Granite 4.2 3B
Intelligence
9.06
#370 of 520 models
Output speed
215 tok/s
Measured generation rate
Cost / index task
$0.006
Measured evaluation workload
End-to-end latency
12ms
First answer 10ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
20 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
- $0.030
- Output / 1M
- $0.120
- Cache read / 1M
- $0.0075
- Cache write / 1M
- —
- Cache-hit discount
- 75%
Response & usage
- Output speed
- 215 tok/s
- First chunk
- 0ms
- First answer
- 10ms
- Output / task
- 18.6k
- Reasoning / task
- 11.2k
Evaluation workload
- Canonical input
- 388.31M
- Canonical output
- 91.92M
- Answer / task
- 7.4k
- Index time / task
- 1.4m
- Run cost
- $14.856
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 222.7 tok/s | 0ms | 9ms | 11ms |
| Long | 215 tok/s | 0ms | 10ms | 12ms |
| Hundred K | 114.1 tok/s | 6ms | 23ms | 28ms |
| Medium Parallel | 179.7 tok/s | 0ms | 11ms | 14ms |
04 / Access
License & availability
Recorded license
Apache 2.0
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Permissive
- Reasoning
- Yes
Routing and providers
No reliable OpenRouter catalog match was captured for this model.
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.