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 123

feat(models): add OpenRouter and Cerebras GPT-OSS models (20b, 120b) with pricing and context windows; update backup; refs #13428 (#13442)

Browse source
This commit is contained in:
Cole McIntosh 2025-08-08 23:47:51 -06:00 • committed by GitHub
parent 035e5497e0
commit d874bec480
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 120 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
litellm/model_prices_and_context_window_backup.json
View file

@ -6074,6 +6074,36 @@
"supports_tool_choice": true,
"source": "https://inference-docs.cerebras.ai/support/pricing"
},
"cerebras/openai/gpt-oss-20b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "cerebras",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://inference-docs.cerebras.ai/support/pricing"
},
"cerebras/openai/gpt-oss-120b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 6.9e-07,
"litellm_provider": "cerebras",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras"
},
"friendliai/meta-llama-3.1-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -11658,6 +11688,36 @@
"mode": "chat",
"supports_tool_choice": true
},
"openrouter/openai/gpt-oss-20b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 8e-07,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://openrouter.ai/openai/gpt-oss-20b"
},
"openrouter/openai/gpt-oss-120b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 8e-07,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://openrouter.ai/openai/gpt-oss-120b"
},
"openrouter/anthropic/claude-instant-v1": {
"max_tokens": 100000,
"max_output_tokens": 8191,

60
model_prices_and_context_window.json
View file

@ -6074,6 +6074,36 @@
"supports_tool_choice": true,
"source": "https://inference-docs.cerebras.ai/support/pricing"
},
"cerebras/openai/gpt-oss-20b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 3e-07,
"litellm_provider": "cerebras",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://inference-docs.cerebras.ai/support/pricing"
},
"cerebras/openai/gpt-oss-120b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 6.9e-07,
"litellm_provider": "cerebras",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras"
},
"friendliai/meta-llama-3.1-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -11658,6 +11688,36 @@
"mode": "chat",
"supports_tool_choice": true
},
"openrouter/openai/gpt-oss-20b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 8e-07,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://openrouter.ai/openai/gpt-oss-20b"
},
"openrouter/openai/gpt-oss-120b": {
"max_tokens": 32768,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"input_cost_per_token": 1.8e-07,
"output_cost_per_token": 8e-07,
"litellm_provider": "openrouter",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://openrouter.ai/openai/gpt-oss-120b"
},
"openrouter/anthropic/claude-instant-v1": {
"max_tokens": 100000,
"max_output_tokens": 8191,