# Muse Spark 1.2

Canonical page: https://agentsky.dev/models/meta/muse-spark-1.2
JSON record: https://gateway.agentsky.dev/v1/models/meta/muse-spark-1.2

Muse Spark 1.2 is a text and image and audio and video and file-input model by Meta, available through the AgentSky API as meta/muse-spark-1.2 at $1.375 per million input tokens and $4.675 per million output tokens, with a 1M context window.

Standard-tier multimodal reasoning model with function tool calling.

## Facts

- **Model id:** `meta/muse-spark-1.2`
- **Maker:** Meta
- **Input modalities:** Text, Image, Audio, Video, File
- **Context:** 1M
- **Aliases:** `meta/muse-spark-1.2`, `muse-spark-1.2`

## Pricing

USD per million tokens on the default plan. Signed-in pages show your own plan's price; every response carries the cost of that call in `usage.cost`.

| Meter | Per 1M tokens |
|---|---|
| Input | $1.375 |
| Output | $4.675 |
| Cache read | $0.165 |
| Cache write | $1.375 |

## Use it

Anthropic wire base URL: `https://gateway.agentsky.dev`. OpenAI wire base URL: `https://gateway.agentsky.dev/v1`. Authenticate with an AgentSky API key (`ast_…`) and pass the model id.

### OpenAI SDK

```js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "meta/muse-spark-1.2",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response
```

### Codex

```bash
export OPENAI_BASE_URL="https://gateway.agentsky.dev/v1"
export OPENAI_API_KEY="$AGENTSKY_API_KEY"

codex --model meta/muse-spark-1.2
```

### OpenCode

```js
// opencode.json — then switch models any time with /models
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "agentsky": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AgentSky",
      "options": {
        "baseURL": "https://gateway.agentsky.dev/v1",
        "apiKey": "{env:AGENTSKY_API_KEY}"
      },
      "models": { "meta/muse-spark-1.2": {} }
    }
  }
}
```

## Run it with an agent

- [Hermes + Muse Spark 1.2](https://agentsky.dev/agents/hermes/with/muse-spark-1.2)
- [Claude Code + Muse Spark 1.2](https://agentsky.dev/agents/claude-code/with/muse-spark-1.2)
- [Codex + Muse Spark 1.2](https://agentsky.dev/agents/codex/with/muse-spark-1.2)
- [OpenClaw + Muse Spark 1.2](https://agentsky.dev/agents/openclaw/with/muse-spark-1.2)
- [pi + Muse Spark 1.2](https://agentsky.dev/agents/pi/with/muse-spark-1.2)
- [DeepSeek Harness + Muse Spark 1.2](https://agentsky.dev/agents/dsh/with/muse-spark-1.2)
- [Kimi Code + Muse Spark 1.2](https://agentsky.dev/agents/kimi-code/with/muse-spark-1.2)
- [OpenCode + Muse Spark 1.2](https://agentsky.dev/agents/opencode/with/muse-spark-1.2)
- [Muse Code + Muse Spark 1.2](https://agentsky.dev/agents/muse-code/with/muse-spark-1.2)

## Questions

### What is Muse Spark 1.2?

Muse Spark 1.2 is a model from Meta. Standard-tier multimodal reasoning model with function tool calling.

### How much does Muse Spark 1.2 cost?

$1.375 / $4.675 per million tokens at the prices shown, for input and output respectively. The exact price of every call comes back in the response as usage.cost, so you never have to compute it.

### What is the context length of Muse Spark 1.2?

1M tokens. These are the limits listed for this model in the current AgentSky catalog.

### Which clients can call Muse Spark 1.2?

Anything that speaks the OpenAI-compatible request format. Point the client's base URL at the gateway, use an AgentSky key, and pass meta/muse-spark-1.2 as the model.

### How do I name Muse Spark 1.2 in a request?

The gateway accepts meta/muse-spark-1.2, muse-spark-1.2. Any of them resolves to the same model, so an existing integration usually needs no change to its model string.

### Can Muse Spark 1.2 read images?

Yes. Its listed input types are text, image, audio, video, file. Include the image with your request; image input does not imply image generation.

### What output can Muse Spark 1.2 produce?

The listed output types are text. This model returns text. Producing image, video or audio files requires a suitable tool or another model; it is not included in text generation.

### How should I plan a long prompt for Muse Spark 1.2?

Plan your instructions, conversation history and source material around the 1M-token context limit, leaving room for the response. A larger window lets you supply more relevant material; it does not make unrelated content useful.

### What would 10,000 input tokens and 2,000 output tokens cost with Muse Spark 1.2?

At the displayed input and output rates, the model-token subtotal is $0.0231. This example assumes uncached input and excludes additional pricing categories, tool calls and agent runtime. Actual usage determines the final charge.

### How is cached input priced for Muse Spark 1.2?

The catalog lists $0.165 per million cache-read tokens. Cache writes are listed at $1.375 per million tokens. Repeating a prompt does not by itself guarantee a cache hit; only usage reported as cached receives that rate.

### Does the Muse Spark 1.2 token price cover an entire agent task?

No. The model price covers the model usage described above. A task can also incur tool and runtime charges, and several model calls may be needed to complete it. Compare total task usage when evaluating cost.

### How do I use Muse Spark 1.2 on AgentSky?

The composer above preselects Muse Spark 1.2 for a compatible agent. Enter a concrete task, select any tools or connectors it needs, and send. Sign in if prompted; paid execution requires available credits.