From 6cffb31e5cda6805a6c62ae900a90852ecf308da Mon Sep 17 00:00:00 2001
From: mateo <mateo@berri.ai>
Date: Sat, 12 Sep 2026 00:36:20 +0000
Subject: [PATCH] feat(model_prices): add DeepSeek V4.1 Flash on Fireworks

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 34 +++++++++++++++++++
 model_prices_and_context_window.json          | 34 +++++++++++++++++++
 .../test_fireworks_serverless_model_costs.py  | 11 ++++--
 3 files changed, 77 insertions(+), 2 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index aadd9bd3028..7fa09951eae 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -57695,6 +57695,23 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 2.2e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 2.2e-07,
@@ -57745,6 +57762,23 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/deepseek-v4p1-flash": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 2.2e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "fireworks_ai/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 2.2e-07,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index aadd9bd3028..7fa09951eae 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -57695,6 +57695,23 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 2.2e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 2.2e-07,
@@ -57745,6 +57762,23 @@
         "supports_tool_choice": true,
         "supports_vision": false
     },
+    "fireworks_ai/deepseek-v4p1-flash": {
+        "cache_read_input_token_cost": 7e-09,
+        "input_cost_per_token": 2.2e-07,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 393216,
+        "max_tokens": 393216,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-07,
+        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "fireworks_ai/deepseek-v4-flash-vision-exp": {
         "cache_read_input_token_cost": 7e-09,
         "input_cost_per_token": 2.2e-07,
diff --git a/tests/test_litellm/test_fireworks_serverless_model_costs.py b/tests/test_litellm/test_fireworks_serverless_model_costs.py
index 701938f5677..b8d36b996df 100644
--- a/tests/test_litellm/test_fireworks_serverless_model_costs.py
+++ b/tests/test_litellm/test_fireworks_serverless_model_costs.py
@@ -62,11 +62,18 @@ TWIN_PINNED_PRICES = {
         "cache_read_input_token_cost": 7e-09,
         "output_cost_per_token": 6.6e-07,
     },
+    "deepseek-v4p1-flash": {
+        "input_cost_per_token": 2.2e-07,
+        "cache_read_input_token_cost": 7e-09,
+        "output_cost_per_token": 6.6e-07,
+        "supports_vision": True,
+        "max_output_tokens": 393216,
+    },
 }
 
 
-def test_deepseek_v4_flash_0731_twins_pin_published_pricing(model_data):
-    """Both 0731 entries carry the price published at docs.fireworks.ai/serverless/pricing."""
+def test_deepseek_v4_flash_twins_pin_published_pricing(model_data):
+    """Both entries of each Flash twin pair carry the price published at docs.fireworks.ai/serverless/pricing."""
     for bare_suffix, expected in TWIN_PINNED_PRICES.items():
         for key in (
             f"fireworks_ai/{bare_suffix}",