Name: GPT-5 Nano API: Fast, Low-Cost LLM by OpenAI
Brand: magicapi
SKU: api-magicapi-fast-language-generation-api-openai-gpt-5-nano
Availability: InStock
Author: API Market

Shashank Agarwal

# ⚡ Fast LLM API (OpenAI GPT-5 Nano)

## Overview
GPT-5 Nano is a language model from OpenAI, which describes it as its fastest, most cost-effective GPT-5 model.

Send a `prompt` (with an optional `system_prompt`), or a whole conversation in `messages`. You can add images in `image_input`. `reasoning_effort` controls how much the model reasons before answering, `verbosity` controls how long the answer is, and `max_completion_tokens` caps the number of tokens generated.

## Features
- **Prompt or messages**: send a single `prompt`, or a list of messages such as `[{"role": "user", "content": "Hello, how are you?"}]` in `messages`. When `messages` is set, `prompt` and `system_prompt` are ignored.
- **Image input**: pass image URLs in `image_input`.
- **Reasoning effort**: `minimal` (default), `low`, `medium` or `high`. `minimal` returns answers faster without extensive reasoning first.
- **Verbosity**: `low`, `medium` (default) or `high` for short or more comprehensive answers.
- **Completion cap**: `max_completion_tokens` limits the tokens generated.

## Use Cases
1. **High-volume text tasks**: classification, extraction, tagging and short answers where speed and cost matter.
2. **Chat features**: send the conversation so far in `messages`.
3. **Image questions**: describe or answer questions about images sent in `image_input`.
4. **Explanations**: concise or detailed explanations, controlled with `verbosity`.

## Visual Examples
### Example Input
Prompt: "Explain Bernoulli's principle"

Settings: `reasoning_effort` `minimal`, `verbosity` `medium`, empty `messages` and `image_input`.

### Example Output
The chunks of this run joined into one answer:

````markdown
Bernoulli's principle (or Bernoulli’s equation) is a statement about how the speed of a fluid, the pressure it exerts, and its height (potential energy) are related along a streamline in steady, incompressible, non-viscous flow. In simplest terms:

- Where a fluid flows faster, its pressure is lower.
- Where a fluid flows slower, its pressure is higher.

Key ideas:

1. Conservation of energy for a fluid element: As a fluid particle moves along a streamline, its energy consists of:
   - Kinetic energy from its speed (½ρv^2, where ρ is fluid density and v is velocity)
   - Pressure energy (p)
   - Potential energy from height (ρgh)

   Bernoulli’s equation along a streamline (for incompressible, non-viscous flow with constant height reference) is:
   p + ½ρv^2 + ρgh = constant

2. Intuition: If the fluid speeds up, it has more kinetic energy. To keep the total energy constant, the pressure term must decrease.

3. Common everyday manifestations:
   - Air over a wing: The curved upper surface causes air to move faster over the top, lowering pressure and producing lift.
   - Venturi effect: A constricted pipe speeds up the fluid, lowering pressure in the throat.
   - Ping-pong ball in a curved air stream: Air jets can keep the ball suspended if the surrounding pressure is lower in the fast stream region.

Important caveats and limits:
- Bernoulli’s principle applies along a streamline for steady, incompressible, inviscid (nearly zero viscosity) flow. Real fluids have viscosity, can be compressible (gas at high speed), and flows can be unsteady.
- It does not by itself explain all lift phenomena; separation, viscosity, and boundary layer effects matter in real wings. Nevertheless, Bernoulli’s concept of speed-pressure trade-off is foundational for understanding many flow phenomena.

Simple takeaway:
- Faster-moving fluid → lower pressure.
- Slower-moving fluid → higher pressure.

If you’d like, I can illustrate with a quick example or diagram, or derive Bernoulli’s equation from energy conservation.
````

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | none |  | The prompt to send to the model. Do not use if using `messages`. |
| `system_prompt` | string | No | none |  | System prompt to set the assistant's behavior |
| `messages` | array of objects | No | `[]` |  | A list of messages, for example `[{"role": "user", "content": "Hello, how are you?"}]`. If provided, `prompt` and `system_prompt` are ignored. |
| `image_input` | array of strings (URLs) | No | `[]` |  | List of image URLs to send to the model |
| `reasoning_effort` | string | No | `minimal` | `minimal`, `low`, `medium`, `high` | Constrains effort on reasoning. `minimal` gets answers back faster without extensive reasoning first. Lower effort means faster responses and fewer tokens used on reasoning. For higher efforts you may need to increase `max_completion_tokens` to avoid empty responses (where all the tokens are used on reasoning). |
| `verbosity` | string | No | `medium` | `low`, `medium`, `high` | Constrains the verbosity of the response. Lower values give more concise responses, higher values more verbose ones. |
| `max_completion_tokens` | integer | No | none |  | Maximum number of completion tokens to generate. For higher reasoning efforts you may need to increase it to avoid empty responses (where all the tokens are used on reasoning). |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.001 per API unit.
- **1 API unit = 1,000 weighted tokens**; an output token counts 1, an input token counts 0.125.
- That is **$0.125 per million input tokens** and **$1 per million output tokens**.
- Each request is rounded up to a whole API unit, so the smallest charge per request is $0.001.
- **Example cost**: the request above used 12 input tokens and 474 output tokens. 12 x 0.125 + 474 = 475.5 weighted tokens, rounded up to 1 API unit = **$0.001**.
- **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/fast-language-generation-api-openai-gpt-5-nano`

### 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/fast-language-generation-api-openai-gpt-5-nano/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "openai/gpt-5-nano",
    "input": {
      "prompt": "Explain Bernoulli'\''s principle",
      "messages": [],
      "verbosity": "medium",
      "image_input": [],
      "reasoning_effort": "minimal"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "60p9srsmwdrmr0d1c6tbt6ckd8",
  "version": "openai/gpt-5-nano",
  "status": "starting",
  "created_at": "2026-10-22T03:42:42.608Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/fast-language-generation-api-openai-gpt-5-nano/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "60p9srsmwdrmr0d1c6tbt6ckd8",
  "status": "succeeded",
  "output": [
    "Bernoulli's principle (or Bernoulli’s equation) is a statement about how the speed of a fluid, the pressure it exerts, and its height (potential energy) are related along a streamline in steady, incompressible, non-viscous flow. In simplest terms:\n\n- Where a fluid flows faster, its pressure is lower.\n- Where a fluid flows slower, its pressure is higher.\n\nKey ideas:\n\n1. Conservation of energy for a fluid element: As a fluid particle moves along a streamline, its energy consists of:\n   - Kinetic energy from its speed (½ρv^2, where ρ is fluid density and v is velocity)\n   - Pressure energy (p)\n   - Potential energy from height (ρgh)\n\n   Bernoulli’s equation along a streamline (for incompressible, non-viscous flow with constant height reference) is:\n   p + ½ρv^2 + ρgh = constant\n\n2. Intuition: If the fluid speeds up, it has more kinetic energy. To keep the total energy constant, the pressure term must decrease.\n\n3. Common everyday manifestations:\n   - Air over a wing: The curved upper surface causes air to move faster over the top, lowering pressure and producing lift.\n   - Venturi effect: A constricted pipe speeds up the fluid, lowering pressure in the throat.\n   - Ping-pong ball in a curved air stream: Air jets can keep the ball suspended if the surrounding pressure is lower in the fast stream region.\n\nImportant caveats and limits:\n- Bernoulli’s principle applies along a streamline for steady, incompressible, inviscid (nearly zero viscosity) flow. Real fluids have viscosity, can be compressible (gas at high speed), and flows can be unsteady.\n- It does not by itself explain all lift phenomena; separation, viscosity, and boundary layer effects matter in real wings. Nevertheless, Bernoulli’s concept of speed-pressure trade-off is foundational for understanding many flow phenomena.\n\nSimple takeaway:\n- Faster-moving fluid → lower pressure.\n- Slower-moving fluid → higher pressure.\n\nIf you’d like, I can illustrate with a quick example or diagram, or derive Bernoulli’s equation from energy conservation."
  ],
  "error": null,
  "created_at": "2026-10-22T03:42:42.608Z",
  "started_at": "2026-10-22T03:42:42.615Z",
  "completed_at": "2026-10-22T03:42:46.612Z"
}
```

`output` is an array of text chunks. Join them in order to get the full answer. The example above shows the chunks from this run already joined into one string.

### 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 `reasoning_effort` or `verbosity` value that is not in the list.
- **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/fast-language-generation-api-openai-gpt-5-nano";

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: "openai/gpt-5-nano", 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.join("");
    }

    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": "Explain Bernoulli's principle",
    "messages": [],
    "verbosity": "medium",
    "image_input": [],
    "reasoning_effort": "minimal"
  }).then((output) => console.log(output));
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/fast-language-generation-api-openai-gpt-5-nano"

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": "openai/gpt-5-nano", "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 "".join(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")

print(create_and_wait_for_prediction({
    "prompt": "Explain Bernoulli's principle",
    "messages": [],
    "verbosity": "medium",
    "image_input": [],
    "reasoning_effort": "minimal"
}))
```

## FAQ
- **Should I use `prompt` or `messages`?**
  - Use `prompt` (and optionally `system_prompt`) for single questions. Use `messages` to send a conversation; when `messages` is set, `prompt` and `system_prompt` are ignored.
- **Why did I get an empty answer?**
  - At higher `reasoning_effort` values all of `max_completion_tokens` can be used on reasoning. Raise `max_completion_tokens` or lower `reasoning_effort`.
- **Can I send images?**
  - Yes. Put image URLs in `image_input`.
- **How do I get shorter answers?**
  - Set `verbosity` to `low`.
- **How is a request billed?**
  - By weighted tokens: input tokens count 0.125 and output tokens count 1, at $0.001 per 1,000 weighted tokens, rounded up to a whole unit per request.
- **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`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## 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 OpenAI GPT-5 Nano with a prompt or a message list, plus optional images, for fast and low-cost text answers. Pay per token, no monthly fee.