Merge pull request #36664 from BerriAI/litellm_groq_model_registry_audit

fix(model_prices): sync the Groq registry with Groq's docs
This commit is contained in:
Mateo Wang 2026-08-12 19:37:39 -07:00 committed by GitHub
commit 6038dc6891
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 138 additions and 16 deletions

View file

@ -26120,11 +26120,12 @@
"supports_vision": true
},
"groq/llama-3.1-8b-instant": {
"deprecation_date": "2026-08-16",
"input_cost_per_token": 5e-08,
"litellm_provider": "groq",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 8e-08,
"supports_function_calling": true,
@ -26132,9 +26133,10 @@
"supports_tool_choice": true
},
"groq/llama-3.3-70b-versatile": {
"deprecation_date": "2026-08-16",
"input_cost_per_token": 5.9e-07,
"litellm_provider": "groq",
"max_input_tokens": 128000,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
@ -26155,7 +26157,28 @@
"supports_response_schema": false,
"supports_tool_choice": true
},
"groq/meta-llama/llama-prompt-guard-2-22m": {
"input_cost_per_token": 3e-08,
"litellm_provider": "groq",
"max_input_tokens": 512,
"max_output_tokens": 512,
"max_tokens": 512,
"mode": "chat",
"output_cost_per_token": 3e-08,
"source": "https://console.groq.com/docs/models"
},
"groq/meta-llama/llama-prompt-guard-2-86m": {
"input_cost_per_token": 4e-08,
"litellm_provider": "groq",
"max_input_tokens": 512,
"max_output_tokens": 512,
"max_tokens": 512,
"mode": "chat",
"output_cost_per_token": 4e-08,
"source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m"
},
"groq/meta-llama/llama-guard-4-12b": {
"deprecation_date": "2026-03-05",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 8192,
@ -26165,6 +26188,7 @@
"output_cost_per_token": 2e-07
},
"groq/meta-llama/llama-4-maverick-17b-128e-instruct": {
"deprecation_date": "2026-03-09",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
@ -26178,6 +26202,7 @@
"supports_vision": true
},
"groq/meta-llama/llama-4-scout-17b-16e-instruct": {
"deprecation_date": "2026-07-17",
"input_cost_per_token": 1.1e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
@ -26191,6 +26216,7 @@
"supports_vision": true
},
"groq/moonshotai/kimi-k2-instruct-0905": {
"deprecation_date": "2026-04-15",
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 5e-07,
@ -26208,8 +26234,8 @@
"input_cost_per_token": 1.5e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32766,
"max_tokens": 32766,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 6e-07,
"search_context_cost_per_query": {
@ -26229,8 +26255,8 @@
"input_cost_per_token": 7.5e-08,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3e-07,
"search_context_cost_per_query": {
@ -26265,7 +26291,26 @@
"supports_tool_choice": true,
"supports_web_search": true
},
"groq/canopylabs/orpheus-v1-english": {
"input_cost_per_character": 2.2e-05,
"litellm_provider": "groq",
"max_input_tokens": 4000,
"max_output_tokens": 50000,
"max_tokens": 50000,
"mode": "audio_speech",
"source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english"
},
"groq/canopylabs/orpheus-arabic-saudi": {
"input_cost_per_character": 4e-05,
"litellm_provider": "groq",
"max_input_tokens": 4000,
"max_output_tokens": 50000,
"max_tokens": 50000,
"mode": "audio_speech",
"source": "https://console.groq.com/docs/models"
},
"groq/playai-tts": {
"deprecation_date": "2025-12-31",
"input_cost_per_character": 5e-05,
"litellm_provider": "groq",
"max_input_tokens": 10000,
@ -26273,7 +26318,23 @@
"max_tokens": 10000,
"mode": "audio_speech"
},
"groq/qwen/qwen3.6-27b": {
"input_cost_per_token": 6e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_tool_choice": true,
"supports_vision": true
},
"groq/qwen/qwen3-32b": {
"deprecation_date": "2026-07-17",
"input_cost_per_token": 2.9e-07,
"litellm_provider": "groq",
"max_input_tokens": 131000,

View file

@ -26120,11 +26120,12 @@
"supports_vision": true
},
"groq/llama-3.1-8b-instant": {
"deprecation_date": "2026-08-16",
"input_cost_per_token": 5e-08,
"litellm_provider": "groq",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 8e-08,
"supports_function_calling": true,
@ -26132,9 +26133,10 @@
"supports_tool_choice": true
},
"groq/llama-3.3-70b-versatile": {
"deprecation_date": "2026-08-16",
"input_cost_per_token": 5.9e-07,
"litellm_provider": "groq",
"max_input_tokens": 128000,
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
@ -26155,7 +26157,28 @@
"supports_response_schema": false,
"supports_tool_choice": true
},
"groq/meta-llama/llama-prompt-guard-2-22m": {
"input_cost_per_token": 3e-08,
"litellm_provider": "groq",
"max_input_tokens": 512,
"max_output_tokens": 512,
"max_tokens": 512,
"mode": "chat",
"output_cost_per_token": 3e-08,
"source": "https://console.groq.com/docs/models"
},
"groq/meta-llama/llama-prompt-guard-2-86m": {
"input_cost_per_token": 4e-08,
"litellm_provider": "groq",
"max_input_tokens": 512,
"max_output_tokens": 512,
"max_tokens": 512,
"mode": "chat",
"output_cost_per_token": 4e-08,
"source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m"
},
"groq/meta-llama/llama-guard-4-12b": {
"deprecation_date": "2026-03-05",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 8192,
@ -26165,6 +26188,7 @@
"output_cost_per_token": 2e-07
},
"groq/meta-llama/llama-4-maverick-17b-128e-instruct": {
"deprecation_date": "2026-03-09",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
@ -26178,6 +26202,7 @@
"supports_vision": true
},
"groq/meta-llama/llama-4-scout-17b-16e-instruct": {
"deprecation_date": "2026-07-17",
"input_cost_per_token": 1.1e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
@ -26191,6 +26216,7 @@
"supports_vision": true
},
"groq/moonshotai/kimi-k2-instruct-0905": {
"deprecation_date": "2026-04-15",
"input_cost_per_token": 1e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 5e-07,
@ -26208,8 +26234,8 @@
"input_cost_per_token": 1.5e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32766,
"max_tokens": 32766,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 6e-07,
"search_context_cost_per_query": {
@ -26229,8 +26255,8 @@
"input_cost_per_token": 7.5e-08,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 3e-07,
"search_context_cost_per_query": {
@ -26265,7 +26291,26 @@
"supports_tool_choice": true,
"supports_web_search": true
},
"groq/canopylabs/orpheus-v1-english": {
"input_cost_per_character": 2.2e-05,
"litellm_provider": "groq",
"max_input_tokens": 4000,
"max_output_tokens": 50000,
"max_tokens": 50000,
"mode": "audio_speech",
"source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english"
},
"groq/canopylabs/orpheus-arabic-saudi": {
"input_cost_per_character": 4e-05,
"litellm_provider": "groq",
"max_input_tokens": 4000,
"max_output_tokens": 50000,
"max_tokens": 50000,
"mode": "audio_speech",
"source": "https://console.groq.com/docs/models"
},
"groq/playai-tts": {
"deprecation_date": "2025-12-31",
"input_cost_per_character": 5e-05,
"litellm_provider": "groq",
"max_input_tokens": 10000,
@ -26273,7 +26318,23 @@
"max_tokens": 10000,
"mode": "audio_speech"
},
"groq/qwen/qwen3.6-27b": {
"input_cost_per_token": 6e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_tool_choice": true,
"supports_vision": true
},
"groq/qwen/qwen3-32b": {
"deprecation_date": "2026-07-17",
"input_cost_per_token": 2.9e-07,
"litellm_provider": "groq",
"max_input_tokens": 131000,