Claude Sonnet 5 Serverless API

Agentic coding, debugging and reasoning with 1M-token context.

PlaygroundHistory
API
Pricing
~5.50s

API Format: Anthropic Claude

This model uses Anthropic Claude request/response format.

POST /v2/claude-sonnet-5 · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5payload = {
 6    "instruction": "You are a helpful assistant.",
 7    "messages": [
 8        {
 9            "role": "user",
10            "content": [
11                {
12                    "type": "text",
13                    "text": "What's in this image?"
14                },
15                {
16                    "type": "image",
17                    "source": {
18                        "type": "base64",
19                        "media_type": "image/jpeg",
20                        "data": "iVBORw0KGgoAAAANSUhEUgA..."
21                    }
22                }
23            ]
24        }
25    ]
26,
27    "response_format": {
28        "type": "json_schema",
29        "json_schema": {
30            "name": "answer",
31            "strict": True,
32            "schema": {
33                "type": "object",
34                "properties": {"answer": {"type": "string"}},
35                "required": ["answer"],
36                "additionalProperties": False
37            }
38        }
39    }
40}
41
42# Async chat (v2): submit to the queue, block until COMPLETED.
43reply = segmind.chat("claude-sonnet-5", **payload)
44print(reply.text)
45
46# --- Or get a handle (track request_id, control the poll cadence) ---
47job = segmind.submit_chat("claude-sonnet-5", **payload)
48print(job.request_id)                         # available immediately
49reply = job.wait(timeout=600)
50print(reply.text)

API Endpoint

POST https://api.segmind.com/v1/claude-sonnet-5

Parameters

messagesrequired
object[]

Array of message objects with role and content array. Images must be base64 encoded with media_type.

Array items:
rolerequired
string

Role of the message sender

Allowed values :
"user""assistant"
contentrequired
array

Array of content blocks (text or image)

instructionoptional
string

System instruction that guides the model's behavior (replaces system message).

response_formatoptional
object

Optional JSON Schema for structured output; list every property in required and set additionalProperties false (json_object unsupported). Use for machine-readable results, omit for plain text.

Response Format

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "I can see a beautiful sunset over the ocean with vibrant orange and pink hues in the sky."
    }
  ],
  "model": "claude-sonnet-5",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 56,
    "output_tokens": 31
  }
}

With response_format

The envelope is unchanged: your JSON arrives as a string in the same field, which you parse yourself. Structured outputs guide

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "{\"answer\":\"Paris\"}"
    }
  ],
  "model": "claude-sonnet-5",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 56,
    "output_tokens": 31
  }
}

Image Input Format

Important: Anthropic Claude Format

Images must be base64 encoded in the source.data field with media_type specified

This model supports vision capabilities. You can include images in your requests.

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/claude-sonnet-5

    Submit — returns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Poll — until COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid message format or parameters — including a response_format this model does not accept, or a json_schema sent without a schema object

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out