Kimi multimodal agent model for visual understanding, coding, and planning
1 figure withheld: the value failed a range check.
Specification
alibaba-cn listing
Context
262K
Max output
33K
Released
2026-01-27
Knowledge cutoff
2025-01
Retires
2027-01-26
Open weights
no
Input
text, image, video
Output
text
Price
US dollars per million tokens · alibaba-cn list price
Input
$0.574
Output
$2.411
Cache read
$0.10
Cache write
free
Quality
7 benchmarks · 2 sources
Composite
71st
percentile of 334 scored models
Rank
97 / 334
±0.06 sd
Evidence
7 × 2
3 or more benchmarks, from 2 or more sources
Effort range
3.0
points between effort settings
coding72nd1/3 bench
reasoning77th2/4 bench
math72nd3/7 bench
knowledge41st1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2 ±3.9 | default | Epoch AI | 2026-02-02 |
| GPQA diamond | 87.6 ±1.9 | default | Epoch AI | 2026-02-02 |
| SWE-Bench verified | 73.8 ±2.0 | default | Epoch AI | 2026-02-17 |
| ↳ | 70.8 | high · mini-SWE-agent | SWE-bench | — |
| Sources and settings disagree by 3.0 points. Both figures stand. | ||||
| FrontierMath-v1 | 27.9 ±2.6 | default | Epoch AI | 2026-02-03 |
| Chess Puzzles | 12.0 ±3.3 | default | Epoch AI | 2026-01-28 |
| FrontierMath-Tier-4-2025-07-01 | 4.2 ±2.9 | default | Epoch AI | 2026-02-02 |
| SimpleQA Verified | 34.3 ±1.5 | default | Epoch AI | 2026-08-27 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 61 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| alibaba-cnvendor | $0.574 | $2.411 | — | — | 262K | 33K | — |
| alibaba-coding-plan | free | free | free | free | 262K | 33K | — |
| alibaba-coding-plan-cn | free | free | free | free | 262K | 33K | — |
| alibaba-token-plan | free | free | free | free | 262K | 98K | — |
| alibaba-token-plan-cn | free | free | free | free | 262K | 98K | — |
| scnet-token-plan | free | free | free | — | 262K | 262K | — |
| tencent-coding-plan | free | free | free | free | 262K | 33K | — |
| nano-gpt · moonshotai | $0.30 | $1.90 | $0.15 | — | 256K | 66K | — |
| nano-gpt · thinking | $0.30 | $1.90 | $0.15 | — | 256K | 66K | — |
| llmgateway | $0.405 | $1.98 | $0.225 | — | 262K | 262K | — |
| llmgateway-providers · embercloud | $0.405 | $1.98 | $0.225 | — | 262K | 262K | — |
| deepinfra | $0.45 | $2.25 | $0.07 | — | 262K | — | — |
| deepinfra · moonshotai | $0.45 | $2.25 | $0.07 | — | 262K | 33K | — |
| edenai | $0.45 | $2.25 | $0.07 | — | 262K | 262K | — |
| meganova · moonshotai | $0.45 | $2.80 | — | — | 262K | 262K | — |
| openrouter | $0.45 | $2.25 | $0.07 | — | 262K | 262K | — |
| openrouter · moonshotai | $0.45 | $2.25 | $0.07 | — | 262K | 236K | — |
| siliconflow · moonshotai | $0.45 | $2.25 | $0.07 | — | 262K | 262K | — |
| siliconflow-cn · pro | $0.45 | $2.25 | $0.07 | — | 262K | 262K | — |
| cortecs | $0.495 | $2.768 | $0.124 | — | 262K | 262K | — |
| auriko | $0.50 | $2.80 | — | — | 262K | 262K | — |
| digitalocean | $0.50 | $2.70 | $0.203 | — | 262K | 262K | — |
| edenai · tensorx | $0.50 | $2.80 | $0.125 | — | 262K | 262K | — |
| tensorx · moonshotai | $0.50 | $2.80 | $0.125 | $0.625 | 262K | 262K | — |
| together_ai | $0.50 | $2.80 | — | — | 256K | — | 2026-05-21 |
| togetherai · moonshotai | $0.50 | $2.80 | — | — | 262K | 262K | — |
| hyper | $0.5344 | $2.815 | $0.2672 | — | 262K | 26K | — |
| venice | $0.56 | $3.50 | $0.22 | — | 256K | 66K | — |
| llmgateway-providers | $0.574 $0.60 | $3.011 $3.00 | $0.10 | — | 262K | 98K 33K | — |
| melious | $0.5796 | $2.956 | $0.1391 | — | 262K | 262K | — |
| zenmux · moonshotai | $0.58 | $3.02 | $0.10 | — | 262K | 64K | — |
| abacus | $0.60 | $3.00 | — | — | 262K | 33K | — |
| aihubmix | $0.60 | $3.00 | $0.10 | — | 262K | 33K | — |
| alibaba-cn · kimi | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| azure | $0.60 | $3.00 | — | — | 262K | 262K | — |
| azure_ai | $0.60 | $3.00 | $0.10 | — | 262K | 262K | 2027-01-26 |
| azure-cognitive-services | $0.60 | $3.00 | — | — | 262K | 262K | — |
| baseten | $0.60 | $3.00 | — | — | — | — | — |
| baseten · moonshotai | $0.60 | $3.00 | $0.12 | — | 262K | 262K | — |
| daoxe | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| fireworks_ai | $0.60 | $3.00 | $0.10 | — | 262K | 33K | — |
| frogbot | $0.60 | $3.00 | $0.10 | — | 256K | 128K | — |
| hpc-ai · moonshotai | $0.60 | $3.00 | $0.10 | — | 256K | 256K | — |
| huggingface · moonshotai | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| jalapeno | $0.60 | $3.00 | — | — | 262K | 180K | — |
| jiekou · moonshotai | $0.60 | $3.00 | — | — | 262K | 262K | — |
| kilo · moonshotai | $0.60 | $3.00 | $0.10 | — | 262K | 236K | — |
| merge-gateway | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| moonshot | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| novita | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| novita-ai · moonshotai | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| ofox · moonshotai | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| opencode | $0.60 | $3.00 | $0.08 | — | 262K | 66K | — |
| opencode-go | $0.60 | $3.00 | $0.10 | — | 262K | 66K | — |
| orcarouter · kimi | $0.60 | $3.00 | $0.10 | free | 262K | 33K | — |
| poe | $0.60 | $3.00 | $0.10 | — | 128K | 262K | — |
| vercel · moonshotai | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| wandb · wandb | $0.60 | $3.00 | $0.10 | — | 262K | 262K | — |
| 302ai | $0.66 | $3.30 | — | — | 262K | 262K | — |
| ollama-cloud | — | — | — | — | 262K | 262K | — |
| qiniu-ai · moonshotai | — | — | — | — | 256K | 256K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | llmgateway-providers | Cache read | $0.07 |
| 2026-09-07 | llmgateway-providers | Cache read | $0.10 |
| 2026-09-02 | openrouter | Cache read | $0.10 |
| 2026-09-06 | openrouter | Cache read | $0.07 |
| 2026-09-02 | hyper | Cache write | $0.2752 |
| 2026-09-02 | hyper | Cache write | $0.2642 |
| 2026-09-05 | hyper | Cache write | $0.2572 |
| 2026-09-08 | hyper | Cache write | $0.2792 |
| 2026-09-02 | hyper | Input | $0.5504 |
| 2026-09-02 | hyper | Input | $0.5284 |
| 2026-09-05 | hyper | Input | $0.5144 |
| 2026-09-08 | hyper | Input | $0.5584 |
| 2026-09-15 | hyper | Input | $0.5344 |
| 2026-09-02 | llmgateway-providers | Input | $0.45 |
| 2026-09-04 | llmgateway-providers | Input | $0.574 |
| 2026-09-07 | llmgateway-providers | Input | $0.574 |
| 2026-09-02 | openrouter | Input | $0.60 |
| 2026-09-06 | openrouter | Input | $0.45 |
| 2026-09-02 | hyper | Output | $2.885 |
| 2026-09-02 | hyper | Output | $2.785 |
| 2026-09-05 | hyper | Output | $2.755 |
| 2026-09-08 | hyper | Output | $2.935 |
| 2026-09-15 | hyper | Output | $2.815 |
| 2026-09-02 | llmgateway-providers | Output | $2.25 |
| 2026-09-04 | llmgateway-providers | Output | $3.011 |
| 2026-09-07 | llmgateway-providers | Output | $3.011 |
| 2026-09-02 | openrouter | Output | $3.00 |
| 2026-09-06 | openrouter | Output | $2.25 |
| 2026-09-11 | hyper | Cache read | $0.2792 |
| 2026-09-15 | hyper | Cache read | $0.2672 |
More from Alibaba
most-hosted first