Kimi K2.6
Intelligence
23.57
#164 of 520 models
Output speed
36.8 tok/s
Measured generation rate
Cost / index task
—
Measured evaluation workload
End-to-end latency
17ms
First answer 3ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
8 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
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
- $0.950
- Output / 1M
- $4.00
- Cache read / 1M
- $0.160
- Cache write / 1M
- —
- Cache-hit discount
- 83.2%
Response & usage
- Output speed
- 36.8 tok/s
- First chunk
- 3ms
- First answer
- 3ms
- Output / task
- —
- Reasoning / task
- —
Evaluation workload
- Canonical input
- —
- Canonical output
- —
- Answer / task
- —
- Index time / task
- —
- Run cost
- —
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Long | 36.8 tok/s | 3ms | 3ms | 17ms |
04 / Access
License & availability
Recorded license
Modified MIT
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Commercial License
- Reasoning
- No
Routing and providers
- OpenRouter ID
- moonshotai/kimi-k2.6
- Tokenizer
- Other
- Instruct type
- —
- Captured endpoints
- 21
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Baidu | fp4 | 262.1k | — |
| Inceptron | int4 | 262.1k | — |
| Chutes | int4 | 262.1k | — |
| DigitalOcean | unknown | 262.1k | — |
| Decart | fp4 | 262.1k | — |
| StreamLake | fp8 | 256k | — |
| CoreWeave | fp4 | 262.1k | — |
| Crusoe | bf16 | 262.1k | — |
| DeepInfra | fp4 | 262.1k | — |
| Venice | int4 | 256k | — |
| Parasail | int4 | 262.1k | — |
| SiliconFlow | fp8 | 262.1k | — |
| Novita | unknown | 262.1k | — |
| GMICloud | fp8 | 262.1k | — |
| AtlasCloud | int4 | 262.1k | — |
| Cloudflare | unknown | 262.1k | — |
| Moonshot AI | int4 | 262.1k | — |
| Phala | unknown | 262.1k | — |
| BaseTen | fp4 | 262k | — |
| Fireworks | unknown | 262.1k | — |
| BaseTen | fp4 | 262k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.