ci/cd run again

This commit is contained in:
Ishaan Jaffer 2025-10-04 08:51:21 -07:00
parent ad2270fe13
commit 67b0c874a3
2 changed files with 309 additions and 260 deletions

View file

@ -367,7 +367,7 @@ disable_add_prefix_to_prompt: bool = (
disable_copilot_system_to_assistant: bool = False # If false (default), converts all 'system' role messages to 'assistant' for GitHub Copilot compatibility. Set to true to disable this behavior.
public_model_groups: Optional[List[str]] = None
public_model_groups_links: Dict[str, str] = {}
#### REQUEST PRIORITIZATION ######
#### REQUEST PRIORITIZATION #######
priority_reservation: Optional[Dict[str, float]] = None
priority_reservation_settings: "PriorityReservationSettings" = (
PriorityReservationSettings()

View file

@ -6693,629 +6693,678 @@
]
},
"deepinfra/Gryphe/MythoMax-L2-13b": {
"input_cost_per_token": 7.2e-08,
"litellm_provider": "deepinfra",
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"max_tokens": 4096,
"input_cost_per_token": 8e-08,
"output_cost_per_token": 9e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 7.2e-08,
"supports_tool_choice": true
},
"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": {
"input_cost_per_token": 7e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 1e-06,
"output_cost_per_token": 1e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 8e-07,
"supports_tool_choice": true
},
"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": {
"input_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 3e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"supports_tool_choice": false
},
"deepinfra/Qwen/QwQ-32B": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen2.5-72B-Instruct": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "deepinfra",
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"input_cost_per_token": 1.2e-07,
"output_cost_per_token": 3.9e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen2.5-7B-Instruct": {
"input_cost_per_token": 4e-08,
"litellm_provider": "deepinfra",
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"input_cost_per_token": 4e-08,
"output_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": {
"input_cost_per_token": 2e-07,
"litellm_provider": "deepinfra",
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"input_cost_per_token": 2e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-14B": {
"input_cost_per_token": 6e-08,
"litellm_provider": "deepinfra",
"max_tokens": 40960,
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"max_tokens": 40960,
"mode": "chat",
"input_cost_per_token": 6e-08,
"output_cost_per_token": 2.4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-235B-A22B": {
"input_cost_per_token": 1.3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 40960,
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"max_tokens": 40960,
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 5.4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": {
"input_cost_per_token": 1.3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"input_cost_per_token": 9e-08,
"output_cost_per_token": 6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"input_cost_per_token": 1.3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 2.9e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-30B-A3B": {
"input_cost_per_token": 8e-08,
"litellm_provider": "deepinfra",
"max_tokens": 40960,
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"max_tokens": 40960,
"mode": "chat",
"input_cost_per_token": 8e-08,
"output_cost_per_token": 2.9e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-32B": {
"input_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 40960,
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"max_tokens": 40960,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 3e-07,
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": {
"input_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"input_cost_per_token": 4e-07,
"output_cost_per_token": 1.6e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": {
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"input_cost_per_token": 2.9e-07,
"output_cost_per_token": 1.2e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 1.4e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 1.4e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": {
"input_cost_per_token": 2e-08,
"litellm_provider": "deepinfra",
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"input_cost_per_token": 4e-08,
"output_cost_per_token": 5e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": {
"input_cost_per_token": 6.5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 6.5e-07,
"output_cost_per_token": 7.5e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": {
"input_cost_per_token": 6.5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 6.5e-07,
"output_cost_per_token": 7.5e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/allenai/olmOCR-7B-0725-FP8": {
"input_cost_per_token": 2.7e-07,
"litellm_provider": "deepinfra",
"max_tokens": 16384,
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/anthropic/claude-3-7-sonnet-latest": {
"cache_read_input_token_cost": 3.3e-07,
"input_cost_per_token": 3.3e-06,
"litellm_provider": "deepinfra",
"max_tokens": 200000,
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"input_cost_per_token": 3.3e-06,
"output_cost_per_token": 1.65e-05,
"cache_read_input_token_cost": 3.3e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/anthropic/claude-4-opus": {
"input_cost_per_token": 1.65e-05,
"litellm_provider": "deepinfra",
"max_tokens": 200000,
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"input_cost_per_token": 1.65e-05,
"output_cost_per_token": 8.25e-05,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/anthropic/claude-4-sonnet": {
"input_cost_per_token": 3.3e-06,
"litellm_provider": "deepinfra",
"max_tokens": 200000,
"max_input_tokens": 200000,
"max_output_tokens": 200000,
"max_tokens": 200000,
"mode": "chat",
"input_cost_per_token": 3.3e-06,
"output_cost_per_token": 1.65e-05,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-R1": {
"input_cost_per_token": 7e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 7e-07,
"output_cost_per_token": 2.4e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-R1-0528": {
"cache_read_input_token_cost": 4e-07,
"input_cost_per_token": 5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 5e-07,
"output_cost_per_token": 2.15e-06,
"cache_read_input_token_cost": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": {
"input_cost_per_token": 1e-06,
"litellm_provider": "deepinfra",
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
"input_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 2e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 4e-07,
"supports_tool_choice": false
},
"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
"input_cost_per_token": 7.5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 2.7e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1.5e-07,
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-R1-Turbo": {
"input_cost_per_token": 1e-06,
"litellm_provider": "deepinfra",
"max_tokens": 40960,
"max_input_tokens": 40960,
"max_output_tokens": 40960,
"max_tokens": 40960,
"mode": "chat",
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-V3": {
"input_cost_per_token": 3.8e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 3.8e-07,
"output_cost_per_token": 8.9e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-V3-0324": {
"cache_read_input_token_cost": 2.24e-07,
"input_cost_per_token": 2.8e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 8.8e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-V3.1": {
"cache_read_input_token_cost": 2.16e-07,
"input_cost_per_token": 2.7e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1e-06,
"supports_reasoning": true,
"cache_read_input_token_cost": 2.16e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": {
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1e-06,
"cache_read_input_token_cost": 2.16e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/google/gemini-2.0-flash-001": {
"input_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"input_cost_per_token": 1e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/google/gemini-2.5-flash": {
"input_cost_per_token": 2.1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 2.5e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1.75e-06,
"supports_tool_choice": true
},
"deepinfra/google/gemini-2.5-pro": {
"input_cost_per_token": 8.75e-07,
"litellm_provider": "deepinfra",
"max_tokens": 1000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 7e-06,
"supports_tool_choice": true
},
"deepinfra/google/gemma-3-12b-it": {
"input_cost_per_token": 5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 5e-08,
"output_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/google/gemma-3-27b-it": {
"input_cost_per_token": 9e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 9e-08,
"output_cost_per_token": 1.6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1.7e-07,
"supports_tool_choice": true
},
"deepinfra/google/gemma-3-4b-it": {
"input_cost_per_token": 4e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 4e-08,
"output_cost_per_token": 8e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": {
"input_cost_per_token": 4.9e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 4.9e-08,
"output_cost_per_token": 4.9e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/meta-llama/Llama-3.2-3B-Instruct": {
"input_cost_per_token": 1.2e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 2e-08,
"output_cost_per_token": 2e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 2.4e-08,
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-3.3-70B-Instruct": {
"input_cost_per_token": 2.3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 2.3e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": {
"input_cost_per_token": 3.8e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 1.3e-07,
"output_cost_per_token": 3.9e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1.2e-07,
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 1048576,
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"max_tokens": 1048576,
"mode": "chat",
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"input_cost_per_token": 8e-08,
"litellm_provider": "deepinfra",
"max_tokens": 327680,
"max_input_tokens": 327680,
"max_output_tokens": 327680,
"max_tokens": 327680,
"mode": "chat",
"input_cost_per_token": 8e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Llama-Guard-3-8B": {
"input_cost_per_token": 5.5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 5.5e-08,
"output_cost_per_token": 5.5e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/meta-llama/Llama-Guard-4-12B": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "deepinfra",
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"max_tokens": 163840,
"mode": "chat",
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 1.8e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": {
"input_cost_per_token": 3e-08,
"litellm_provider": "deepinfra",
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"input_cost_per_token": 3e-08,
"output_cost_per_token": 6e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": {
"input_cost_per_token": 2.3e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 4e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"input_cost_per_token": 1e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 1e-07,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": {
"input_cost_per_token": 3e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 3e-08,
"output_cost_per_token": 5e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
"input_cost_per_token": 1.5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 2e-08,
"output_cost_per_token": 3e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 2e-08,
"supports_tool_choice": true
},
"deepinfra/microsoft/WizardLM-2-8x22B": {
"input_cost_per_token": 4.8e-07,
"litellm_provider": "deepinfra",
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"input_cost_per_token": 4.8e-07,
"output_cost_per_token": 4.8e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
},
"deepinfra/microsoft/phi-4": {
"input_cost_per_token": 7e-08,
"litellm_provider": "deepinfra",
"max_tokens": 16384,
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"input_cost_per_token": 7e-08,
"output_cost_per_token": 1.4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/mistralai/Mistral-Nemo-Instruct-2407": {
"input_cost_per_token": 2e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 2e-08,
"output_cost_per_token": 4e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": {
"input_cost_per_token": 5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"input_cost_per_token": 5e-08,
"output_cost_per_token": 8e-08,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": {
"input_cost_per_token": 5e-08,
"litellm_provider": "deepinfra",
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"input_cost_per_token": 7.5e-08,
"output_cost_per_token": 2e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1e-07,
"supports_tool_choice": true
},
"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": {
"input_cost_per_token": 8e-08,
"litellm_provider": "deepinfra",
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 32768,
"input_cost_per_token": 4e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 2.4e-07,
"supports_tool_choice": true
},
"deepinfra/moonshotai/Kimi-K2-Instruct": {
"input_cost_per_token": 5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 5e-07,
"output_cost_per_token": 2e-06,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/moonshotai/Kimi-K2-Instruct-0905": {
"max_tokens": 262144,
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"input_cost_per_token": 5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 6e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 4e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 4e-08,
"output_cost_per_token": 1.6e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 3e-07,
"supports_tool_choice": true
},
"deepinfra/openai/gpt-oss-120b": {
"input_cost_per_token": 9e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4.5e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": true
},
"deepinfra/openai/gpt-oss-20b": {
"input_cost_per_token": 4e-08,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"input_cost_per_token": 4e-08,
"output_cost_per_token": 1.5e-07,
"litellm_provider": "deepinfra",
"mode": "chat",
"output_cost_per_token": 1.6e-07,
"supports_tool_choice": true
},
"deepinfra/zai-org/GLM-4.5": {
"input_cost_per_token": 5.5e-07,
"litellm_provider": "deepinfra",
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-06,
"supports_tool_choice": true
},
"deepinfra/zai-org/GLM-4.5-Air": {
"input_cost_per_token": 2e-07,
"input_cost_per_token": 4e-07,
"output_cost_per_token": 1.6e-06,
"litellm_provider": "deepinfra",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.1e-06,
"supports_tool_choice": true
},
"deepseek/deepseek-chat": {