Agnes 3.0 Pro

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.

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

POST https://apihub.agnes-ai.com/v1/chat/completions

Headers

-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.

{
  "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

Basic Chat
Coding
Streaming
Image Understanding

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
  }'

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
  }'

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
  }'

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"
            }
          }
        ]
      }
    ]
  }'

Response Format

{
  "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

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.

Text Input
Structured Input

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
  }'

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
  }'

Responses output format

{
  "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.

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.

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.

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.

Messages API

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

Messages endpoint

POST https://apihub.agnes-ai.com/v1/messages

Messages headers

-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

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

{
  "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.

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

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`

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.

Best Practices

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.

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.

Long-context Tasks

Use structured sections, filenames, or document labels inside the prompt so the model can refer to sources and produce traceable conclusions.

Integration Checklist

Use agnes-3.0-pro as the model name.

After launch, confirm that your account has access to Agnes 3.0 Pro.

Basic chat completion requests must include model and messages.

Use publicly accessible image_url values for image inputs.

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

Get Started

Use Guides

Overview

Core directions and highlights

Evaluation results

API Reference

Endpoint

Headers

Request Parameters

Image URL Input

Request Examples

Response Format

Response Fields

Responses API

Responses endpoint

Responses request parameters

Responses output format

Messages API

Messages endpoint

Messages headers

Messages request parameters

Messages request example

Messages response format

Limits and Pricing

Best Practices

Integration Checklist

​Overview

​Core directions and highlights

​Evaluation results

​API Reference

​Endpoint

​Headers

​Request Parameters

​Image URL Input

​Request Examples

​Response Format

​Response Fields

​Responses API

​Responses endpoint

​Responses request parameters

​Responses output format

​Messages API

​Messages endpoint

​Messages headers

​Messages request parameters

​Messages request example

​Messages response format

​Limits and Pricing

​Best Practices

​Integration Checklist

Overview

Core directions and highlights

Evaluation results

API Reference

Endpoint

Headers

Request Parameters

Image URL Input

Request Examples

Response Format

Response Fields

Responses API

Responses endpoint

Responses request parameters

Responses output format

Messages API

Messages endpoint

Messages headers

Messages request parameters

Messages request example

Messages response format

Limits and Pricing

Best Practices

Integration Checklist