Name: Claude Sonnet 4.5 API: Coding and Text Generation
Brand: magicapi
SKU: api-magicapi-code-generation-api-anthropic-claude-4-5-sonnet
Availability: InStock
Author: API Market

Shashank Agarwal

# 💻 Coding and Text Generation API (Anthropic Claude Sonnet 4.5)

## Overview
Claude Sonnet 4.5 is a large language model from Anthropic. Its developer describes it as its best coding model to date, with improvements across the whole development lifecycle.

Send a text `prompt`, an optional `system_prompt` and an optional `image`. The model returns its reply as a list of text chunks; join them in order to get the full text. You pay per token: input and output tokens are counted separately.

## Features
- **Code and text generation**: write, explain, review and refactor code, or answer questions and draft documents from one `prompt`.
- **System prompt**: set the model's role, tone or rules with `system_prompt` (default empty).
- **Image input**: pass one `image` URL and ask about it in `prompt`. An image counts as about (width x height) / 750 input tokens.
- **Image downscaling**: `max_image_resolution` (0.001 to 2 megapixels, default 0.5) shrinks the image before the model reads it, which lowers input tokens.
- **Long replies**: `max_tokens` sets the output limit from 1024 to 64000 tokens (default 8192).

## Use Cases
1. **Coding assistants**: generate functions, tests and refactors, or explain an unfamiliar codebase snippet.
2. **Code review**: paste a diff in `prompt` and ask for bugs and fixes.
3. **Screenshots and diagrams**: send an `image` of an error dialog, chart or architecture diagram and ask questions about it.
4. **Writing and analysis**: drafts, summaries and structured answers with formatting rules set in `system_prompt`.

## Visual Examples
### Example Input
Prompt: "Give me a recipe for pancakes that could feed all of California."

`max_tokens` was set to `1024`, `system_prompt` was empty and no image was sent (`max_image_resolution` `0.5`).

### Example Output
The output chunks joined in order (21 input tokens, 347 output tokens):

```text
# Pancakes for California (39 million people)

## Ingredients:
- **195 million eggs** (5 per person)
- **48.75 million cups flour** (1.25 cups per person)
- **39 million cups milk** (1 cup per person)
- **9.75 million tablespoons sugar** (¼ tbsp per person)
- **9.75 million tablespoons baking powder** (¼ tbsp per person)
- **4.875 million tablespoons salt** (⅛ tbsp per person)
- **9.75 million tablespoons melted butter** (¼ tbsp per person)

## Fun Facts About This Recipe:
- Those eggs would require about **1.6 billion chickens working for one day**
- The flour would weigh about **6.8 million tons**
- You'd need roughly **5 million gallons of milk**
- The batter would fill about **51 Olympic swimming pools**

## Cooking Logistics:
If every California household (13 million) made pancakes simultaneously, each would cook for about 3 people. Much more manageable!

---

*For a normal serving (4 people): 4 eggs, 1 cup flour, ¾ cup milk, 2 tbsp sugar, 2 tbsp baking powder, 1 tsp salt, 2 tbsp melted butter. Mix, cook on griddle, enjoy!*
```

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | The prompt to send to the model |
| `image` | string (URL) | No | none |  | Optional input image URL. An image counts as about (width px * height px) / 750 input tokens |
| `system_prompt` | string | No | `""` |  | System prompt that sets the model's behavior |
| `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. The image is scaled down to this size before the model reads it, which lowers input tokens and processing time |

## 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 works out to **$3.80 per million input tokens** and **$19 per million output tokens**.
- Each request is rounded up to a whole API unit. An input image counts as input tokens (about width x height / 750).
- **Example cost**: the example request used 21 input tokens and 347 output tokens: 21 x 0.2 + 347 = 351.2 weighted tokens, rounded up to 4 API units = **$0.0076**.
- **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/code-generation-api-anthropic-claude-4-5-sonnet`

### 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/code-generation-api-anthropic-claude-4-5-sonnet/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "anthropic/claude-4.5-sonnet",
    "input": {
      "prompt": "Give me a recipe for pancakes that could feed all of California.",
      "max_tokens": 1024,
      "system_prompt": "",
      "max_image_resolution": 0.5
    }
  }'
```

Response (201 Created):
```json
{
  "id": "1y7zp6d7e9rmw0d1c6qaz4n3b0",
  "version": "anthropic/claude-4.5-sonnet",
  "status": "starting",
  "created_at": "2026-10-22T03:36:38.922Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/code-generation-api-anthropic-claude-4-5-sonnet/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "1y7zp6d7e9rmw0d1c6qaz4n3b0",
  "status": "succeeded",
  "output": [
    "# Pancakes for California (39 million people)\n\n## Ingredients:\n- **195 million eggs** (5 per person)\n- **48.75 million cups flour** (1.25 cups per person)\n- **39 million cups milk** (1 cup per person)\n- **9.75 million tablespoons sugar** (¼ tbsp per person)\n- **9.75 million tablespoons baking powder** (¼ tbsp per person)\n- **4.875 million tablespoons salt** (⅛ tbsp per person)\n- **9.75 million tablespoons melted butter** (¼ tbsp per person)\n\n## Fun Facts About This Recipe:\n- Those eggs would require about **1.6 billion chickens working for one day**\n- The flour would weigh about **6.8 million tons**\n- You'd need roughly **5 million gallons of milk**\n- The batter would fill about **51 Olympic swimming pools**\n\n## Cooking Logistics:\nIf every California household (13 million) made pancakes simultaneously, each would cook for about 3 people. Much more manageable!\n\n---\n\n*For a normal serving (4 people): 4 eggs, 1 cup flour, ¾ cup milk, 2 tbsp sugar, 2 tbsp baking powder, 1 tsp salt, 2 tbsp melted butter. Mix, cook on griddle, enjoy!*"
  ],
  "error": null,
  "created_at": "2026-10-22T03:36:38.922Z",
  "started_at": "2026-10-22T03:36:39.922Z",
  "completed_at": "2026-10-22T03:36:48.000Z"
}
```

`output` is a list of text chunks. Join them in order to get the full reply. The example above shows the reply joined into one element; a real response usually splits it into many short chunks.

### 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 1024 or above 64000.
- **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/code-generation-api-anthropic-claude-4-5-sonnet";

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-4.5-sonnet", 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": "Give me a recipe for pancakes that could feed all of California.",
  "max_tokens": 1024,
  "system_prompt": "",
  "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/code-generation-api-anthropic-claude-4-5-sonnet"


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-4.5-sonnet", "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": "Give me a recipe for pancakes that could feed all of California.",
    "max_tokens": 1024,
    "system_prompt": "",
    "max_image_resolution": 0.5
})
print("".join(output))
```

## FAQ
- **How do I get the full reply text?**
  - `output` is an array of text chunks. Join them in order with no separator: `output.join("")` in JavaScript or `"".join(output)` in Python.
- **Does it support multi-turn chat?**
  - There is no messages field. Send earlier turns as text inside `prompt` and set the assistant's behavior with `system_prompt`.
- **How many images can I send?**
  - One. The `image` field takes a single URL. Lower `max_image_resolution` to cut the input tokens an image uses.
- **How much does a request cost?**
  - It depends on the tokens used: $3.80 per million input tokens and $19 per million output tokens, rounded up to a whole API unit ($0.0019) per request. The example request cost $0.0076.
- **Why did the reply stop early?**
  - The model stops when it reaches `max_tokens`. Raise it (up to 64000) for longer answers.
- **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.


Call Anthropic's Claude Sonnet 4.5 for coding, writing and image questions with a prompt, system prompt and optional image. Pay as you go, no monthly fee.