scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 156

Merge pull request #40812 from BerriAI/litellm_fireworks_deepseek_v4p1_flash

Browse source 
feat(model_prices): add DeepSeek V4.1 Flash on Fireworks
This commit is contained in:
Mateo Wang 2026-09-11 18:43:00 -07:00 • committed by GitHub
commit eed11ba59b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 93 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
litellm/model_prices_and_context_window_backup.json
View file

@ -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,

34
model_prices_and_context_window.json
View file

@ -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,

27
tests/test_litellm/test_fireworks_serverless_model_costs.py
View file

@ -14,6 +14,8 @@ import os
import pytest
from litellm import completion_cost
from litellm.types.utils import Choices, Message, ModelResponse, Usage
from litellm.utils import get_model_info
@ -56,17 +58,38 @@ def test_bare_fireworks_ids_resolve_through_prefixed_entries():
assert info["max_output_tokens"] == expected["max_output_tokens"]
def test_deepseek_v4p1_flash_twin_costs(local_model_cost_map):
for model in (
"fireworks_ai/deepseek-v4p1-flash",
"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash",
):
response = ModelResponse(
model=model,
choices=[Choices(index=0, message=Message(role="assistant", content="ok"))],
usage=Usage(prompt_tokens=1000, completion_tokens=1000, total_tokens=2000),
)
cost = completion_cost(completion_response=response, model=model)
assert cost == pytest.approx(8.8e-04)
TWIN_PINNED_PRICES = {
"deepseek-v4-flash-0731": {
"input_cost_per_token": 2.2e-07,
"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}",