Meta Models

3 modelsGeneral models from $1.375/M inputUp to 1.05M context

Usage

Last 30 days · 2026-09-03 to 2026-10-02

Tokens

2.5B

Requests

20.3K

Models in use

3 of 3

Tokens per day, stacked by model

0342M684M09-0309-1009-1709-2410-012026-09-03 — 684,062,080 tokens muse-spark-1.3: 682,894,540 muse-spark-1.2: 1,167,5402026-09-04 — 181,872,030 tokens muse-spark-1.3: 181,758,820 muse-spark-1.2: 113,2102026-09-05 — 34,848,820 tokens muse-spark-1.3: 34,848,8202026-09-06 — 7,291,715 tokens muse-spark-1.3: 7,291,585 muse-spark-1.2: 65 muse-spark-1.1: 652026-09-07 — 21,119,655 tokens muse-spark-1.3: 21,116,860 muse-spark-1.1: 1,665 muse-spark-1.2: 1,1302026-09-08 — 53,749,125 tokens muse-spark-1.3: 53,749,1252026-09-09 — 66,313,735 tokens muse-spark-1.3: 66,186,395 muse-spark-1.2: 127,3402026-09-10 — 55,044,445 tokens muse-spark-1.3: 54,927,780 muse-spark-1.1: 114,670 muse-spark-1.2: 1,9952026-09-11 — 9,592,115 tokens muse-spark-1.3: 9,592,1152026-09-12 — 15,267,105 tokens muse-spark-1.3: 15,260,305 muse-spark-1.2: 6,370 muse-spark-1.1: 4302026-09-13 — 11,956,840 tokens muse-spark-1.3: 11,946,640 muse-spark-1.2: 9,770 muse-spark-1.1: 4302026-09-14 — 47,615,090 tokens muse-spark-1.3: 47,576,650 muse-spark-1.1: 30,690 muse-spark-1.2: 7,7502026-09-15 — 90,795,720 tokens muse-spark-1.3: 90,795,7202026-09-16 — 56,141,000 tokens muse-spark-1.3: 56,132,010 muse-spark-1.2: 5,015 muse-spark-1.1: 3,9752026-09-17 — 83,531,725 tokens muse-spark-1.3: 83,530,595 muse-spark-1.2: 565 muse-spark-1.1: 5652026-09-18 — 36,320,910 tokens muse-spark-1.3: 36,294,210 muse-spark-1.2: 15,250 muse-spark-1.1: 11,4502026-09-19 — 30,831,970 tokens muse-spark-1.3: 30,831,570 muse-spark-1.2: 200 muse-spark-1.1: 2002026-09-20 — 49,510,605 tokens muse-spark-1.3: 49,510,6052026-09-21 — 309,939,890 tokens muse-spark-1.3: 309,920,680 muse-spark-1.2: 19,2102026-09-22 — 227,127,040 tokens muse-spark-1.3: 227,108,815 muse-spark-1.2: 9,510 muse-spark-1.1: 8,7152026-09-23 — 47,796,455 tokens muse-spark-1.3: 47,795,075 muse-spark-1.2: 690 muse-spark-1.1: 6902026-09-24 — 47,635,935 tokens muse-spark-1.3: 47,632,320 muse-spark-1.1: 1,935 muse-spark-1.2: 1,6802026-09-25 — 28,972,135 tokens muse-spark-1.3: 28,966,485 muse-spark-1.2: 2,845 muse-spark-1.1: 2,8052026-09-26 — 40,056,690 tokens muse-spark-1.3: 39,909,400 muse-spark-1.2: 146,860 muse-spark-1.1: 4302026-09-27 — 55,060,675 tokens muse-spark-1.3: 52,092,960 muse-spark-1.2: 2,967,035 muse-spark-1.1: 6802026-09-28 — 29,703,305 tokens muse-spark-1.3: 29,650,275 muse-spark-1.1: 51,180 muse-spark-1.2: 1,8502026-09-29 — 42,531,935 tokens muse-spark-1.3: 42,528,870 muse-spark-1.2: 1,705 muse-spark-1.1: 1,3602026-09-30 — 31,456,225 tokens muse-spark-1.3: 31,449,850 muse-spark-1.2: 3,265 muse-spark-1.1: 3,1102026-10-01 — 66,660,520 tokens muse-spark-1.3: 64,138,745 muse-spark-1.2: 2,520,695 muse-spark-1.1: 1,0802026-10-02 — 41,683,085 tokens muse-spark-1.3: 41,683,085
  • muse-spark-1.3
  • muse-spark-1.2
  • muse-spark-1.1

Which models that traffic went to

  1. Muse Spark 1.399.7%2.5B
  2. Muse Spark 1.20.3%7.1M
  3. Muse Spark 1.1<0.1%236K

Share of 2.5B 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, PDF, returns text.1.05M—$1.375$4.675/M———
muse-spark-1.2Takes text, vision, audio, video, PDF, returns text.1.05M—$1.375$4.675/M—108 tok/s14.25 s
muse-spark-1.3Takes text, vision, audio, video, PDF, returns text.1.05M1M$1.375$4.675/M$0.165/M69 tok/s6.27 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 muse-spark-1.3muse-spark-1.1 vs qwen3.8-max-previewkimi-k3 vs muse-spark-1.1glm-5.2 vs muse-spark-1.1

Meta on AIHubMix

Which Meta model should I start with?

muse-spark-1.1 at $1.375/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.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example muse-spark-1.3 bills cache hits at 12% 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
149 modelsOpenAI
142 modelsGoogle
87 modelsZ.AI
71 modelsLlama
53 models

Start calling Meta in one line

One key, one endpoint, 911 models across 42 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies