Agnes 2.5 Pro Alpha
Intelligence
27.8
#126 of 520 models
Output speed
168 tok/s
Measured generation rate
Cost / index task
—
Measured evaluation workload
End-to-end latency
19ms
First answer 16ms
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
- $0.450
- Output / 1M
- $0.900
- Cache read / 1M
- $0.010
- Cache write / 1M
- —
- Cache-hit discount
- 97.8%
Response & usage
- Output speed
- 168 tok/s
- First chunk
- 4ms
- First answer
- 16ms
- Output / task
- 78.1k
- Reasoning / task
- 56.6k
Evaluation workload
- Canonical input
- 3.78B
- Canonical output
- 163.8M
- Answer / task
- 21.4k
- Index time / task
- 7.3m
- Run cost
- —
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 181.9 tok/s | 3ms | 14ms | 16ms |
| Long | 168 tok/s | 4ms | 16ms | 19ms |
| Hundred K | 198 tok/s | 19ms | 30ms | 32ms |
| Medium Parallel | 139.5 tok/s | 2ms | 16ms | 20ms |
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.