scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-15 09:12:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 311

fix(openinfer): sync catalog to live @oi model IDs

Browse source 
OpenInfer currently serves @oi/Llama-3.2-1B-Instruct and @oi/Qwen3.5-9B;
keep the @oi/ prefix so LiteLLM forwards the API model id after the provider split.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
AJ-ing 2026-08-14 22:43:29 +10:00
parent 306d10c850
commit 3bc50c5bdd
3 changed files with 30 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
litellm/model_prices_and_context_window_backup.json
View file

@ -63838,7 +63838,7 @@
"supports_response_schema": true,
"supports_vision": false
},
"openinfer/llama-3.1-8b-instruct": {
"openinfer/@oi/Llama-3.2-1B-Instruct": {
"max_tokens": 8192,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
@ -63848,5 +63848,16 @@
"mode": "chat",
"supports_function_calling": true,
"source": "https://api.openinfer.ai/v1/models"
},
"openinfer/@oi/Qwen3.5-9B": {
"max_tokens": 8192,
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "openinfer",
"mode": "chat",
"supports_function_calling": true,
"source": "https://api.openinfer.ai/v1/models"
}
}

13
model_prices_and_context_window.json
View file

@ -63838,7 +63838,7 @@
"supports_response_schema": true,
"supports_vision": false
},
"openinfer/llama-3.1-8b-instruct": {
"openinfer/@oi/Llama-3.2-1B-Instruct": {
"max_tokens": 8192,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
@ -63848,5 +63848,16 @@
"mode": "chat",
"supports_function_calling": true,
"source": "https://api.openinfer.ai/v1/models"
},
"openinfer/@oi/Qwen3.5-9B": {
"max_tokens": 8192,
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "openinfer",
"mode": "chat",
"supports_function_calling": true,
"source": "https://api.openinfer.ai/v1/models"
}
}

12
tests/test_litellm/llms/openai_like/test_openinfer_provider.py
View file

@ -31,13 +31,13 @@ class TestOpenInferProviderConfig:
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
model, provider, api_key, api_base = get_llm_provider(
model="openinfer/llama-3.1-8b-instruct",
model="openinfer/@oi/Llama-3.2-1B-Instruct",
custom_llm_provider=None,
api_base=None,
api_key="sk-test",
)
assert model == "llama-3.1-8b-instruct"
assert model == "@oi/Llama-3.2-1B-Instruct"
assert provider == "openinfer"
assert api_key == "sk-test"
assert api_base == "https://api.openinfer.ai/v1"
@ -49,7 +49,7 @@ class TestOpenInferProviderConfig:
monkeypatch.setenv("OPENINFER_API_BASE", "https://proxy.internal/v1")
_, provider, api_key, api_base = get_llm_provider(
model="openinfer/llama-3.1-8b-instruct",
model="openinfer/@oi/Qwen3.5-9B",
custom_llm_provider=None,
api_base=None,
api_key=None,
@ -65,7 +65,7 @@ class TestOpenInferProviderConfig:
monkeypatch.setenv("OPENINFER_API_KEY", "sk-env-key")
_, provider, api_key, api_base = get_llm_provider(
model="llama-3.1-8b-instruct",
model="@oi/Llama-3.2-1B-Instruct",
custom_llm_provider=None,
api_base="https://api.openinfer.ai/v1",
api_key=None,
@ -76,14 +76,14 @@ class TestOpenInferProviderConfig:
def test_chat_completions_url(self):
config = litellm.ProviderConfigManager.get_provider_chat_config(
model="llama-3.1-8b-instruct", provider=litellm.LlmProviders.OPENINFER
model="@oi/Llama-3.2-1B-Instruct", provider=litellm.LlmProviders.OPENINFER
)
assert config is not None
assert (
config.get_complete_url(
api_base=None,
api_key="sk-test",
model="llama-3.1-8b-instruct",
model="@oi/Llama-3.2-1B-Instruct",
optional_params={},
litellm_params={},
)