokens: 131072, + } satisfies Model<"openai-completions">, + "glm-5": { + id: "glm-5", + name: "GLM 5", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 202752, + maxTokens: 131072, } satisfies Model<"openai-completions">, "gpt-oss:120b": { id: "gpt-oss:120b", @@ -13745,6 +13745,42 @@ export const MODELS = { api: "openai-completions", provider: "ollama-cloud", baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 32768, + } satisfies Model<"openai-completions">, + "gpt-oss:20b": { + id: "gpt-oss:20b", + name: "GPT-OSS 20B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 131072, + maxTokens: 32768, + } satisfies Model<"openai-completions">, + "kimi-k2:1t": { + id: "kimi-k2:1t", + name: "Kimi K2 1T", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, reasoning: false, input: ["text"], @@ -13754,8 +13790,332 @@ export const MODELS = { cacheRead: 0, cacheWrite: 0, }, - contextWindow: 131072, - maxTokens: 8192, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"openai-completions">, + "kimi-k2.5": { + id: "kimi-k2.5", + name: "Kimi K2.5", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"openai-completions">, + "kimi-k2-thinking": { + id: "kimi-k2-thinking", + name: "Kimi K2 Thinking", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"openai-completions">, + "minimax-m2.1": { + id: "minimax-m2.1", + name: "Minimax M2.1", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 204800, + maxTokens: 131072, + } satisfies Model<"openai-completions">, + "minimax-m2.5": { + id: "minimax-m2.5", + name: "Minimax M2.5", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 204800, + maxTokens: 131072, + } satisfies Model<"openai-completions">, + "minimax-m2": { + id: "minimax-m2", + name: "Minimax M2", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 204800, + maxTokens: 128000, + } satisfies Model<"openai-completions">, + "ministral-3:14b": { + id: "ministral-3:14b", + name: "Ministral 3 14B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 128000, + } satisfies Model<"openai-completions">, + "ministral-3:3b": { + id: "ministral-3:3b", + name: "Ministral 3 3B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 128000, + } satisfies Model<"openai-completions">, + "ministral-3:8b": { + id: "ministral-3:8b", + name: "Ministral 3 8B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 128000, + } satisfies Model<"openai-completions">, + "mistral-large-3:675b": { + id: "mistral-large-3:675b", + name: "Mistral Large 3 675B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 262144, + } satisfies Model<"openai-completions">, + "nemotron-3-nano:30b": { + id: "nemotron-3-nano:30b", + name: "Nemotron 3 Nano 30B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 1048576, + maxTokens: 131072, + } satisfies Model<"openai-completions">, + "nemotron-3-super": { + id: "nemotron-3-super", + name: "Nemotron 3 Super", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 65536, + } satisfies Model<"openai-completions">, + "qwen3.5:397b": { + id: "qwen3.5:397b", + name: "Qwen 3.5 397B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 81920, + } satisfies Model<"openai-completions">, + "qwen3-coder:480b": { + id: "qwen3-coder:480b", + name: "Qwen 3 Coder 480B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 65536, + } satisfies Model<"openai-completions">, + "qwen3-coder-next": { + id: "qwen3-coder-next", + name: "Qwen 3 Coder Next", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 65536, + } satisfies Model<"openai-completions">, + "qwen3-next:80b": { + id: "qwen3-next:80b", + name: "Qwen 3 Next 80B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 32768, + } satisfies Model<"openai-completions">, + "qwen3-vl:235b-instruct": { + id: "qwen3-vl:235b-instruct", + name: "Qwen 3 VL 235B Instruct", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 131072, + } satisfies Model<"openai-completions">, + "qwen3-vl:235b": { + id: "qwen3-vl:235b", + name: "Qwen 3 VL 235B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: true, + input: ["text", "image"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 262144, + maxTokens: 32768, + } satisfies Model<"openai-completions">, + "rnj-1:8b": { + id: "rnj-1:8b", + name: "RNJ 1 8B", + api: "openai-completions", + provider: "ollama-cloud", + baseUrl: "https://ollama.com/v1", + compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false}, + reasoning: false, + input: ["text"], + cost: { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + }, + contextWindow: 32768, + maxTokens: 4096, } satisfies Model<"openai-completions">, }, } as const;