From efdccd88111248ea5091eb6706946ec77b9c4d2e Mon Sep 17 00:00:00 2001
From: "berriai-litellm-provider-info-sync[bot]"
 <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
Date: Wed, 30 Sep 2026 09:08:16 -0700
Subject: [PATCH] chore(cost-map): add fireworks priority prices for ember-1,
 nemotron and glm 5.3 us rows (#43811)

Price-Sync: litellm-providers

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 27 +++++++++++++++++++
 model_prices_and_context_window.json          | 27 +++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 677c45d6d57..e7eff5230dc 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -61352,13 +61352,16 @@
     },
     "fireworks_ai/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_priority": 2.5e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61368,13 +61371,16 @@
     },
     "fireworks_ai/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
+        "output_cost_per_token_priority": 3e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61404,13 +61410,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_priority": 2.5e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61420,13 +61429,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
+        "output_cost_per_token_priority": 3e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64336,13 +64348,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-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,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64371,13 +64386,16 @@
     },
     "fireworks_ai/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-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,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64461,12 +64479,15 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -64492,12 +64513,15 @@
     },
     "fireworks_ai/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -77493,11 +77517,14 @@
     },
     "fireworks_ai/accounts/fireworks/models/ember-1": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 677c45d6d57..e7eff5230dc 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -61352,13 +61352,16 @@
     },
     "fireworks_ai/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_priority": 2.5e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61368,13 +61371,16 @@
     },
     "fireworks_ai/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
+        "output_cost_per_token_priority": 3e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61404,13 +61410,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": {
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_priority": 1.25e-08,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_priority": 6.25e-08,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
+        "output_cost_per_token_priority": 2.5e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -61420,13 +61429,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": {
         "cache_read_input_token_cost": 1.2e-07,
+        "cache_read_input_token_cost_priority": 1.5e-07,
         "input_cost_per_token": 6e-07,
+        "input_cost_per_token_priority": 7.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
+        "output_cost_per_token_priority": 3e-06,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64336,13 +64348,16 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-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,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64371,13 +64386,16 @@
     },
     "fireworks_ai/glm-5p3-us": {
         "cache_read_input_token_cost": 3.9e-07,
+        "cache_read_input_token_cost_priority": 4.875e-07,
         "input_cost_per_token": 2.1e-06,
+        "input_cost_per_token_priority": 2.625e-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,
+        "output_cost_per_token_priority": 8.25e-06,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
@@ -64461,12 +64479,15 @@
     },
     "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -64492,12 +64513,15 @@
     },
     "fireworks_ai/glm-5p3-flash-us": {
         "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_priority": 5.625e-08,
         "input_cost_per_token": 2.25e-07,
+        "input_cost_per_token_priority": 2.8125e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "output_cost_per_token_priority": 9.375e-07,
         "source": "https://docs.fireworks.ai/serverless/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
@@ -77493,11 +77517,14 @@
     },
     "fireworks_ai/accounts/fireworks/models/ember-1": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,