scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 86

fix(pricing): correct grok-4.20 series rates and context window

Browse source 
The built-in grok-4.20 entries billed input at $2/M and output at $6/M
with a 2M context window. x.ai documents $1.25/M input, $2.50/M output,
$0.20/M cached input and a 1M context window for the non-reasoning,
reasoning and multi-agent variants, so every request was overbilled and
the advertised context window was double the real one

Corrects input_cost_per_token, output_cost_per_token, max_input_tokens,
max_output_tokens and max_tokens for the four xai/grok-4.20-* keys and
the two vertex_ai/xai/grok-4.20-* keys (which mirror x.ai pricing), in
both model_prices_and_context_window.json and the bundled backup. The
cached input rate was already correct and is left untouched

Sources:
https://docs.x.ai/developers/models/grok-4.20-0309-non-reasoning
https://docs.x.ai/developers/models/grok-4.20-0309-reasoning
https://docs.x.ai/developers/models/grok-4.20-multi-agent-0309
This commit is contained in:
Zero Clover 2026-06-13 14:49:08 +08:00
parent ec9353cb69
commit a17c8b8ef9
Failed to extract signature
2 changed files with 60 additions and 60 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

@ -35504,13 +35504,13 @@
},
"vertex_ai/xai/grok-4.20-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"supports_function_calling": true,
"supports_response_schema": true,
@ -35520,13 +35520,13 @@
},
"vertex_ai/xai/grok-4.20-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"supports_function_calling": true,
"supports_reasoning": true,
@ -36840,13 +36840,13 @@
},
"xai/grok-4.20-multi-agent-beta-0309": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -36857,13 +36857,13 @@
},
"xai/grok-4.20-beta-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -36874,13 +36874,13 @@
},
"xai/grok-4.20-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
@ -36890,13 +36890,13 @@
},
"xai/grok-4.20-beta-0309-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,

60
model_prices_and_context_window.json
View file

@ -35544,13 +35544,13 @@
},
"vertex_ai/xai/grok-4.20-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"supports_function_calling": true,
"supports_response_schema": true,
@ -35560,13 +35560,13 @@
},
"vertex_ai/xai/grok-4.20-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
"supports_function_calling": true,
"supports_reasoning": true,
@ -36870,13 +36870,13 @@
},
"xai/grok-4.20-multi-agent-beta-0309": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -36887,13 +36887,13 @@
},
"xai/grok-4.20-beta-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -36904,13 +36904,13 @@
},
"xai/grok-4.20-0309-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_reasoning": true,
@ -36920,13 +36920,13 @@
},
"xai/grok-4.20-beta-0309-non-reasoning": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "xai",
"max_input_tokens": 2000000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token": 2.5e-06,
"source": "https://docs.x.ai/docs/models",
"supports_function_calling": true,
"supports_prompt_caching": true,