> ## Documentation Index
> Fetch the complete documentation index at: https://masaic-ai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Providers

> Supported model providers and how to use them with OpenResponses

# Model Providers

OpenResponses supports various model providers that can be used with the `provider@model_name` convention. This page provides examples of how to use each supported provider with curl commands.

## Supported Model Providers

| Provider   | API Endpoint                                                                                                         |
| ---------- | -------------------------------------------------------------------------------------------------------------------- |
| openai     | [https://api.openai.com/v1](https://api.openai.com/v1)                                                               |
| claude     | [https://api.anthropic.com/v1](https://api.anthropic.com/v1)                                                         |
| anthropic  | [https://api.anthropic.com/v1](https://api.anthropic.com/v1)                                                         |
| groq       | [https://api.groq.com/openai/v1](https://api.groq.com/openai/v1)                                                     |
| togetherai | [https://api.together.xyz/v1](https://api.together.xyz/v1)                                                           |
| gemini     | [https://generativelanguage.googleapis.com/v1beta/openai/](https://generativelanguage.googleapis.com/v1beta/openai/) |
| google     | [https://generativelanguage.googleapis.com/v1beta/openai/](https://generativelanguage.googleapis.com/v1beta/openai/) |
| deepseek   | [https://api.deepseek.com](https://api.deepseek.com)                                                                 |
| ollama     | [http://localhost:11434/v1](http://localhost:11434/v1)                                                               |
| xai        | [https://api.x.ai/v1](https://api.x.ai/v1)                                                                           |

## Provider Examples

### OpenAI

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $OPENAI_API_KEY' \
--data '{
    "model": "openai@gpt-4o",
    "tools": [{
      "type": "file_search",
      "vector_store_ids": ["vs_technical_docs"],
      "max_num_results": 5,
      "filters": {
        "type": "and",
        "filters": [
          {
            "type": "eq",
            "key": "category",
            "value": "documentation"
          }
        ]
      }
    }],
    "input": "How do I implement rate limiting?",
    "instructions": "Answer questions using information from the provided documents."
}'
```

### Claude / Anthropic

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $ANTHROPIC_API_KEY' \
--data '{
    "model": "claude@claude-3-5-sonnet-20240620",
    "tools": [{
      "type": "file_search",
      "vector_store_ids": ["vs_technical_docs"],
      "max_num_results": 5
    }],
    "input": "Explain the architecture of the system",
    "instructions": "Be technical and concise in your answers."
}'
```

### Groq

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $GROQ_API_KEY' \
--data '{
    "model": "groq@llama3-70b-8192",
    "tools": [{
      "type": "function_call",
      "functions": [
        {
          "name": "get_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              }
            },
            "required": ["location"]
          }
        }
      ]
    }],
    "input": "What's the weather like in San Francisco?",
    "instructions": "Use the provided tools to answer questions."
}'
```

### TogetherAI

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $TOGETHER_API_KEY' \
--data '{
    "model": "togetherai@mistralai/Mixtral-8x7B-Instruct-v0.1",
    "tools": [{
      "type": "code_interpreter"
    }],
    "input": "Plot a sine wave from 0 to 2π",
    "instructions": "Use code interpreter when mathematical calculations are needed."
}'
```

### Google / Gemini

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $GOOGLE_API_KEY' \
--data '{
    "model": "google@gemini-2.0-flash",
    "tools": [{
      "type": "web_search"
    }],
    "input": "What are the latest developments in quantum computing?",
    "instructions": "Use web search to provide up-to-date information."
}'
```

### DeepSeek

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $DEEPSEEK_API_KEY' \
--data '{
    "model": "deepseek@deepseek-chat",
    "input": "Help me debug this Python function: def factorial(n): return n * factorial(n-1)",
    "instructions": "Provide code improvements with explanations."
}'
```

### Ollama (Local)

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--data '{
    "model": "ollama@llama3",
    "input": "Generate a short story about a robot learning to paint.",
    "instructions": "Be creative and descriptive."
}'
```

### xAI

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $XAI_API_KEY' \
--data '{
    "model": "xai@grok-2",
    "input": "Explain how neural networks work",
    "instructions": "Explain complex topics in simple terms."
}'
```

## Using Custom Model Providers

For any model provider not listed above, you can use the `model_endpoint@model_name` convention by directly specifying the full API endpoint URL:

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $YOUR_API_KEY' \
--data '{
    "model": "http://your-custom-model-endpoint.com/v1@your-model-name",
    "input": "Summarize this technical document",
    "instructions": "Be thorough but concise."
}'
```

### Example with Local LLM Server

```bash theme={null}
curl --location 'http://localhost:6644/v1/responses' \
--header 'Content-Type: application/json' \
--data '{
    "model": "http://localhost:1234/v1@local-model",
    "input": "Generate unit tests for this function",
    "instructions": "Focus on edge cases and error handling."
}'
```

The format for specifying a model is always `provider@model-name` or `model_endpoint@model_name`, where:

* `provider`: The model provider (e.g., claude, deepseek, google, openai)
* `model_endpoint`: For locally deployed models or any custom model provider, the endpoint URL where chat/completions is available
* `model-name`: The specific model to use from that provider or endpoint