Name: Claude Sonnet 4.6 API: Coding and Agent Planning LLM
Brand: magicapi
SKU: api-magicapi-ai-agent-planning-anthropic-claude-sonnet-4-6
Availability: InStock
Author: API Market

Shashank Agarwal

# 🤖 Coding and Agent Planning LLM API (Anthropic Claude Sonnet 4.6)

## Overview
Claude Sonnet 4.6 is a large language model from Anthropic. Its developer describes it as a full upgrade to coding, computer use, long-context reasoning, agent planning, knowledge work and design.

Send a text `prompt`, an optional `system_prompt` and an optional `image`. The model returns its answer as a list of text chunks; join them to get the full response. `max_tokens` allows answers of up to 64,000 tokens (minimum 1,024, default 8,192).

## Features
- **Text and image input**: ask about one optional `image` together with the `prompt`.
- **System prompt**: set the assistant's role, tone or rules with `system_prompt`.
- **Long answers**: `max_tokens` from 1,024 to 64,000 (default 8,192).
- **Image cost control**: `max_image_resolution` (0.001 to 2 megapixels, default 0.5) scales the image down before it is sent to the model, which lowers its input token count.
- **Token pricing**: you pay for the input and output tokens each request uses.

## Use Cases
1. **Coding help**: write functions, tests and refactors, or explain existing code.
2. **Agent planning**: break a task into steps for an agent you run.
3. **Image analysis**: describe screenshots, diagrams, charts or photos and answer questions about them.
4. **Knowledge work**: summaries, reports and structured answers from long inputs.

## Visual Examples
### Example Input
A coding request with a system prompt. No image was sent; `max_tokens` and `max_image_resolution` were at their defaults (8,192 and 0.5).

```json
{
  "prompt": "Write a Python function `merge_intervals(intervals)` that takes a list of [start, end] integer intervals and returns the list of merged, non-overlapping intervals in sorted order. Include a short docstring with a usage example, and use only the standard library.",
  "max_tokens": 8192,
  "system_prompt": "You are an experienced Python engineer",
  "max_image_resolution": 0.5
}
```

### Example Output
The model returned a Python function with a docstring, a self-test block and a short explanation table (934 output tokens). An excerpt of the joined output:

````markdown
```python
def merge_intervals(intervals):
    """
    Merge all overlapping intervals and return a sorted list of
    non-overlapping intervals.
    [...]
    """
    if not intervals:
        return []

    # Sort by the start of each interval
    sorted_intervals = sorted(intervals, key=lambda x: x[0])

    merged = [sorted_intervals[0][:]]  # Copy the first interval

    for current_start, current_end in sorted_intervals[1:]:
        last_start, last_end = merged[-1]

        if current_start <= last_end:
            # Overlapping or touching: extend the last interval if needed
            merged[-1][1] = max(last_end, current_end)
        else:
            # No overlap: start a new interval
            merged.append([current_start, current_end])

    return merged
```

[...]

**Time complexity:** O(n log n) - dominated by the sort.
**Space complexity:** O(n) for the output list.
````

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Input prompt |
| `image` | string (URL) | No | none |  | Optional input image. Images are priced as (width px * height px)/750 input tokens |
| `system_prompt` | string | No | `""` |  | System prompt |
| `max_tokens` | integer | No | `8192` | 1024 to 64000 | Maximum number of output tokens |
| `max_image_resolution` | number | No | `0.5` | 0.001 to 2 | Maximum image resolution in megapixels. Scales down image before sending it to Claude, to save time and money. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0019 per API unit.
- **1 API unit = 100 weighted tokens**; an output token counts 1, an input token counts 0.2.
- That is **$3.80 per million input tokens** and **$19.00 per million output tokens**.
- Each request's weighted token total is rounded up to a whole unit.
- **Example cost**: the example request used 71 input tokens and 934 output tokens: 71 x 0.2 + 934 = 948.2 weighted tokens, rounded up to 10 units = **$0.019**.
- An input image counts as input tokens: (width px x height px) / 750, after it is scaled down to `max_image_resolution`. At the default 0.5 megapixels that is about 667 input tokens.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/ai-agent-planning-anthropic-claude-sonnet-4-6`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/ai-agent-planning-anthropic-claude-sonnet-4-6/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "anthropic/claude-sonnet-4.6",
    "input": {
      "prompt": "Write a Python function `merge_intervals(intervals)` that takes a list of [start, end] integer intervals and returns the list of merged, non-overlapping intervals in sorted order. Include a short docstring with a usage example, and use only the standard library.",
      "max_tokens": 8192,
      "system_prompt": "You are an experienced Python engineer",
      "max_image_resolution": 0.5
    }
  }'
```

Response (201 Created):
```json
{
  "id": "9e8t7vcwahrmt0d1d0s91s8f78",
  "version": "anthropic/claude-sonnet-4.6",
  "status": "starting",
  "created_at": "2026-10-23T09:58:29.971Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/ai-agent-planning-anthropic-claude-sonnet-4-6/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "9e8t7vcwahrmt0d1d0s91s8f78",
  "status": "succeeded",
  "output": [
    "```",
    "python\ndef merge_intervals(",
    "intervals):\n    \"\"\"\n    ",
    "Merge all",
    " overl",
    "apping intervals",
    " and",
    " return a",
    " sorted",
    " list of",
    "\n    non-overlapping intervals.",
    "\n\n    Args:\n        intervals:",
    " A",
    " list of [start, end]",
    " integer pairs"
  ],
  "error": null,
  "created_at": "2026-10-23T09:58:29.971Z",
  "started_at": "2026-10-23T09:58:30.471Z",
  "completed_at": "2026-10-23T09:58:44.289Z"
}
```

`output` is a list of text chunks. Join them in order to get the full response. The example above is cut to its first 15 chunks; the full response had 256.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt` or a `max_tokens` value below 1,024.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/ai-agent-planning-anthropic-claude-sonnet-4-6";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "anthropic/claude-sonnet-4.6", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "prompt": "Write a Python function `merge_intervals(intervals)` that takes a list of [start, end] integer intervals and returns the list of merged, non-overlapping intervals in sorted order. Include a short docstring with a usage example, and use only the standard library.",
  "max_tokens": 8192,
  "system_prompt": "You are an experienced Python engineer",
  "max_image_resolution": 0.5
}).then((output) => console.log(output.join("")));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/ai-agent-planning-anthropic-claude-sonnet-4-6"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "anthropic/claude-sonnet-4.6", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


output = create_and_wait_for_prediction({
    "prompt": "Write a Python function `merge_intervals(intervals)` that takes a list of [start, end] integer intervals and returns the list of merged, non-overlapping intervals in sorted order. Include a short docstring with a usage example, and use only the standard library.",
    "max_tokens": 8192,
    "system_prompt": "You are an experienced Python engineer",
    "max_image_resolution": 0.5
})
print("".join(output))
```

## FAQ
- **How do I get the full answer text?**
  - Join the strings in `output` in order: `output.join("")` in JavaScript or `"".join(output)` in Python.
- **How much does an image add?**
  - Images are counted as input tokens: (width px x height px) / 750 after scaling to `max_image_resolution`. At the default 0.5 megapixels that is about 667 input tokens, about $0.0025 at the input token rate. Lower `max_image_resolution` to pay less.
- **Can I send more than one image?**
  - No. Each request takes one optional `image` URL.
- **Does the API keep conversation history?**
  - No. Each request is independent. To continue a conversation, include the earlier turns in `prompt`.
- **What did the example request cost?**
  - 10 API units, $0.019.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Use Anthropic's Claude Sonnet 4.6 for coding, agent planning, long-form reasoning and image analysis with one API key. Pay as you go, no monthly fee.