scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

Replace Nebius AI Studio with Token Factory

Browse source
This commit is contained in:
shivay-couchbase 2026-02-10 01:25:29 +05:30
parent f2ba120c43
commit dfcef103f1
9 changed files with 19 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -340,7 +340,7 @@ Support for more providers. Missing a provider or LLM Platform, raise a [feature
| [Mistral AI API (`mistral`)](https://docs.litellm.ai/docs/providers/mistral) | ✅ | ✅ | ✅ | ✅ | | | | | | |
| [Moonshot (`moonshot`)](https://docs.litellm.ai/docs/providers/moonshot) | ✅ | ✅ | ✅ | | | | | | | |
| [Morph (`morph`)](https://docs.litellm.ai/docs/providers/morph) | ✅ | ✅ | ✅ | | | | | | | |
| [Nebius AI Studio (`nebius`)](https://docs.litellm.ai/docs/providers/nebius) | ✅ | ✅ | ✅ | ✅ | | | | | | |
| [Nebius Token Factory (`nebius`)](https://docs.litellm.ai/docs/providers/nebius) | ✅ | ✅ | ✅ | ✅ | | | | | | |
| [NLP Cloud (`nlp_cloud`)](https://docs.litellm.ai/docs/providers/nlp_cloud) | ✅ | ✅ | ✅ | | | | | | | |
| [Novita AI (`novita`)](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link) | ✅ | ✅ | ✅ | | | | | | | |
| [Nscale (`nscale`)](https://docs.litellm.ai/docs/providers/nscale) | ✅ | ✅ | ✅ | | | | | | | |

4
docs/my-website/docs/embedding/supported_embedding.md
View file

@ -632,7 +632,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/embeddings' \
</TabItem>
</Tabs>
## Nebius AI Studio Embedding Models
## Nebius Token Factory Embedding Models
### Usage - Embedding
```python
@ -648,7 +648,7 @@ print(response)
```
### Supported Models
All supported models can be found here: https://studio.nebius.ai/models/embedding
All supported models can be found here: https://tokenfactory.nebius.com/models
| Model Name | Function Call |
|--------------------------|-----------------------------------------------------------------|

10
docs/my-website/docs/providers/nebius.md
View file

@ -1,12 +1,12 @@
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
# Nebius AI Studio
https://docs.nebius.com/studio/inference/quickstart
# Nebius Token Factory
https://tokenfactory.nebius.com/
:::tip
**Litellm provides support to all models from Nebius AI Studio. To use a model, set `model=nebius/<any-model-on-nebius-ai-studio>` as a prefix for litellm requests. The full list of supported models is provided at https://studio.nebius.ai/ **
**Litellm provides support to all models from Nebius Token Factory. To use a model, set `model=nebius/<any-model-on-nebius-token-factory>` as a prefix for litellm requests. The full list of supported models is provided at https://tokenfactory.nebius.com/**
:::
@ -90,7 +90,7 @@ print(response)
## Usage with LiteLLM Proxy Server
Here's how to call a Nebius AI Studio model with the LiteLLM Proxy Server
Here's how to call a Nebius Token Factory model with the LiteLLM Proxy Server
1. Modify the config.yaml
@ -98,7 +98,7 @@ Here's how to call a Nebius AI Studio model with the LiteLLM Proxy Server
model_list:
- model_name: my-model
litellm_params:
model: nebius/<your-model-name> # add nebius/ prefix to use Nebius AI Studio as provider
model: nebius/<your-model-name> # add nebius/ prefix to use Nebius Token Factory as provider
api_key: api-key # api key to send your model
```
2. Start the proxy

2
docs/my-website/release_notes/v1.72.0-stable/index.md
View file

@ -126,7 +126,7 @@ print(result)
- Tool calls parsing on streaming - [PR](https://github.com/BerriAI/litellm/pull/11171)
- **[Cohere](../../docs/providers/cohere)**
- Swapped Cohere and Cohere Chat provider positioning - [PR](https://github.com/BerriAI/litellm/pull/11173)
- **[Nebius AI Studio](../../docs/providers/nebius)**
- **[Nebius Token Factory](../../docs/providers/nebius)**
- New provider integration - [PR](https://github.com/BerriAI/litellm/pull/11143)
## LLM API Endpoints

2
litellm/llms/nebius/chat/transformation.py
View file

@ -1,5 +1,5 @@
"""
Nebius AI Studio Chat Completions API - Transformation
Nebius Token Factory Chat Completions API - Transformation
This is OpenAI compatible - no translation needed / occurs
"""

2
litellm/llms/nebius/embedding/transformation.py
View file

@ -1,5 +1,5 @@
"""
Calls handled in openai/
as Nebius AI Studio is an openai-compatible endpoint.
as Nebius Token Factory is an openai-compatible endpoint.
"""

2
provider_endpoints_support.json
View file

@ -1450,7 +1450,7 @@
}
},
"nebius": {
"display_name": "Nebius AI Studio (`nebius`)",
"display_name": "Nebius Token Factory (`nebius`)",
"url": "https://docs.litellm.ai/docs/providers/nebius",
"endpoints": {
"chat_completions": true,

12
tests/test_litellm/llms/nebius/test_nebius_chat_transformation.py
View file

@ -1,8 +1,8 @@
"""
Unit tests for Nebius AI Studio configuration.
Unit tests for Nebius Token Factory configuration.
These tests validate the NebiusConfig class which extends OpenAIGPTConfig.
Nebius AI Studio is an OpenAI-compatible provider with minor customizations.
Nebius Token Factory is an OpenAI-compatible provider with minor customizations.
"""
import os
@ -20,7 +20,7 @@ from litellm.llms.nebius.chat.transformation import NebiusConfig
class TestNebiusConfig:
"""Test class for Nebius AI Studio functionality"""
"""Test class for Nebius Token Factory functionality"""
def test_default_api_base(self):
"""Test that default API base is used when none is provided"""
@ -50,7 +50,7 @@ class TestNebiusConfig:
@pytest.mark.respx()
def test_nebius_completion_mock(self, respx_mock):
"""
Mock test for Nebius AI Studio completion using the model format from docs.
Mock test for Nebius Token Factory completion using the model format from docs.
This test mocks the actual HTTP request to test the integration properly.
"""
@ -60,11 +60,11 @@ class TestNebiusConfig:
# Set up environment variables for the test
api_key = "fake-nebius-key"
api_base = "https://api.studio.nebius.ai/v1"
api_base = "https://api.tokenfactory.nebius.com/v1/"
model = "nebius/Qwen/Qwen3-4B"
model_name = "Qwen3-4B" # The actual model name without provider prefix
# Mock the HTTP request to the Nebius AI Studio API
# Mock the HTTP request to the Nebius Token Factory API
respx_mock.post(f"{api_base}/chat/completions").respond(
json={
"id": "chatcmpl-123",

2
tests/test_litellm/llms/wandb/test_wandb_chat_transformation.py
View file

@ -2,7 +2,7 @@
Unit tests for WandB Inference configuration.
These tests validate the WandbInferenceConfig class which extends OpenAIGPTConfig.
Nebius AI Studio is an OpenAI-compatible provider with minor customizations.
Nebius Token Factory is an OpenAI-compatible provider with minor customizations.
"""
import os