AIHubMixAIHubMix

Meta Models

2 modelsGeneral models from $1.38/M inputUp to 1.05M context

Usage

Last 24 days · 2026-07-19 to 2026-08-11

Tokens

71.5M

Requests

2.5K

Models in use

2 of 2

Tokens per day

05.8M11.5M07-1907-2608-0208-092026-07-19 — 2,203,775 tokens2026-07-20 — 10,858,010 tokens2026-07-21 — 4,078,890 tokens2026-07-22 — 489,975 tokens2026-07-23 — 922,895 tokens2026-07-24 — 3,817,845 tokens2026-07-25 — 1,049,085 tokens2026-07-26 — 434,230 tokens2026-07-27 — 2,906,145 tokens2026-07-28 — 1,168,945 tokens2026-07-29 — 716,915 tokens2026-07-30 — 5,472,840 tokens2026-07-31 — 11,534,625 tokens2026-08-01 — 2,222,995 tokens2026-08-02 — 72,710 tokens2026-08-03 — 2,232,285 tokens2026-08-04 — 15,780 tokens2026-08-05 — 211,900 tokens2026-08-06 — 4,966,540 tokens2026-08-07 — 409,260 tokens2026-08-08 — 1,346,100 tokens2026-08-09 — 156,885 tokens2026-08-10 — 7,403,175 tokens2026-08-11 — 6,849,170 tokens

Which models that traffic went to

  1. muse-spark-1.177.9%55.7M
  2. muse-spark-1.222.1%15.8M

Share of 71.5M 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 24 days, counting the 2 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 2 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/M184 tok/s5.94 s
muse-spark-1.2Takes text, vision, audio, video, returns text.1.05M$1.38$4.67/M138 tok/s5.41 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-spark-1.1 vs muse-spark-1.2muse-spark-1.1 vs qwen3.8-max-previewkimi-k3 vs muse-spark-1.1glm-5.2 vs muse-spark-1.1grok-4.5 vs muse-spark-1.1

Meta on AIHubMix

Which Meta model should I start with?

muse-spark-1.1 at $1.38/M input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to muse-spark-1.2 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.

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 Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 models

Start calling Meta in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect