MiMo-V2.6-Pro
Intelligence
46.32
#30 of 520 models
Output speed
40.8 tok/s
Measured generation rate
Cost / index task
$0.133
Measured evaluation workload
End-to-end latency
65ms
First answer 53ms
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
- $0.435
- Output / 1M
- $0.870
- Cache read / 1M
- $0.0036
- Cache write / 1M
- —
- Cache-hit discount
- 99.2%
Response & usage
- Output speed
- 40.8 tok/s
- First chunk
- 4ms
- First answer
- 53ms
- Output / task
- 64.3k
- Reasoning / task
- 37.5k
Evaluation workload
- Canonical input
- 4.43B
- Canonical output
- 143.69M
- Answer / task
- 26.8k
- Index time / task
- 25.6m
- Run cost
- $206.655
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 42.9 tok/s | 3ms | 50ms | 61ms |
| Long | 40.8 tok/s | 4ms | 53ms | 65ms |
| Hundred K | 123.8 tok/s | 7ms | 23ms | 27ms |
| Medium Parallel | 56.1 tok/s | 3ms | 39ms | 48ms |
04 / Access
License & availability
Recorded license
MIT
No direct license document is available in the captured record. Weight availability alone does not establish usage rights.
- Weight access
- Open weights
- Classification
- Permissive
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- xiaomi/mimo-v2.6-pro
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 3
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| DeepInfra | fp8 | 1.05M | — |
| GMICloud | bf16 | 1.05M | — |
| Xiaomi | fp8 | 1.05M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.