Mercury 2.5
Intelligence
12.34
#313 of 520 models
Output speed
677.2 tok/s
Measured generation rate
Cost / index task
$0.117
Measured evaluation workload
End-to-end latency
4ms
First answer 4ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
18 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
- $0.250
- Output / 1M
- $0.750
- Cache read / 1M
- $0.025
- Cache write / 1M
- —
- Cache-hit discount
- 90%
Response & usage
- Output speed
- 677.2 tok/s
- First chunk
- 4ms
- First answer
- 4ms
- Output / task
- 9.1k
- Reasoning / task
- 8.4k
Evaluation workload
- Canonical input
- 1.1B
- Canonical output
- 35.25M
- Answer / task
- 660
- Index time / task
- 13.2s
- Run cost
- $218.107
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 713.3 tok/s | 3ms | 3ms | 4ms |
| Long | 677.2 tok/s | 4ms | 4ms | 4ms |
| Hundred K | 5,198.3 tok/s | 5ms | 5ms | 5ms |
| Medium Parallel | 1,018.9 tok/s | 4ms | 4ms | 4ms |
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
- inception/mercury-2.5
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 1
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Inception | unknown | 260k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.