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

# Agnes 3.0 Pro

> A new-generation Pro model, coming soon, for agentic work, professional document analysis, scientific coding, and long-context reasoning.

<Warning>
  Agnes 3.0 Pro is coming soon. This documentation is available for integration preparation; API availability will be announced at launch. Responses below are format examples, not evidence of current availability.
</Warning>

## Overview

Agnes 3.0 Pro is Agnes AI's new-generation Pro model, focused on real-world agentic tasks, professional document understanding, scientific coding, and long-context analysis. It is designed for applications that combine evidence, tools, and reasoning to address complex work.

| Item | Value |
| - | - |
| Model | `agnes-3.0-pro` |
| Status | Coming soon |
| Base URL | `https://apihub.agnes-ai.com/v1` |
| Endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages` |
| Input | Text and image URLs |
| Output | Text |
| Billing | Cache read, regular input, and output tokens |

## Core directions and highlights

* **Agentic work**: Focused on analyzing and executing multi-step tasks. In the supplied snapshot, AA-Briefcase v1.1 is the highest among the four pictured models, while GDPval-AA v2.1 is close to the comparison models.
* **Professional document analysis**: Designed for extracting evidence and forming conclusions from documents. GDP.pdf is the highest among the models in this comparison.
* **Scientific coding and complex reasoning**: Suitable for scientific computing, code analysis, and technical problem-solving. SciCode exceeds the two pictured Flash comparison models; performance varies across reasoning and coding tasks.
* **Long-context synthesis**: Supports analysis across long documents and multiple sources, with an AA-LCR v1.1 score of 80.0.
* **Developer workflows**: Includes tool-calling parameters, streaming, and text and image input examples for interactive assistants and agentic applications.

## Evaluation results

The following scores reproduce the supplied pre-release AA evaluation snapshot, including its metric names and values. They are not a live leaderboard ranking. Results from different evaluation versions should not be compared directly, and this snapshot does not establish across-the-board gains over the previous generation.

| Metric | Score |
| - | -: |
| AA Index | 42.87 |
| AA-Briefcase v1.1 | 1585 |
| GDPval-AA v2.1 | 1639 |
| AutomationBench-AA | 59.8 |
| Terminal-Bench 4.0 | 32.5 |
| SciCode | 55.67 |
| Humanity's Last Exam | 37.91 |
| GDP.pdf | 15.9 |
| CritPt | 15.2 |
| AA-Omniscience Accuracy | 27.4 |
| AA-LCR v1.1 | 80.0 |

## API Reference

### Endpoint

```text theme={null}
POST https://apihub.agnes-ai.com/v1/chat/completions
```

### Headers

```bash theme={null}
-H "Authorization: Bearer YOUR_API_KEY"
-H "Content-Type: application/json"
```

### Request Parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | Model name. Use `agnes-3.0-pro`. |
| `messages` | array | Yes | Conversation messages, including `system`, `user`, and `assistant` messages. |
| `messages[].content` | string / array | Yes | Message content. It can be plain text or an array of content blocks containing `text` and `image_url`. |
| `temperature` | number | No | Controls randomness. Lower values produce more deterministic output. |
| `top_p` | number | No | Controls nucleus sampling. |
| `max_tokens` | number | No | Maximum number of tokens to generate in the response. |
| `stream` | boolean | No | Whether to enable streaming output. |
| `tools` | array | No | Tool definitions for tool-calling workflows. |
| `tool_choice` | string / object | No | Controls whether and how the model uses tools. |
| `chat_template_kwargs` | object | No | Extension field for OpenAI-compatible requests. |
| `thinking` | object | No | Field for enabling Thinking mode in Anthropic-compatible requests. |

## Image URL Input

Agnes 3.0 Pro supports text and image URL inputs in the same `messages` request.

```json theme={null}
{
  "role": "user",
  "content": [
    {
      "type": "text",
      "text": "Analyze this architecture diagram and identify possible failure points."
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/diagram.png"
      }
    }
  ]
}
```

## Request Examples

<Tabs>
  <Tab title="Basic Chat">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "messages": [
          {
            "role": "system",
            "content": "You are a precise technical assistant."
          },
          {
            "role": "user",
            "content": "Explain the tradeoffs between optimistic locking and pessimistic locking in distributed systems."
          }
        ],
        "temperature": 0.3,
        "max_tokens": 1200
      }'
    ```
  </Tab>

  <Tab title="Coding">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "messages": [
          {
            "role": "user",
            "content": "Review this TypeScript API handler for security issues, explain the risks, and provide a corrected version."
          }
        ],
        "temperature": 0.2,
        "max_tokens": 2000
      }'
    ```
  </Tab>

  <Tab title="Streaming">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "messages": [
          {
            "role": "user",
            "content": "Create a step-by-step migration plan for moving a monolith to services."
          }
        ],
        "stream": true
      }'
    ```
  </Tab>

  <Tab title="Image Understanding">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "messages": [
          {
            "role": "user",
            "content": [
              {
                "type": "text",
                "text": "Summarize this chart and call out any anomalies."
              },
              {
                "type": "image_url",
                "image_url": {
                  "url": "https://example.com/chart.png"
                }
              }
            ]
          }
        ]
      }'
    ```
  </Tab>
</Tabs>

## Response Format

```json theme={null}
{
  "id": "chatcmpl_xxx",
  "object": "chat.completion",
  "created": 1784899200,
  "model": "agnes-3.0-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 120,
    "completion_tokens": 300,
    "total_tokens": 420
  }
}
```

### Response Fields

| Field | Type | Description |
| - | - | - |
| `id` | string | Unique ID of the completion request. |
| `object` | string | Object type, usually `chat.completion`. |
| `created` | integer | Request timestamp. |
| `model` | string | Model used for the request. |
| `choices` | array | List of generated responses. |
| `choices[].message.role` | string | Role of the message sender. |
| `choices[].message.content` | string | Content generated by the model. |
| `choices[].finish_reason` | string | Reason generation stopped. |
| `usage` | object | Token usage information. |

## Responses API

In addition to Chat Completions, this model supports the OpenAI Responses API. Use `input` instead of `messages`.

### Responses endpoint

```text theme={null}
POST https://apihub.agnes-ai.com/v1/responses
```

### Responses request parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | Model name. Use `agnes-3.0-pro`. |
| `input` | string / array | Yes | A plain text prompt or an array of structured input messages. |
| `max_output_tokens` | integer | No | Maximum output budget. Use a larger value for reasoning models to avoid an `incomplete` response. |

<Tabs>
  <Tab title="Text Input">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/responses \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "input": "Explain how autonomous agents use tools.",
        "max_output_tokens": 1024
      }'
    ```
  </Tab>

  <Tab title="Structured Input">
    ```bash theme={null}
    curl https://apihub.agnes-ai.com/v1/responses \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "agnes-3.0-pro",
        "input": [
          {
            "role": "user",
            "content": [
              {
                "type": "input_text",
                "text": "Explain how autonomous agents use tools."
              }
            ]
          }
        ],
        "max_output_tokens": 1024
      }'
    ```
  </Tab>
</Tabs>

### Responses output format

```json theme={null}
{
  "id": "resp_xxx",
  "object": "response",
  "status": "completed",
  "model": "agnes-3.0-pro",
  "output": [
    {
      "type": "reasoning",
      "summary": []
    },
    {
      "type": "message",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Autonomous agents use tools to retrieve data and perform actions."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 40,
    "output_tokens": 80,
    "total_tokens": 120
  },
  "error": null,
  "incomplete_details": null
}
```

| Field | Type | Description |
| - | - | - |
| `id` | string | Unique response ID. |
| `object` | string | Object type, usually `response`. |
| `status` | string | Response state, such as `completed` or `incomplete`. |
| `output` | array | Ordered response items, including reasoning and assistant messages. |
| `output[].type` | string | Item type, such as `reasoning` or `message`. |
| `output[].content[].type` | string | Content type. Generated text uses `output_text`. |
| `output[].content[].text` | string | Generated assistant text. |
| `usage` | object | Token usage information. |
| `error` | object / null | Error details when the request fails. |
| `incomplete_details` | object / null | Explains why a response stopped before completion. |

<Warning>
  The current response does not include a top-level `output_text` convenience field. Extract generated text from message items where `output[].type` is `message` and `output[].content[].type` is `output_text`.
</Warning>

<Note>
  Reasoning items are optional and can use either `content[].reasoning_text` or `summary[].summary_text`. Token usage field names can also vary by model: support both `input_tokens` / `output_tokens` and `prompt_tokens` / `completion_tokens`.
</Note>

<Tip>
  If `status` is `incomplete`, inspect `incomplete_details` and retry with a larger `max_output_tokens` value. Reasoning models can consume part of the output budget before producing assistant text.
</Tip>

## Messages API

This model also supports the Anthropic-compatible Messages API. Send conversation input in `messages` and authenticate with `x-api-key`.

### Messages endpoint

```text theme={null}
POST https://apihub.agnes-ai.com/v1/messages
```

### Messages headers

```bash theme={null}
-H "x-api-key: YOUR_API_KEY"
-H "anthropic-version: 2023-06-01"
-H "Content-Type: application/json"
```

### Messages request parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | Model name. Use `agnes-3.0-pro`. |
| `max_tokens` | integer | Yes | Maximum number of output tokens. Use a larger value for reasoning models. |
| `messages` | array | Yes | Conversation messages containing `user` and `assistant` roles. |
| `messages[].role` | string | Yes | Message role. Use `user` or `assistant`. |
| `messages[].content` | string / array | Yes | Plain text or an array of Anthropic-compatible content blocks. |
| `system` | string / array | No | System instruction for the request. |
| `temperature` | number | No | Controls output randomness. |
| `stream` | boolean | No | Whether to return a streaming response. |

### Messages request example

```bash theme={null}
curl https://apihub.agnes-ai.com/v1/messages \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-3.0-pro",
    "max_tokens": 1024,
    "system": "You are a helpful AI assistant.",
    "messages": [
      {
        "role": "user",
        "content": "Explain how autonomous agents use tools."
      }
    ]
  }'
```

### Messages response format

```json theme={null}
{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "model": "agnes-3.0-pro",
  "content": [
    {
      "type": "text",
      "text": "Autonomous agents use tools to retrieve information and perform actions."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 290,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "output_tokens": 28
  }
}
```

| Field | Type | Description |
| - | - | - |
| `id` | string | Unique message ID. |
| `type` | string | Object type, usually `message`. |
| `role` | string | Response role, usually `assistant`. |
| `model` | string | Model used for the request. |
| `content` | array | Ordered response content blocks. |
| `content[].type` | string | Content block type. Generated text uses `text`. |
| `content[].text` | string | Generated assistant text. |
| `stop_reason` | string | Reason generation stopped, such as `end_turn` or `max_tokens`. |
| `usage.input_tokens` | integer | Number of input tokens used. |
| `usage.output_tokens` | integer | Number of output tokens generated. |
| `usage.cache_creation_input_tokens` | integer | Input tokens written to the prompt cache. |
| `usage.cache_read_input_tokens` | integer | Input tokens read from the prompt cache. |

<Note>
  Read generated text from content blocks where `content[].type` is `text`. If `stop_reason` is `max_tokens`, retry with a larger `max_tokens` value.
</Note>

## Limits and Pricing

Agnes 3.0 Pro is an upcoming paid model. Usage is billed by cache read, input, and output tokens.

| Item | Value |
| - | - |
| Input modalities | Text, image |
| Output modalities | Text |
| Reasoning | Yes |

| Type | USD Price |
| - | -: |
| Input cache hit / Cache Read | `$0.045 / M tokens` |
| Input cache miss / Input | `$0.45 / M tokens` |
| Output | `$0.90 / M tokens` |

<Note>
  The cached-input price is 10% of the regular input-token price. Pricing and availability may vary by account, region, billing configuration, or later pricing updates. Use the Agnes AI platform dashboard as the source of truth for your account.
</Note>

## Best Practices

<AccordionGroup>
  <Accordion title="Reasoning-heavy Tasks">
    Use Agnes 3.0 Pro for tasks where correctness and multi-step reasoning matter more than raw latency, such as scientific reasoning, complex policy analysis, and long-form technical planning.
  </Accordion>

  <Accordion title="Coding Tasks">
    Provide the target language, framework, existing code, error messages, expected behavior, and constraints. Ask for root-cause analysis before the patch when debugging complex issues.
  </Accordion>

  <Accordion title="Long-context Tasks">
    Use structured sections, filenames, or document labels inside the prompt so the model can refer to sources and produce traceable conclusions.
  </Accordion>
</AccordionGroup>

## Integration Checklist

<Check>
  Use `agnes-3.0-pro` as the model name.
</Check>

<Check>
  After launch, confirm that your account has access to Agnes 3.0 Pro.
</Check>

<Check>
  Basic chat completion requests must include `model` and `messages`.
</Check>

<Check>
  Use publicly accessible `image_url` values for image inputs.
</Check>

<Check>
  Track cache read, input, and output token usage because this is a paid model.
</Check>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.