gpt-6-astra

GPT-6 Astra uses the Responses API for text, image and file input, Structured Outputs, and tool workflows. Select a tab for the request shape you need.

gpt-6-astra also accepts text requests through POST /v1/chat/completions. Use this Responses API reference for reasoning controls, tools, image and file input, Structured Outputs, streaming, and prompt caching.

Text and reasoning
Image and file input
Structured output
Tool workflows
Chat Completions

Create response

POST /v1/responses

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6-astra",
    "instructions": "Act as a senior reliability engineer.",
    "input": "Review this retry design and propose a safe implementation plan.",
    "reasoning": { "effort": "high", "summary": "auto" },
    "text": { "verbosity": "medium" },
    "max_output_tokens": 4096,
    "store": true
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format.

Request body

string

required

AnyFast model ID. Use gpt-6-astra.

string | object[]

required

Text or an ordered list of message, image, file, and tool-result items.

string

System or developer instructions inserted into the model context.

object

Reasoning configuration.

string

low, medium, high, xhigh, or max. none and minimal are not supported.

string

auto, concise, or detailed.

string

auto, current_turn, or all_turns.

string

Use standard. The current AnyFast route does not expose GPT-6 Astra Pro mode.

integer

Maximum visible-output and reasoning tokens. Maximum: 128000.

string

low, medium, or high.

string[]

Additional response data. Use reasoning.encrypted_content for encrypted reasoning items. Do not use message.output_text.logprobs.

string

Stable key that improves cache matching for related requests.

object

Prompt-cache options. mode selects implicit or explicit breakpoints; ttl currently supports 30m; comparison_response_id requests comparison diagnostics.

string

implicit or explicit.

string

default:"30m"

Currently only 30m is supported.

object

Marks an explicit reusable-prefix boundary. Use { "mode": "explicit" }.

object

Application-defined string key-value pairs.

boolean

default:false

Stream response events over SSE.

boolean

Controls event obfuscation for streaming responses.

boolean

default:true

Controls upstream response storage. AnyFast does not expose response retrieval.

string

default:"disabled"

Use disabled on the current AnyFast route.

Do not send temperature, top_p, or top_logprobs. GPT-6 Astra also does not support message.output_text.logprobs in include.

AnyFast does not expose Responses retrieval, Conversations, or Vector Stores management. Do not use background, conversation, previous_response_id, stored prompt references, or configuration_update.

Response

200

{
  "id": "resp_01astraexample",
  "object": "response",
  "created_at": 1788460800,
  "completed_at": 1788460802,
  "model": "gpt-6-astra",
  "status": "completed",
  "output": [
    { "id": "rs_01reasoning", "type": "reasoning", "summary": [] },
    {
      "id": "msg_01astraexample",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [{
        "type": "output_text",
        "text": "Use bounded exponential backoff, idempotency keys, and a single retry owner.",
        "annotations": []
      }]
    }
  ],
  "output_text": "Use bounded exponential backoff, idempotency keys, and a single retry owner.",
  "usage": {
    "input_tokens": 38,
    "input_tokens_details": { "cached_tokens": 0, "cache_write_tokens": 0 },
    "output_tokens": 124,
    "output_tokens_details": { "reasoning_tokens": 82 },
    "total_tokens": 162
  },
  "error": null,
  "incomplete_details": null
}

string

Response ID.

string

Always response.

string

queued, in_progress, completed, incomplete, failed, or cancelled.

object[]

Ordered reasoning, message, and tool-call output items.

string

Convenience aggregation of text output when available.

object

Input, output, cached, cache-write, and reasoning token usage.

object | null

Why a response ended incomplete.

object | null

Error details for a failed response.

Create response

POST /v1/responses

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6-astra",
    "input": [{
      "role": "user",
      "content": [
        { "type": "input_text", "text": "Compare the diagram with the deployment notes and list conflicts." },
        { "type": "input_image", "image_url": "data:image/png;base64,<BASE64_IMAGE_DATA>", "detail": "high" },
        { "type": "input_file", "filename": "deployment-notes.pdf", "file_data": "data:application/pdf;base64,<BASE64_PDF_DATA>" }
      ]
    }],
    "reasoning": { "effort": "high" }
  }'

Request body

string

required

Use gpt-6-astra.

object[]

required

Ordered Responses API input items.

string

required

user, assistant, system, or developer.

string | object[]

required

Text, image, or file content parts.

string

required

input_text, input_image, or input_file.

string

Text for an input_text part.

string

Public URL or data URL for an input_image part.

string

auto, low, or high.

string

Filename for inline file data.

string

Data URL containing Base64-encoded inline file data.

Public image URLs must allow server-side downloads. Data URLs and inline files are supported. Audio and video are not supported GPT-6 Astra input modalities.

Response

200

{
  "id": "resp_01visionexample",
  "object": "response",
  "model": "gpt-6-astra",
  "status": "completed",
  "output": [{
    "id": "msg_01visionexample",
    "type": "message",
    "status": "completed",
    "role": "assistant",
    "content": [{
      "type": "output_text",
      "text": "The diagram uses two retry owners, while the notes require one.",
      "annotations": []
    }]
  }],
  "usage": { "input_tokens": 842, "output_tokens": 67, "total_tokens": 909 }
}

string

Output item type, such as message or reasoning.

string

Content type, such as output_text.

string

Generated text.

object[]

Citations and annotations when present.

Create response

POST /v1/responses

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6-astra",
    "input": "Classify the deployment risk.",
    "text": {
      "format": {
        "type": "json_schema",
        "name": "deployment_risk",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {
            "risk": { "type": "string", "enum": ["low", "medium", "high"] },
            "reason": { "type": "string" }
          },
          "required": ["risk", "reason"],
          "additionalProperties": false
        }
      }
    }
  }'

Request body

string

required

Use gpt-6-astra.

string | object[]

required

Prompt and optional context.

string

required

Use json_schema or text.

string

Schema name.

string

Description of the expected output.

object

required

JSON Schema that defines the response.

boolean

Enforce strict schema adherence.

Response

200

{
  "id": "resp_01structuredexample",
  "object": "response",
  "model": "gpt-6-astra",
  "status": "completed",
  "output": [{
    "id": "msg_01structuredexample",
    "type": "message",
    "status": "completed",
    "role": "assistant",
    "content": [{
      "type": "output_text",
      "text": "{\"risk\":\"medium\",\"reason\":\"Retries are not idempotent.\"}",
      "annotations": []
    }]
  }]
}

string

JSON text that conforms to the supplied schema.

Create response

POST /v1/responses

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/responses \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6-astra",
    "input": "Check the deployment status for service api-gateway.",
    "tools": [{
      "type": "function",
      "name": "get_deployment_status",
      "description": "Return the current deployment status for a service.",
      "parameters": {
        "type": "object",
        "properties": { "service": { "type": "string" } },
        "required": ["service"],
        "additionalProperties": false
      },
      "strict": true,
      "async": true
    }],
    "tool_choice": "auto",
    "parallel_tool_calls": true,
    "max_tool_calls": 4
  }'

Request body

string

required

Use gpt-6-astra. Tool calling requires the Responses API.

object[]

required

Function, custom, or supported built-in tool definitions.

string

required

function, custom, web_search, code_interpreter, shell, apply_patch, computer, or mcp.

string

Function or custom-tool name.

string

When and how to use the tool.

object

JSON Schema for function arguments.

boolean

Strict function-argument validation.

boolean

Allow independent work while your application runs a function or custom tool.

string[]

Use direct for direct model tool calls.

object

Optional JSON Schema for Function output.

string

Web Search context size, such as low.

string[]

Domains allowed for Web Search.

object

Code Interpreter container configuration. Use { "type": "auto" }; memory_limit is supported.

object

Shell environment configuration. Use { "type": "container_auto" }; memory_limit is supported.

string

Label for an MCP server.

string

HTTPS endpoint for an MCP server.

string | object

MCP approval policy, such as never.

string | object

none, auto, or a forced-tool object.

boolean

Allow multiple tool calls in one turn.

integer

Maximum total built-in tool calls.

string[]

Tool details to return, such as web_search_call.action.sources or code_interpreter_call.outputs.

Your application executes Function and Custom Tool calls. File Search requires a Vector Store created in the same upstream resource, but AnyFast does not currently expose the Vector Stores management endpoint.

Tool-call response

200

{
  "id": "resp_01toolexample",
  "object": "response",
  "model": "gpt-6-astra",
  "status": "completed",
  "output": [{
    "id": "fc_01deployment",
    "type": "function_call",
    "call_id": "call_01deployment",
    "name": "get_deployment_status",
    "arguments": "{\"service\":\"api-gateway\"}",
    "status": "completed",
    "async": true
  }]
}

string

function_call for this workflow.

string

Tool-call correlation ID.

string

Function name.

string

JSON-encoded arguments.

boolean

Whether the call can complete asynchronously.

Do not rely on cross-request response or tool-item references. Requests routed to different upstream resources can reject those references.

Create text completion

POST /v1/chat/completions

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/chat/completions \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6-astra",
    "messages": [{ "role": "user", "content": "Return a concise deployment checklist." }],
    "reasoning_effort": "low",
    "max_completion_tokens": 1024
  }'

Request body

string

required

Use gpt-6-astra.

object[]

required

Ordered Chat Completions messages.

string

required

Message role.

string

required

Text message content.

string

low, medium, high, xhigh, or max.

integer

Maximum completion and reasoning tokens.

Use Chat Completions for text requests only. GPT-6 Astra tool calling requires Responses API. Do not send temperature, top_p, top_logprobs, or logprobs.

Response

string

Chat completion ID.

string

Generated text.

string

Why generation stopped.

object

Prompt, completion, and total token usage.

Common errors

error

Invalid input, unsupported reasoning or sampling parameter, incompatible state fields, or invalid tool/schema configuration.

error

Missing or invalid API key.

error

Rate or quota limit reached.

Overview

Native Compatible Endpoints

Model APIs

Create response

Request headers

Request body

Response

Create response

Request body

Response

Create response

Request body

Response

Create response

Request body

Tool-call response

Create text completion

Request body

Response

Common errors

Official references

​Create response

​Request headers

​Request body

​Response

​Create response

​Request body

​Response

​Create response

​Request body

​Response

​Create response

​Request body

​Tool-call response

​Create text completion

​Request body

​Response

​Common errors

​Official references

Create response

Request headers

Request body

Response

Create response

Request body

Response

Create response

Request body

Response

Create response

Request body

Tool-call response

Create text completion

Request body

Response

Common errors

Official references