diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c9658c6cc4..90a6430021 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -19775,6 +19775,848 @@ "supports_system_messages": true, "supports_tool_choice": false }, + "vercel_ai_gateway/alibaba/qwen3-coder": { + "max_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "max_output_tokens": 66536, + "max_input_tokens": 262144, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "max_tokens": 0, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/gemini-2.5-pro": { + "max_tokens": 1048576, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 65536, + "max_input_tokens": 1048576, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/deepseek/deepseek-v3": { + "max_tokens": 128000, + "input_cost_per_token": 9e-07, + "output_cost_per_token": 9e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/amazon/nova-lite": { + "max_tokens": 300000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "max_output_tokens": 8192, + "max_input_tokens": 300000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-4-scout": { + "max_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "max_output_tokens": 8192, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.2-1b": { + "max_tokens": 128000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/mistral-small": { + "max_tokens": 32000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "max_output_tokens": 4000, + "max_input_tokens": 32000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/gemini-2.5-flash": { + "max_tokens": 1000000, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "max_output_tokens": 65536, + "max_input_tokens": 1000000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/inception/mercury-coder-small": { + "max_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1e-06, + "max_output_tokens": 16384, + "max_input_tokens": 32000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/text-embedding-3-small": { + "max_tokens": 0, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "max_tokens": 32768, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 32768, + "max_input_tokens": 32768, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/xai/grok-2": { + "max_tokens": 131072, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 4000, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "max_tokens": 131072, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 9.9e-07, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.1-70b": { + "max_tokens": 128000, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/xai/grok-3": { + "max_tokens": 131072, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/alibaba/qwen-3-235b": { + "max_tokens": 40960, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "max_output_tokens": 16384, + "max_input_tokens": 40960, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/xai/grok-3-fast": { + "max_tokens": 131072, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "max_tokens": 128000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 32768, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/o4-mini": { + "max_tokens": 200000, + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "max_output_tokens": 100000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/magistral-medium": { + "max_tokens": 128000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 5e-06, + "max_output_tokens": 64000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "max_tokens": 0, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "max_tokens": 40960, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "max_output_tokens": 16384, + "max_input_tokens": 40960, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/zai/glm-4.5-air": { + "max_tokens": 128000, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "max_output_tokens": 96000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "max_tokens": 128000, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "max_output_tokens": 4096, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/mistral-large": { + "max_tokens": 32000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "max_output_tokens": 4000, + "max_input_tokens": 32000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "max_tokens": 200000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 8000, + "max_input_tokens": 200000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.2-90b": { + "max_tokens": 128000, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3-8b": { + "max_tokens": 8192, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "max_output_tokens": 8192, + "max_input_tokens": 8192, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/text-embedding-005": { + "max_tokens": 0, + "input_cost_per_token": 2.5e-08, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/mistral/pixtral-large": { + "max_tokens": 128000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "max_output_tokens": 4000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "max_tokens": 200000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 8192, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/amazon/nova-micro": { + "max_tokens": 128000, + "input_cost_per_token": 3.5e-08, + "output_cost_per_token": 1.4e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/cohere/command-r": { + "max_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "max_output_tokens": 4096, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/morph/morph-v3-large": { + "max_tokens": 32768, + "input_cost_per_token": 9e-07, + "output_cost_per_token": 1.9e-06, + "max_output_tokens": 16384, + "max_input_tokens": 32768, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { + "max_tokens": 65536, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 1.2e-06, + "max_output_tokens": 2048, + "max_input_tokens": 65536, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/xai/grok-4": { + "max_tokens": 256000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 256000, + "max_input_tokens": 256000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "max_tokens": 131000, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "max_output_tokens": 131072, + "max_input_tokens": 131000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-3-opus": { + "max_tokens": 200000, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 7.5e-05, + "max_output_tokens": 4096, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/zai/glm-4.5": { + "max_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.2e-06, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4o": { + "max_tokens": 128000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 16384, + "max_input_tokens": 128000, + "cache_read_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/o3-mini": { + "max_tokens": 200000, + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "max_output_tokens": 100000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 5.5e-07, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/ministral-8b": { + "max_tokens": 128000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, + "max_output_tokens": 4000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/o3": { + "max_tokens": 200000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "max_output_tokens": 100000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/vercel/v0-1.0-md": { + "max_tokens": 128000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 32000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/text-multilingual-embedding-002": { + "max_tokens": 0, + "input_cost_per_token": 2.5e-08, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/amazon/nova-pro": { + "max_tokens": 300000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 3.2e-06, + "max_output_tokens": 8192, + "max_input_tokens": 300000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/morph/morph-v3-fast": { + "max_tokens": 32768, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 1.2e-06, + "max_output_tokens": 16384, + "max_input_tokens": 32768, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "max_tokens": 16385, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "max_output_tokens": 4096, + "max_input_tokens": 16385, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/codestral": { + "max_tokens": 256000, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "max_output_tokens": 4000, + "max_input_tokens": 256000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "max_tokens": 128000, + "input_cost_per_token": 1.6e-07, + "output_cost_per_token": 1.6e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3-70b": { + "max_tokens": 8192, + "input_cost_per_token": 5.9e-07, + "output_cost_per_token": 7.9e-07, + "max_output_tokens": 8192, + "max_input_tokens": 8192, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "max_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 4e-06, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/text-embedding-3-large": { + "max_tokens": 0, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "max_tokens": 1048576, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "max_output_tokens": 8192, + "max_input_tokens": 1048576, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/ministral-3b": { + "max_tokens": 128000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 4e-08, + "max_output_tokens": 4000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "max_tokens": 127000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "max_output_tokens": 8000, + "max_input_tokens": 127000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/gemini-embedding-001": { + "max_tokens": 0, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "max_tokens": 200000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "max_output_tokens": 4096, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/o1": { + "max_tokens": 200000, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 6e-05, + "max_output_tokens": 100000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "max_tokens": 128000, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.19e-06, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/mistral-embed": { + "max_tokens": 0, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "max_tokens": 1047576, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "max_output_tokens": 32768, + "max_input_tokens": 1047576, + "cache_read_input_token_cost": 1e-07, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4o-mini": { + "max_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "max_output_tokens": 16384, + "max_input_tokens": 128000, + "cache_read_input_token_cost": 7.5e-08, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "max_tokens": 40960, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "max_output_tokens": 16384, + "max_input_tokens": 40960, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-4-opus": { + "max_tokens": 200000, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 7.5e-05, + "max_output_tokens": 32000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "max_tokens": 32768, + "input_cost_per_token": 7.9e-07, + "output_cost_per_token": 7.9e-07, + "max_output_tokens": 32768, + "max_input_tokens": 32768, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "max_tokens": 127000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "max_output_tokens": 8000, + "max_input_tokens": 127000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "max_tokens": 200000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "max_output_tokens": 8192, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 8e-08, + "cache_creation_input_token_cost": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/cohere/command-a": { + "max_tokens": 256000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 8000, + "max_input_tokens": 256000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/gemma-2-9b": { + "max_tokens": 8192, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "max_output_tokens": 8192, + "max_input_tokens": 8192, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.2-3b": { + "max_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "max_tokens": 1047576, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "max_output_tokens": 32768, + "max_input_tokens": 1047576, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "max_tokens": 200000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 64000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/perplexity/sonar": { + "max_tokens": 127000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1e-06, + "max_output_tokens": 8000, + "max_input_tokens": 127000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-4-maverick": { + "max_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "max_output_tokens": 8192, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/text-embedding-ada-002": { + "max_tokens": 0, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "embedding" + }, + "vercel_ai_gateway/xai/grok-3-mini": { + "max_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 5e-07, + "max_output_tokens": 131072, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/cohere/embed-v4.0": { + "max_tokens": 0, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 0.0, + "max_output_tokens": 0, + "max_input_tokens": 0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/meta/llama-3.3-70b": { + "max_tokens": 128000, + "input_cost_per_token": 7.2e-07, + "output_cost_per_token": 7.2e-07, + "max_output_tokens": 8192, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/cohere/command-r-plus": { + "max_tokens": 128000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "max_output_tokens": 4096, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "max_tokens": 8192, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, + "max_output_tokens": 4096, + "max_input_tokens": 8192, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/devstral-small": { + "max_tokens": 128000, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "max_output_tokens": 128000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "max_tokens": 200000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "max_output_tokens": 64000, + "max_input_tokens": 200000, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "max_tokens": 1048576, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "max_output_tokens": 8192, + "max_input_tokens": 1048576, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/pixtral-12b": { + "max_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "max_output_tokens": 4000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/mistral/magistral-small": { + "max_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "max_output_tokens": 64000, + "max_input_tokens": 128000, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/moonshotai/kimi-k2": { + "max_tokens": 131072, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.2e-06, + "max_output_tokens": 16384, + "max_input_tokens": 131072, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "max_tokens": 40960, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "max_output_tokens": 16384, + "max_input_tokens": 40960, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, + "vercel_ai_gateway/openai/gpt-4.1": { + "max_tokens": 1047576, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "max_output_tokens": 32768, + "max_input_tokens": 1047576, + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 0.0, + "litellm_provider": "vercel_ai_gateway", + "mode": "chat" + }, "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { "max_tokens": 512000, "max_input_tokens": 512000, @@ -20009,4 +20851,4 @@ "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" } } -} +} \ No newline at end of file diff --git a/tests/llm_translation/test_openrouter.py b/tests/llm_translation/test_openrouter.py new file mode 100644 index 0000000000..4c3cb1d6e4 --- /dev/null +++ b/tests/llm_translation/test_openrouter.py @@ -0,0 +1,18 @@ + +import os +import sys +import pytest +sys.path.insert( + 0, os.path.abspath("../..") +) # Adds the parent directory to the system paths +import litellm + +def test_completion_openrouter_reasoning_content(): + litellm._turn_on_debug() + resp = litellm.completion( + model="openrouter/anthropic/claude-3.7-sonnet", + messages=[{"role": "user", "content": "Hello world"}], + reasoning={"effort": "high"}, + ) + print(resp) + assert resp.choices[0].message.reasoning_content is not None diff --git a/tests/local_testing/test_completion.py b/tests/local_testing/test_completion.py index 535f5cb00a..b65705e51b 100644 --- a/tests/local_testing/test_completion.py +++ b/tests/local_testing/test_completion.py @@ -4592,14 +4592,3 @@ def test_completion_gpt_4o_empty_str(): messages=[{"role": "user", "content": ""}], ) assert resp.choices[0].message.content is not None - - -def test_completion_openrouter_reasoning_content(): - litellm._turn_on_debug() - resp = litellm.completion( - model="openrouter/anthropic/claude-3.7-sonnet", - messages=[{"role": "user", "content": "Hello world"}], - reasoning={"effort": "high"}, - ) - print(resp) - assert resp.choices[0].message.reasoning_content is not None