scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Update fireworks ai pricing (#10425)

Browse source 
* build(model_prices_and_context_window.json): add fireworks ai new 0-4b pricing tier

* build(model_prices_and_context_window.json): add more fireworks ai models

* test: update testing

* test: testing updates

* test: update test

* test: update test
This commit is contained in:
Krish Dholakia 2025-04-29 20:58:05 -07:00 • committed by GitHub
parent 839878f4f5
commit d783190e04
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 150 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
litellm/constants.py
View file

@ -94,6 +94,7 @@ STREAM_SSE_DONE_STRING: str = "[DONE]"
DEFAULT_REPLICATE_GPU_PRICE_PER_SECOND = 0.001400 # price per second for a100 80GB
FIREWORKS_AI_56_B_MOE = 56
FIREWORKS_AI_176_B_MOE = 176
FIREWORKS_AI_4_B = 4
FIREWORKS_AI_16_B = 16
FIREWORKS_AI_80_B = 80

12
litellm/llms/fireworks_ai/cost_calculator.py
View file

@ -5,9 +5,9 @@ For calculating cost of fireworks ai serverless inference models.
from typing import Tuple
from litellm.constants import (
FIREWORKS_AI_4_B,
FIREWORKS_AI_16_B,
FIREWORKS_AI_56_B_MOE,
FIREWORKS_AI_80_B,
FIREWORKS_AI_176_B_MOE,
)
from litellm.types.utils import Usage
@ -43,10 +43,12 @@ def get_base_model_for_pricing(model_name: str) -> str:
params_billion = float(params_match)
# Determine the category based on the number of parameters
if params_billion <= FIREWORKS_AI_16_B:
return "fireworks-ai-up-to-16b"
elif params_billion <= FIREWORKS_AI_80_B:
return "fireworks-ai-16b-80b"
if params_billion <= FIREWORKS_AI_4_B:
return "fireworks-ai-up-to-4b"
elif params_billion <= FIREWORKS_AI_16_B:
return "fireworks-ai-4.1b-to-16b"
elif params_billion > FIREWORKS_AI_16_B:
return "fireworks-ai-above-16b"
# If no matches, return the original model_name
return "fireworks-ai-default"

72
litellm/model_prices_and_context_window_backup.json
View file

@ -11084,7 +11084,7 @@
"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": {
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 8192,
"max_output_tokens": 65536,
"input_cost_per_token": 0.0000012,
"output_cost_per_token": 0.0000012,
"litellm_provider": "fireworks_ai",
@ -11106,7 +11106,66 @@
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/deepseek-r1": {
"max_tokens": 20480,
"max_input_tokens": 128000,
"max_output_tokens": 20480,
"input_cost_per_token": 3e-6,
"output_cost_per_token": 8e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": {
"max_tokens": 20480,
"max_input_tokens": 128000,
"max_output_tokens": 20480,
"input_cost_per_token": 0.55e-6,
"output_cost_per_token": 2.19e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 3e-6,
"output_cost_per_token": 3e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.22e-6,
"output_cost_per_token": 0.88e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.15e-6,
"output_cost_per_token": 0.60e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/nomic-ai/nomic-embed-text-v1.5": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -11152,12 +11211,17 @@
"mode": "embedding",
"source": "https://fireworks.ai/pricing"
},
"fireworks-ai-up-to-16b": {
"fireworks-ai-up-to-4b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "fireworks_ai"
},
"fireworks-ai-16.1b-to-80b": {
"fireworks-ai-4.1b-to-16b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "fireworks_ai"
},
"fireworks-ai-above-16b": {
"input_cost_per_token": 0.0000009,
"output_cost_per_token": 0.0000009,
"litellm_provider": "fireworks_ai"

72
model_prices_and_context_window.json
View file

@ -11084,7 +11084,7 @@
"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": {
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 8192,
"max_output_tokens": 65536,
"input_cost_per_token": 0.0000012,
"output_cost_per_token": 0.0000012,
"litellm_provider": "fireworks_ai",
@ -11106,7 +11106,66 @@
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/deepseek-r1": {
"max_tokens": 20480,
"max_input_tokens": 128000,
"max_output_tokens": 20480,
"input_cost_per_token": 3e-6,
"output_cost_per_token": 8e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": {
"max_tokens": 20480,
"max_input_tokens": 128000,
"max_output_tokens": 20480,
"input_cost_per_token": 0.55e-6,
"output_cost_per_token": 2.19e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 3e-6,
"output_cost_per_token": 3e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.22e-6,
"output_cost_per_token": 0.88e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.15e-6,
"output_cost_per_token": 0.60e-6,
"litellm_provider": "fireworks_ai",
"mode": "chat",
"supports_response_schema": true,
"source": "https://fireworks.ai/pricing",
"supports_tool_choice": true
},
"fireworks_ai/nomic-ai/nomic-embed-text-v1.5": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -11152,12 +11211,17 @@
"mode": "embedding",
"source": "https://fireworks.ai/pricing"
},
"fireworks-ai-up-to-16b": {
"fireworks-ai-up-to-4b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "fireworks_ai"
},
"fireworks-ai-16.1b-to-80b": {
"fireworks-ai-4.1b-to-16b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "fireworks_ai"
},
"fireworks-ai-above-16b": {
"input_cost_per_token": 0.0000009,
"output_cost_per_token": 0.0000009,
"litellm_provider": "fireworks_ai"

3
tests/local_testing/test_completion.py
View file

@ -2661,11 +2661,10 @@ def test_re_use_openaiClient():
def test_completion_azure():
try:
print("azure chatgpt-v-3 test\n\n")
litellm.set_verbose = False
## Test azure call
response = completion(
model="azure/chatgpt-v-3",
model="azure/gpt-4o-new-test",
messages=messages,
api_key="os.environ/AZURE_API_KEY",
)

2
tests/local_testing/test_completion_cost.py
View file

@ -1283,7 +1283,7 @@ from litellm.llms.fireworks_ai.cost_calculator import get_base_model_for_pricing
@pytest.mark.parametrize(
"model, base_model",
[
("fireworks_ai/llama-v3p1-405b-instruct", "fireworks-ai-default"),
("fireworks_ai/llama-v3p1-405b-instruct", "fireworks-ai-above-16b"),
("fireworks_ai/llama4-maverick-instruct-basic", "fireworks-ai-default"),
],
)

6
tests/local_testing/test_custom_callback_input.py
View file

@ -450,12 +450,12 @@ def test_chat_azure_stream():
customHandler = CompletionCustomHandler()
litellm.callbacks = [customHandler]
response = litellm.completion(
model="azure/chatgpt-v-3",
model="azure/gpt-4o-new-test",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
)
# test streaming
response = litellm.completion(
model="azure/chatgpt-v-3",
model="azure/gpt-4o-new-test",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
stream=True,
)
@ -464,7 +464,7 @@ def test_chat_azure_stream():
# test failure callback
try:
response = litellm.completion(
model="azure/chatgpt-v-3",
model="azure/gpt-4o-new-test",
messages=[{"role": "user", "content": "Hi 👋 - i'm sync azure"}],
api_key="my-bad-key",
stream=True,

2
tests/local_testing/test_timeout.py
View file

@ -104,7 +104,7 @@ def test_hanging_request_azure():
{
"model_name": "azure-gpt",
"litellm_params": {
"model": "azure/chatgpt-v-3",
"model": "azure/gpt-4o-new-test",
"api_base": os.environ["AZURE_API_BASE"],
"api_key": os.environ["AZURE_API_KEY"],
},