From cbe342171cb30e98bcfe6d555ba60489eff46b9d Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 24 Sep 2026 17:27:00 -0700 Subject: [PATCH] feat(cost-map): add fireworks glm-5p3 US-only rows and kimi-k3-us priority prices (#43092) Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 66 +++++++++++++++++++ model_prices_and_context_window.json | 66 +++++++++++++++++++ 2 files changed, 132 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f12c8563392..c58ea51db9f 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -60319,13 +60319,16 @@ }, "fireworks_ai/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", @@ -60527,13 +60530,16 @@ }, "fireworks_ai/accounts/fireworks/routers/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", @@ -63292,6 +63298,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, "cache_read_input_token_cost_priority": 3.25e-07, @@ -63311,6 +63333,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, @@ -63358,6 +63396,20 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, @@ -63375,6 +63427,20 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f12c8563392..c58ea51db9f 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -60319,13 +60319,16 @@ }, "fireworks_ai/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", @@ -60527,13 +60530,16 @@ }, "fireworks_ai/accounts/fireworks/routers/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", @@ -63292,6 +63298,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, "cache_read_input_token_cost_priority": 3.25e-07, @@ -63311,6 +63333,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, @@ -63358,6 +63396,20 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, @@ -63375,6 +63427,20 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "input_cost_per_token": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06,