← All models
Get an API key
Meta
meta-models/…
1 serving nowup to 128K context
Every Meta model we serve, with the numbers most providers leave out — the quantisation each endpoint actually runs at, measured first-token latency, and real uptime. Model ids are copyable: pass one straight to any OpenAI-compatible client.
Muse Glimmer is Meta's 30B dense vision-language model tuned for agent workloads: tool use, long-horizon tasks and failure recovery. It accepts text and image input, supports a 131K context window, tool calling and structured output, and carries a January 2026 knowledge cutoff. Built to run always-on agents; strong on settlement-style arithmetic and reliable tool selection.
- Parameters
- 31.8B
- Max context
- 128K
| Quantisation | Context | p50 TTFT | Throughput | Uptime | Input /M | Output /M | Cached in /M | Status |
|---|---|---|---|---|---|---|---|---|
| Undisclosed | 128K | — | — | 99.96% | $0.35 | $1.50 | — | live |
agentmultimodalvisiontool-usereasoning
Qwen
DeepSeek
Ornith
Infersia
Google
OpenAI
Thinking Machines Lab
xAI