diff --git a/internal/providers/configs/openrouter.json b/internal/providers/configs/openrouter.json index 01d1c0a3d87d01533adc1715824ed2ad5db0cf10..bc394e78e2013289377191c8e27e39cff7111a08 100644 --- a/internal/providers/configs/openrouter.json +++ b/internal/providers/configs/openrouter.json @@ -23,12 +23,12 @@ { "id": "z-ai/glm-4.5v", "name": "Z.AI: GLM 4.5V", - "cost_per_1m_in": 0.6, - "cost_per_1m_out": 1.7999999999999998, + "cost_per_1m_in": 0.5, + "cost_per_1m_out": 1.7, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0.11, + "cost_per_1m_out_cached": 0, "context_window": 65536, - "default_max_tokens": 8192, + "default_max_tokens": 32768, "can_reason": true, "has_reasoning_efforts": false, "supports_attachments": true @@ -156,9 +156,9 @@ "cost_per_1m_in": 0.6, "cost_per_1m_out": 2.2, "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, + "cost_per_1m_out_cached": 0.11, "context_window": 131072, - "default_max_tokens": 65536, + "default_max_tokens": 48000, "can_reason": true, "has_reasoning_efforts": false, "supports_attachments": false @@ -231,12 +231,12 @@ { "id": "qwen/qwen3-coder", "name": "Qwen: Qwen3 Coder ", - "cost_per_1m_in": 0.38, - "cost_per_1m_out": 1.53, + "cost_per_1m_in": 1.5, + "cost_per_1m_out": 7.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, - "default_max_tokens": 131072, + "default_max_tokens": 32768, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": false @@ -257,8 +257,8 @@ { "id": "qwen/qwen3-235b-a22b-2507", "name": "Qwen: Qwen3 235B A22B Instruct 2507", - "cost_per_1m_in": 0.22, - "cost_per_1m_out": 0.7999999999999999, + "cost_per_1m_in": 0.15, + "cost_per_1m_out": 0.85, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 262144, @@ -283,12 +283,12 @@ { "id": "moonshotai/kimi-k2", "name": "MoonshotAI: Kimi K2", - "cost_per_1m_in": 0.5700000000000001, - "cost_per_1m_out": 2.3, + "cost_per_1m_in": 0.6, + "cost_per_1m_out": 2.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, - "default_max_tokens": 65536, + "default_max_tokens": 13107, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": false @@ -348,8 +348,8 @@ { "id": "mistralai/mistral-small-3.2-24b-instruct", "name": "Mistral: Mistral Small 3.2 24B", - "cost_per_1m_in": 0.10366159999999999, - "cost_per_1m_out": 0.414848, + "cost_per_1m_in": 0.09999999999999999, + "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, @@ -491,12 +491,12 @@ { "id": "deepseek/deepseek-r1-0528", "name": "DeepSeek: R1 0528", - "cost_per_1m_in": 0.7, - "cost_per_1m_out": 2.5, + "cost_per_1m_in": 2.5500000000000003, + "cost_per_1m_out": 5.95, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 163840, - "default_max_tokens": 81920, + "default_max_tokens": 65536, "can_reason": true, "has_reasoning_efforts": false, "supports_attachments": false @@ -540,19 +540,6 @@ "has_reasoning_efforts": false, "supports_attachments": false }, - { - "id": "mistralai/devstral-small-2505", - "name": "Mistral: Devstral Small 2505", - "cost_per_1m_in": 0.01999188, - "cost_per_1m_out": 0.0800064, - "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 131072, - "default_max_tokens": 13107, - "can_reason": false, - "has_reasoning_efforts": false, - "supports_attachments": false - }, { "id": "openai/codex-mini", "name": "OpenAI: Codex Mini", @@ -660,12 +647,12 @@ { "id": "qwen/qwen3-32b", "name": "Qwen: Qwen3 32B", - "cost_per_1m_in": 0.39999999999999997, - "cost_per_1m_out": 0.7999999999999999, + "cost_per_1m_in": 0.15, + "cost_per_1m_out": 0.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, - "default_max_tokens": 16384, + "default_max_tokens": 4000, "can_reason": true, "has_reasoning_efforts": false, "supports_attachments": false @@ -803,12 +790,12 @@ { "id": "meta-llama/llama-4-maverick", "name": "Meta: Llama 4 Maverick", - "cost_per_1m_in": 0.18, - "cost_per_1m_out": 0.6, + "cost_per_1m_in": 0.22, + "cost_per_1m_out": 0.88, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 1048576, - "default_max_tokens": 524288, + "default_max_tokens": 104857, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": true @@ -912,7 +899,7 @@ "cost_per_1m_in_cached": 3.75, "cost_per_1m_out_cached": 0.3, "context_window": 200000, - "default_max_tokens": 32000, + "default_max_tokens": 64000, "can_reason": true, "has_reasoning_efforts": false, "supports_attachments": true @@ -1141,12 +1128,12 @@ { "id": "meta-llama/llama-3.3-70b-instruct", "name": "Meta: Llama 3.3 70B Instruct", - "cost_per_1m_in": 0.13, - "cost_per_1m_out": 0.39, + "cost_per_1m_in": 0.12, + "cost_per_1m_out": 0.3, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 131072, - "default_max_tokens": 60000, + "default_max_tokens": 65536, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": false @@ -1256,8 +1243,8 @@ "supports_attachments": false }, { - "id": "anthropic/claude-3.5-haiku", - "name": "Anthropic: Claude 3.5 Haiku", + "id": "anthropic/claude-3.5-haiku-20241022", + "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)", "cost_per_1m_in": 0.7999999999999999, "cost_per_1m_out": 4, "cost_per_1m_in_cached": 1, @@ -1269,8 +1256,8 @@ "supports_attachments": true }, { - "id": "anthropic/claude-3.5-haiku-20241022", - "name": "Anthropic: Claude 3.5 Haiku (2024-10-22)", + "id": "anthropic/claude-3.5-haiku", + "name": "Anthropic: Claude 3.5 Haiku", "cost_per_1m_in": 0.7999999999999999, "cost_per_1m_out": 4, "cost_per_1m_in_cached": 1, @@ -1437,19 +1424,6 @@ "has_reasoning_efforts": false, "supports_attachments": true }, - { - "id": "meta-llama/llama-3.1-8b-instruct", - "name": "Meta: Llama 3.1 8B Instruct", - "cost_per_1m_in": 0.049999999999999996, - "cost_per_1m_out": 0.08, - "cost_per_1m_in_cached": 0, - "cost_per_1m_out_cached": 0, - "context_window": 131072, - "default_max_tokens": 65536, - "can_reason": false, - "has_reasoning_efforts": false, - "supports_attachments": false - }, { "id": "meta-llama/llama-3.1-405b-instruct", "name": "Meta: Llama 3.1 405B Instruct", @@ -1476,6 +1450,19 @@ "has_reasoning_efforts": false, "supports_attachments": false }, + { + "id": "meta-llama/llama-3.1-8b-instruct", + "name": "Meta: Llama 3.1 8B Instruct", + "cost_per_1m_in": 0.09999999999999999, + "cost_per_1m_out": 0.09999999999999999, + "cost_per_1m_in_cached": 0, + "cost_per_1m_out_cached": 0, + "context_window": 131072, + "default_max_tokens": 4000, + "can_reason": false, + "has_reasoning_efforts": false, + "supports_attachments": false + }, { "id": "mistralai/mistral-nemo", "name": "Mistral: Mistral Nemo", @@ -1490,8 +1477,8 @@ "supports_attachments": false }, { - "id": "openai/gpt-4o-mini", - "name": "OpenAI: GPT-4o-mini", + "id": "openai/gpt-4o-mini-2024-07-18", + "name": "OpenAI: GPT-4o-mini (2024-07-18)", "cost_per_1m_in": 0.15, "cost_per_1m_out": 0.6, "cost_per_1m_in_cached": 0, @@ -1503,8 +1490,8 @@ "supports_attachments": true }, { - "id": "openai/gpt-4o-mini-2024-07-18", - "name": "OpenAI: GPT-4o-mini (2024-07-18)", + "id": "openai/gpt-4o-mini", + "name": "OpenAI: GPT-4o-mini", "cost_per_1m_in": 0.15, "cost_per_1m_out": 0.6, "cost_per_1m_in_cached": 0, @@ -1529,10 +1516,10 @@ "supports_attachments": true }, { - "id": "mistralai/mistral-7b-instruct:free", - "name": "Mistral: Mistral 7B Instruct (free)", - "cost_per_1m_in": 0, - "cost_per_1m_out": 0, + "id": "mistralai/mistral-7b-instruct-v0.3", + "name": "Mistral: Mistral 7B Instruct v0.3", + "cost_per_1m_in": 0.028, + "cost_per_1m_out": 0.054, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 32768, @@ -1542,10 +1529,10 @@ "supports_attachments": false }, { - "id": "mistralai/mistral-7b-instruct", - "name": "Mistral: Mistral 7B Instruct", - "cost_per_1m_in": 0.028, - "cost_per_1m_out": 0.054, + "id": "mistralai/mistral-7b-instruct:free", + "name": "Mistral: Mistral 7B Instruct (free)", + "cost_per_1m_in": 0, + "cost_per_1m_out": 0, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 32768, @@ -1555,8 +1542,8 @@ "supports_attachments": false }, { - "id": "mistralai/mistral-7b-instruct-v0.3", - "name": "Mistral: Mistral 7B Instruct v0.3", + "id": "mistralai/mistral-7b-instruct", + "name": "Mistral: Mistral 7B Instruct", "cost_per_1m_in": 0.028, "cost_per_1m_out": 0.054, "cost_per_1m_in_cached": 0, @@ -1646,10 +1633,10 @@ "supports_attachments": true }, { - "id": "meta-llama/llama-3-8b-instruct", - "name": "Meta: Llama 3 8B Instruct", - "cost_per_1m_in": 0.03, - "cost_per_1m_out": 0.06, + "id": "meta-llama/llama-3-70b-instruct", + "name": "Meta: Llama 3 70B Instruct", + "cost_per_1m_in": 0.3, + "cost_per_1m_out": 0.39999999999999997, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8192, @@ -1659,10 +1646,10 @@ "supports_attachments": false }, { - "id": "meta-llama/llama-3-70b-instruct", - "name": "Meta: Llama 3 70B Instruct", - "cost_per_1m_in": 0.3, - "cost_per_1m_out": 0.39999999999999997, + "id": "meta-llama/llama-3-8b-instruct", + "name": "Meta: Llama 3 8B Instruct", + "cost_per_1m_in": 0.03, + "cost_per_1m_out": 0.06, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, "context_window": 8192, @@ -1685,27 +1672,27 @@ "supports_attachments": false }, { - "id": "google/gemini-pro-1.5", - "name": "Google: Gemini 1.5 Pro", - "cost_per_1m_in": 1.25, - "cost_per_1m_out": 5, + "id": "openai/gpt-4-turbo", + "name": "OpenAI: GPT-4 Turbo", + "cost_per_1m_in": 10, + "cost_per_1m_out": 30, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 2000000, - "default_max_tokens": 4096, + "context_window": 128000, + "default_max_tokens": 2048, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": true }, { - "id": "openai/gpt-4-turbo", - "name": "OpenAI: GPT-4 Turbo", - "cost_per_1m_in": 10, - "cost_per_1m_out": 30, + "id": "google/gemini-pro-1.5", + "name": "Google: Gemini 1.5 Pro", + "cost_per_1m_in": 1.25, + "cost_per_1m_out": 5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 128000, - "default_max_tokens": 2048, + "context_window": 2000000, + "default_max_tokens": 4096, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": true @@ -1893,26 +1880,26 @@ "supports_attachments": false }, { - "id": "openai/gpt-3.5-turbo", - "name": "OpenAI: GPT-3.5 Turbo", - "cost_per_1m_in": 0.5, - "cost_per_1m_out": 1.5, + "id": "openai/gpt-4", + "name": "OpenAI: GPT-4", + "cost_per_1m_in": 30, + "cost_per_1m_out": 60, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 16385, + "context_window": 8191, "default_max_tokens": 2048, "can_reason": false, "has_reasoning_efforts": false, "supports_attachments": false }, { - "id": "openai/gpt-4", - "name": "OpenAI: GPT-4", - "cost_per_1m_in": 30, - "cost_per_1m_out": 60, + "id": "openai/gpt-3.5-turbo", + "name": "OpenAI: GPT-3.5 Turbo", + "cost_per_1m_in": 0.5, + "cost_per_1m_out": 1.5, "cost_per_1m_in_cached": 0, "cost_per_1m_out_cached": 0, - "context_window": 8191, + "context_window": 16385, "default_max_tokens": 2048, "can_reason": false, "has_reasoning_efforts": false,