8000 Documentation: Inference -> List supported models by kaisopos · Pull Request #1279 · oumi-ai/oumi · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Documentation: Inference -> List supported models #1279

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jan 28, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
74 changes: 74 additions & 0 deletions docs/user_guides/infer/inference_engines.md
Original file line number Diff line number Diff line change
Expand Up @@ -314,6 +314,18 @@ engine = AnthropicInferenceEngine(
)
```

**Supported Models**

The Anthropic models available via this API as of late Jan'2025 are listed below. For an up-to-date list, please visit [this page](https://docs.anthropic.com/en/docs/about-claude/models).

| Anthropic Model | API Model Name |
|---------------------------------------|---------------------------|
| Claude 3.5 Sonnet (most intelligent) | claude-3-5-sonnet-latest |
| Claude 3.5 Haiku (fastest) | claude-3-5-haiku-latest |
| Claude 3.0 Opus | claude-3-opus-latest |
| Claude 3.0 Sonnet | claude-3-sonnet-20240229 |
| Claude 3.0 Haiku | claude-3-haiku-20240307 |

**Resources**

- [Anthropic API Documentation](https://docs.anthropic.com/en/api/getting-started)
Expand Down Expand Up @@ -347,6 +359,28 @@ engine = GoogleVertexInferenceEngine(
)
```

**Supported Models**

The most popular Google Vertex AI models available via this API (as of late Jan'2025) are listed below. For a full list, including specialized and 3rd party models, please visit [this page](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models).

| Gemini Model | API Model Name |
|---------------------------------------|----------------------------------|
| Gemini 2.0 Flash Thinking Mode | google/gemini-2.0-flash-thinking-exp-01-21 |
| Gemini 2.0 Flash | google/gemini-2.0-flash-exp |
| Gemini 1.5 Flash | google/gemini-1.5-flash-002 |
| Gemini 1.5 Pro | google/gemini-1.5-pro-002 |
| Gemini 1.0 Pro Vision | google/gemini-1.0-pro-vision-001 |

| Gemma Model | API Model Name |
|---------------------------------------|----------------------------------|
| Gemma 2 2B IT | google/gemma2-2b-it |
| Gemma 2 9B IT | google/gemma2-9b-it |
| Gemma 2 27B IT | google/gemma2-27b-it |
| Code Gemma 2B | google/codegemma-2b |
| Code Gemma 7B | google/codegemma-7b |
| Code Gemma 7B IT | google/codegemma-7b-it |


**Resources**

- [Vertex AI Documentation](https://cloud.google.com/vertex-ai/docs) for Google Cloud AI services
Expand All @@ -369,6 +403,19 @@ engine = GoogleGeminiInferenceEngine(
)
```

**Supported Models**

The Gemini models available via this API as of late Jan'2025 are listed below. For an up-to-date list, please visit [this page](https://ai.google.dev/gemini-api/docs/models/gemini).

| Model Name | API Model Name |
|---------------------------------------|---------------------------|
| Gemini 2.0 Flash (experimental) | gemini-2.0-flash-exp |
| Gemini 1.5 Flash | gemini-1.5-flash |
| Gemini 1.5 Flash-8B | gemini-1.5-flash-8b |
| Gemini 1.5 Pro | gemini-1.5-pro |
| Gemini 1.0 Pro (deprecated) | gemini-1.0-pro |
| AQA | aqa |

**Resources**

- [Gemini API Documentation](https://ai.google.dev/docs) for Gemini API details
Expand All @@ -393,6 +440,19 @@ engine = OpenAIInferenceEngine(
)
```

**Supported Models**

The most popular models available via the OpenAI API as of late Jan'2025 are listed below. For a full list please visit [this page](https://platform.openai.com/docs/models)

| OpenAI Model | API Model Name |
|---------------------------------------|---------------------------|
| GPT 4o (flagship model) | gpt-4o |
| GPT 4o mini (fast and affordable) | gpt-4o-mini |
| o1 (reasoning model) | o1 |
| o1 mini (reasoning and affordable) | o1-mini |
| GPT-4 Turbo | gpt-4-turbo |
| GPT-4 | gpt-4 |

**Resources**

- [OpenAI API Documentation](https://platform.openai.com/docs) for OpenAI API details
Expand All @@ -417,6 +477,8 @@ engine = TogetherInferenceEngine(
)
```

The models available via this API can be found at [together.ai](https://www.together.ai/).

### DeepSeek

[DeepSeek](https://deepseek.com) allows to access the DeepSeek models (Chat, Code, and Reasoning) through the DeepSeek AI Platform.
Expand All @@ -437,6 +499,16 @@ engine = DeepSeekInferenceEngine(
)
```

**Supported Models**

The DeepSeek models available via this API as of late Jan'2025 are listed below. For an up-to-date list, please visit [this page](https://api-docs.deepseek.com/quick_start/pricing).

| DeepSeek Model | API Model Name |
|---------------------------------------|---------------------------|
| DeepSeek-V3 | deepseek-chat |
| DeepSeek-R1 (reasoning with CoT) | deepseek-reasoner |


### Parasail.io

[Parasail.io](https://parasail.io) offers a cloud-native inference platform that combines the flexibility of self-hosted models with the convenience of cloud infrastructure.
Expand All @@ -461,6 +533,8 @@ engine = ParasailInferenceEngine(
)
```

The models available via this API can be found at [docs.parasail.io](https://docs.parasail.io/).

**Resources**

- [Parasail.io Documentation](https://docs.parasail.io)
Expand Down
0