scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-27 01:22:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 145

fix(providers): align Prism pricing and limits with the live catalog

Browse source 
deepseek-v4.1-flash bills 0.17/0.63 USD per 1M input/output tokens and takes image input;
deepseek-v4-flash bills 0.17/0.21 and caps output at 384000 tokens, per GET /v1/models
This commit is contained in:
mateo-berri 2026-09-19 05:11:33 -07:00
parent ea3cadd3e2
commit 6c371f76fd
3 changed files with 26 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
litellm/model_prices_and_context_window_backup.json
View file

@ -74785,13 +74785,13 @@
},
"prism/deepseek-v4.1-flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token": 1.7e-07,
"litellm_provider": "prism",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"output_cost_per_token": 6.3e-07,
"source": "https://prisminference.com/pricing",
"supported_endpoints": [
"/v1/chat/completions",
@ -74805,17 +74805,18 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": true
},
"prism/deepseek-v4-flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token": 1.7e-07,
"litellm_provider": "prism",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 2.1e-07,
"source": "https://prisminference.com/pricing",
"supported_endpoints": [
"/v1/chat/completions",
@ -74829,6 +74830,7 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": false
}
}

18
model_prices_and_context_window.json
View file

@ -74785,13 +74785,13 @@
},
"prism/deepseek-v4.1-flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token": 1.7e-07,
"litellm_provider": "prism",
"max_input_tokens": 1000000,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"output_cost_per_token": 6.3e-07,
"source": "https://prisminference.com/pricing",
"supported_endpoints": [
"/v1/chat/completions",
@ -74805,17 +74805,18 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": true
},
"prism/deepseek-v4-flash": {
"cache_read_input_token_cost": 7e-08,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token": 1.7e-07,
"litellm_provider": "prism",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 2.1e-07,
"source": "https://prisminference.com/pricing",
"supported_endpoints": [
"/v1/chat/completions",
@ -74829,6 +74830,7 @@
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_vision": false
}
}

11
tests/test_litellm/llms/openai_like/test_prism_provider.py
View file

@ -52,17 +52,17 @@ def test_prism_provider_keeps_explicit_credentials(monkeypatch: pytest.MonkeyPat
@pytest.mark.parametrize(
("model", "input_cost", "output_cost", "max_output_tokens"),
("model", "input_cost", "output_cost", "supports_vision"),
[
("prism/deepseek-v4.1-flash", 0.30, 1.20, 384_000),
("prism/deepseek-v4-flash", 0.14, 0.28, 393_216),
("prism/deepseek-v4.1-flash", 0.17, 0.63, True),
("prism/deepseek-v4-flash", 0.17, 0.21, False),
],
)
def test_prism_model_cost_and_capabilities(
model: str,
input_cost: float,
output_cost: float,
max_output_tokens: int,
supports_vision: bool,
):
from litellm.cost_calculator import cost_per_token
@ -78,11 +78,12 @@ def test_prism_model_cost_and_capabilities(
assert completion_cost == pytest.approx(output_cost)
assert model_info["cache_read_input_token_cost"] == pytest.approx(7e-08)
assert model_info["max_input_tokens"] == 1_000_000
assert model_info["max_output_tokens"] == max_output_tokens
assert model_info["max_output_tokens"] == 384_000
assert model_info["supports_function_calling"] is True
assert model_info["supports_native_streaming"] is True
assert model_info["supports_reasoning"] is True
assert model_info["supports_response_schema"] is True
assert litellm.supports_vision(model) is supports_vision
def test_prism_is_available_in_add_model_form():