# Muse Glimmer 30B

> Meta Muse Glimmer 30B is a ~30B dense multimodal instruct model (text and image in, text out) with a 131K context window, chain-of-thought reasoning, and function calling. Available on NVIDIA NIM for chat and agent workflows.

**ID**: `meta/muse-glimmer-30b`  
**Creator**: meta  
**Category**: multimodal  
**Context**: 131K tokens  
**Input**: $0.35/M  
**Output**: $1.50/M  
**Released**: 2026-08-01  
**Web page**: https://anyrouter.dev/model/meta/muse-glimmer-30b

**Input modalities**: text, image  
**Output modalities**: text  

**Capabilities**: chat, streaming, function-calling, reasoning, vision, coding, agentic

**Supported parameters**: max_tokens, temperature, top_p, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs

**Aliases**: `nvidia/muse-glimmer-30b`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/muse-glimmer-30b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| nvidia | $0 | $0 |
| nvidia-byok | $0 | $0 |
| vercel-byok | $0 | $0 |

## Source

- Upstream docs: https://build.nvidia.com/meta/muse-glimmer-30b