> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/models/muse-glimmer-30b/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Muse Glimmer 30B

> Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.

![Muse Glimmer 30B](https://media.empiriolabs.ai/model-logos/muse-spark-1-1.png)

[Meta AI](/providers/meta) · Text Generation

`POST /v1/chat/completions`

Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.

## At a glance

| Field               | Value                                                                                                                                                  |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Model id            | `muse-glimmer-30b`                                                                                                                                     |
| Model release date  | 2026-08-10                                                                                                                                             |
| Input modalities    | Text, Image                                                                                                                                            |
| Output modalities   | Text                                                                                                                                                   |
| Context window      | 128K                                                                                                                                                   |
| Weight precision    | NVFP4 weights + FP8 KV                                                                                                                                 |
| Max output tokens   | 32,768                                                                                                                                                 |
| Features            | reasoning, vision, multimodal, function\_calling, json\_mode, cache                                                                                    |
| Native inference    | Yes                                                                                                                                                    |
| New                 | Yes                                                                                                                                                    |
| Structured output   | JSON Schema                                                                                                                                            |
| Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1/completions`, `POST /v1beta/models/muse-glimmer-30b:generateContent` |
| Alternate model ids | `meta/muse-glimmer-30b`, `muse-glimmer`, `meta-models/muse-glimmer-30b`                                                                                |

## Pricing

| Charge              | Spec                       | Rate                |
| ------------------- | -------------------------- | ------------------- |
| Input               | per 1M prompt tokens       | \$0.20 (was \$0.35) |
| Output              | per 1M generated tokens    | \$0.80 (was \$1.50) |
| Implicit cache read | per 1M cached input tokens | \$0.05              |
| Web Search (Linkup) | per call when invoked      | \$0.013             |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "muse-glimmer-30b", "messages": [{"role":"user","content":"Hello"}]}'
```

## Parameters

| Parameter            | Type    | Required | Default  | Description                                                                                                                                                                                                                                                                         |
| -------------------- | ------- | -------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `temperature`        | number  | no       | `1.0`    | Sampling temperature. 0 is deterministic and 2 is maximum randomness. · Range: 0 – 2                                                                                                                                                                                                |
| `top_p`              | number  | no       | `0.95`   | Nucleus sampling probability mass. Lower values make outputs more focused. · Range: 0 – 1                                                                                                                                                                                           |
| `max_tokens`         | number  | no       | `4096`   | Maximum output tokens. · Range: 1 – 32768                                                                                                                                                                                                                                           |
| `stop`               | string  | no       | -        | Up to 4 strings where the model will stop generating further tokens.                                                                                                                                                                                                                |
| `reasoning_effort`   | enum    | no       | `"high"` | Reasoning strength level. Higher levels think longer before answering. none requests minimal thinking and max maps to the model's xhigh strength. · Allowed: `none`, `low`, `medium`, `high`, `max`                                                                                 |
| `top_k`              | number  | no       | `64`     | Limit sampling to the top K candidate tokens when supported. · Range: 1 – 200                                                                                                                                                                                                       |
| `min_p`              | number  | no       | `0`      | Minimum probability threshold for token sampling. · Range: 0 – 1                                                                                                                                                                                                                    |
| `frequency_penalty`  | number  | no       | `0`      | Penalty based on how often a token has already appeared. · Range: -2 – 2                                                                                                                                                                                                            |
| `presence_penalty`   | number  | no       | `0`      | Penalty for tokens that already appeared in the generated text. · Range: -2 – 2                                                                                                                                                                                                     |
| `response_format`    | enum    | no       | -        | Constrain the output to valid JSON. Use JSON mode for any JSON object, or supply a JSON Schema to force an exact response shape. · Allowed: `text`, `json_object`, `json_schema`                                                                                                    |
| `web_search_linkup`  | boolean | no       | false    | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds \$0.013 per call when invoked on top of the model's normal token cost. Disabled by default. |
| `disable_formatting` | boolean | no       | false    | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another system that expects no decoration.                                                                              |

## Notes

Supports text and image input, streaming, function tools, structured JSON output, and reasoning strength control through reasoning\_effort (none, low, medium, high, max). Reasoning defaults to high.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/muse-glimmer-30b`.

> Meta open 30B agentic model with image understanding, 128K context, tool calling, structured output, and controllable reasoning strength.