Meta — pricing & performance
Models served
5
of 1,094 tracked models
Mean output speed
94
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
3.0s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$0.12
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Meta
Output tokens per second for all 5 models on Meta with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 5 of 5 models⇩
The Known Good
5 models on Meta
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Meta: Muse Spark 1.1
|
Meta | $1.25 | $4.25 | $2.00 | 97 | 2.5s | 1.05M |
|
Meta: Muse Spark 1.2
|
Meta | $1.25 | $4.25 | $2.00 | 84 | 1.7s | 1.05M |
|
Meta: Muse Spark 1.2 Contributor
|
Meta | $0.10 | $0.20 | $0.12 | 150 | 2.9s | 1.05M |
|
Meta: Muse Spark 1.3
|
Meta | $1.25 | $4.25 | $2.00 | 62 | 4.2s | 1.05M |
|
Meta: Muse Spark 1.3 Contributor
|
Meta | $0.10 | $0.20 | $0.12 | 77 | 3.6s | 1.05M |
The Known Good
Source. Prices, endpoint availability and throughput for Meta are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.