Muse Spark 1.2 (xhigh)
Intelligence
39.8
#57 of 520 models
Output speed
207.3 tok/s
Measured generation rate
Cost / index task
$0.975
Measured evaluation workload
End-to-end latency
24ms
First answer 22ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
23 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $1.25
- Output / 1M
- $4.25
- Cache read / 1M
- $0.150
- Cache write / 1M
- —
- Cache-hit discount
- 88%
Response & usage
- Output speed
- 207.3 tok/s
- First chunk
- 12ms
- First answer
- 22ms
- Output / task
- 47.9k
- Reasoning / task
- 22.7k
Evaluation workload
- Canonical input
- 3.61B
- Canonical output
- 125.54M
- Answer / task
- 25.2k
- Index time / task
- 4m
- Run cost
- $1,385.401
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 260.4 tok/s | 10ms | 18ms | 20ms |
| Long | 207.3 tok/s | 12ms | 22ms | 24ms |
| Hundred K | 323.7 tok/s | 14ms | 20ms | 22ms |
| Medium Parallel | 240.4 tok/s | 9ms | 18ms | 20ms |
04 / Access
License & availability
Recorded license
No license recorded
No direct license document is available in the captured record. Weight availability alone does not establish usage rights.
- Weight access
- Closed / unavailable
- Classification
- Proprietary
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- meta/muse-spark-1.2
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 1
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Meta | unknown | 1.05M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.