Muse Spark 1.1
Meta · released Jul 16, 2026
- Type
- Proprietary
- Input
- $1.25
- Output
- $4.25
- Cached
- $0.15
List price · per 1M tokens · Meta at 1M context · source ↗
Our take
Written Aug 3, 2026Muse Spark is Meta's hosted-only flagship that accepts text, images, files, audio and video in a single request of up to one million tokens. It scores well on live coding and creative-writing leaderboards, with stable pricing across its two providers.
Choose this for long-context multimodal work or coding and web development with measured quality scores. Use it when predictable pricing matters, or when you need confirmed throughput on Meta's own endpoint. Skip it if you want to self-host, need a cheaper output tier, or are routing through third-party hosts where speed is unverified.
The case for it
- Broad multimodal input: text, images, files, audio and video in one model.
- One-million-token request limit, matching the largest proprietary windows available.
- Strong measured coding performance, with Arena Code (WebDev) Elo 1535.9479 and Arena Coding Elo 1529.1558.
- Identical pricing across both tracked providers, so there is no arbitrage hunt.
The case against it
- Hosted only with no download option: weights are proprietary and the parameter count is undisclosed.
- Premium output pricing with no cheaper tier available across either provider.
- Overall Arena text score declined slightly in the latest measurement, falling 1.6583 points over three days.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)5th of 143 · 1489.7
CodingWriting and fixing code on its own
Arena Coding6th of 143 · 1529.2
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)16th of 36 · 0.008
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Muse Spark 1.1 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model16 scoresEvery figure we hold, from 16 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes Meta's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.25 in / $4.25 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.25 / $4.25 | 1M | not measured | Unknown | Unknown | Unknown |
| Meta | $1.25 / $4.25 | 1M | 90 tok/s | No | Yes30 days | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Meta | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file+audio+video->text
- Catalogue slug
- meta-muse-spark-1-1