From eedf4ef4e0a969aa58f51a7f45da7743676a1131 Mon Sep 17 00:00:00 2001 From: solomonic Date: Sat, 20 Jun 2026 00:15:06 +0700 Subject: [PATCH] fix(pricing): correct xai/grok-4.20 token costs to match cited xAI docs The four xai/grok-4.20-* entries were priced at $2.00/$6.00 per 1M input/output tokens, but the source cited on these entries (https://docs.x.ai/docs/models) lists every grok-4.20 variant at $1.25 input / $2.50 output, the same tier as grok-4.3 (already 1.25e-06 / 2.5e-06 here). Their cache_read_input_token_cost (2e-07) already matches that tier, and OpenRouter (x-ai/grok-4.20) also lists $1.25 / $2.50. Sets input 2e-06 -> 1.25e-06 and output 6e-06 -> 2.5e-06 for: - xai/grok-4.20-0309-reasoning - xai/grok-4.20-beta-0309-reasoning - xai/grok-4.20-beta-0309-non-reasoning - xai/grok-4.20-multi-agent-beta-0309 in both the root map and the litellm/ backup. cache_read left unchanged. Co-Authored-By: Claude Opus 4.8 (1M context) --- .../model_prices_and_context_window_backup.json | 16 ++++++++-------- model_prices_and_context_window.json | 16 ++++++++-------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7a5f8b9e1e3..ac6707895f6 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -37314,13 +37314,13 @@ }, "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, "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, @@ -37331,13 +37331,13 @@ }, "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, "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, @@ -37348,13 +37348,13 @@ }, "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, "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, @@ -37364,13 +37364,13 @@ }, "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, "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, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 47b7190185e..22613f5c58e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -37352,13 +37352,13 @@ }, "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, "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, @@ -37369,13 +37369,13 @@ }, "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, "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, @@ -37386,13 +37386,13 @@ }, "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, "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, @@ -37402,13 +37402,13 @@ }, "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, "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,