AIHubMixAIHubMix

Meta Models

3 modelsGeneral models from $0.35/M inputUp to 1.05M context

Usage

Last 30 days · 2026-07-22 to 2026-08-20

Tokens

244M

Requests

11.1K

Models in use

3 of 3

Tokens per day, stacked by model

033.1M66.2M07-2207-2908-0508-1208-192026-07-22 — 489,975 tokens muse-spark-1.1: 489,9752026-07-23 — 922,895 tokens muse-spark-1.1: 922,8952026-07-24 — 3,817,845 tokens muse-spark-1.1: 3,817,8452026-07-25 — 1,049,085 tokens muse-spark-1.1: 1,049,0852026-07-26 — 434,230 tokens muse-spark-1.1: 434,2302026-07-27 — 2,906,145 tokens muse-spark-1.1: 2,906,1452026-07-28 — 1,168,945 tokens muse-spark-1.1: 1,168,9452026-07-29 — 716,915 tokens muse-spark-1.1: 716,9152026-07-30 — 5,472,840 tokens muse-spark-1.1: 5,472,8402026-07-31 — 11,534,625 tokens muse-spark-1.1: 11,534,6252026-08-01 — 2,222,995 tokens muse-spark-1.1: 2,222,9952026-08-02 — 72,710 tokens muse-spark-1.1: 72,7102026-08-03 — 2,232,285 tokens muse-spark-1.1: 2,232,2852026-08-04 — 15,780 tokens muse-spark-1.1: 15,7802026-08-05 — 211,900 tokens muse-spark-1.1: 211,9002026-08-06 — 4,966,540 tokens muse-spark-1.2: 4,296,540 muse-spark-1.1: 670,0002026-08-07 — 409,260 tokens muse-spark-1.2: 209,275 muse-spark-1.1: 199,9852026-08-08 — 1,346,100 tokens muse-spark-1.1: 1,291,630 muse-spark-1.2: 54,4702026-08-09 — 156,885 tokens muse-spark-1.2: 152,275 muse-spark-1.1: 4,6102026-08-10 — 7,403,175 tokens muse-spark-1.2: 4,707,045 muse-spark-1.1: 2,696,1302026-08-11 — 6,849,170 tokens muse-spark-1.2: 6,416,825 muse-spark-1.1: 432,3452026-08-12 — 1,839,035 tokens muse-spark-1.1: 1,444,405 muse-spark-1.2: 394,6302026-08-13 — 10,303,790 tokens muse-spark-1.2: 10,303,7902026-08-14 — 14,370,070 tokens muse-spark-1.2: 14,305,805 muse-spark-1.1: 52,290 muse-glimmer-30b: 11,9752026-08-15 — 4,437,425 tokens muse-spark-1.2: 4,427,780 muse-spark-1.1: 5,270 muse-glimmer-30b: 4,3752026-08-16 — 66,217,375 tokens muse-spark-1.2: 58,483,615 muse-glimmer-30b: 7,733,7602026-08-17 — 14,373,540 tokens muse-spark-1.2: 14,373,230 muse-spark-1.1: 3102026-08-18 — 45,814,345 tokens muse-spark-1.2: 45,797,170 muse-spark-1.1: 17,1752026-08-19 — 10,158,850 tokens muse-spark-1.2: 10,158,300 muse-spark-1.1: 5502026-08-20 — 22,450,370 tokens muse-spark-1.2: 22,445,830 muse-spark-1.1: 4,540
  • muse-spark-1.2
  • muse-spark-1.1
  • muse-glimmer-30b

Which models that traffic went to

  1. Muse Spark 1.280.4%197M
  2. Muse Spark 1.116.4%40.1M
  3. Muse Glimmer 30B3.2%7.8M

Share of 244M tokens.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 3 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 3 Meta Models

Open in model list
Meta models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
muse-spark-1.1Takes text, vision, audio, video, returns text.1.05M$1.38$4.67/M—122 tok/s7.75 s
muse-spark-1.2Takes text, vision, audio, video, returns text.1.05M$1.38$4.67/M—65 tok/s19.81 s
muse-glimmer-30bTakes text, vision, returns text.131K$0.35$1.50/M$0.04/M119 tok/s3.41 s

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

muse-glimmer-30b vs muse-spark-1.1muse-glimmer-30b vs muse-spark-1.2muse-glimmer-30b vs qwen3.8-max-previewkimi-k3 vs muse-glimmer-30bglm-5.2 vs muse-glimmer-30b

Meta on AIHubMix

Which Meta model should I start with?

muse-glimmer-30b at $0.35/M input — the cheapest entry here that declares tool calling, and it carries a 131K context. Move up to muse-spark-1.1 when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example muse-glimmer-30b bills cache hits at 11.43% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate Meta account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
141 modelsOpenAI
133 modelsGoogle
83 modelsZ.AI
66 modelsLlama
52 models

Start calling Meta in one line

One key, one endpoint, 859 models across 37 model authors.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect