scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 124

added qwen3, deepseek r1 0528 throughput, glm 4.5 and gpt oss models

Browse source
This commit is contained in:
Tasmay Pankaj Tibrewal 2025-08-15 04:33:49 +05:30 • committed by GitHub
parent aaf9c38a10
commit 4b51e5787c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 88 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

88
model_prices_and_context_window.json
View file

@ -14649,6 +14649,50 @@
"mode": "chat",
"supports_tool_choice": true
},
"deepseek-ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 6e-06,
"max_input_tokens": 262000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"supports_tool_choice": false
"source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8"
},
"deepseek-ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 2e-06,
"max_input_tokens": 256000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"supports_tool_choice": false
"source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct"
},
"deepseek-ai/Qwen/Qwen3-235B-A22B-Thinking-2507": {
"input_cost_per_token": 6.5e-07,
"output_cost_per_token": 3e-06,
"max_input_tokens": 256000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"supports_tool_choice": false
"source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507"
},
"deepseek-ai/Qwen/Qwen3-235B-A22B-fp8-tput": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 6e-07,
"max_input_tokens": 40000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"supports_tool_choice": false
"source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput"
},
"together_ai/deepseek-ai/DeepSeek-V3": {
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1.25e-06,
@ -14673,6 +14717,17 @@
"mode": "chat",
"supports_tool_choice": true
},
"deepseek-ai/DeepSeek-R1-0528-tput": {
"input_cost_per_token": 5.5e-07,
"output_cost_per_token": 2.19e-06,
"max_input_tokens": 128000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"supports_tool_choice": false
"source": "https://www.together.ai/models/deepseek-r1-0528-throughput"
},
"together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
"litellm_provider": "together_ai",
"supports_function_calling": true,
@ -14690,6 +14745,39 @@
"mode": "chat",
"source": "https://www.together.ai/models/kimi-k2-instruct"
},
"together_ai/openai/gpt-oss-120b": {
"input_cost_per_token": 1.5e-07,
"output_cost_per_token": 6e-07,
"max_input_tokens": 128000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_tool_choice": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"source": "https://www.together.ai/models/gpt-oss-120b"
},
"together_ai/OpenAI/gpt-oss-20B": {
"input_cost_per_token": 5e-08,
"output_cost_per_token": 2e-07,
"max_input_tokens": 128000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_tool_choice": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"source": "https://www.together.ai/models/gpt-oss-20b"
},
"together_ai/zai-org/GLM-4.5-Air-FP8": {
"input_cost_per_token": 2e-07,
"output_cost_per_token": 1.1e-06,
"max_input_tokens": 128000,
"litellm_provider": "together_ai",
"supports_function_calling": false,
"supports_tool_choice": false,
"supports_parallel_function_calling": false,
"mode": "chat",
"source": "https://www.together.ai/models/glm-4-5-air"
},
"ollama/codegemma": {
"max_tokens": 8192,
"max_input_tokens": 8192,