Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
Kimi K2.7 Code by moonshotai is offered by 62 providers on this page. Public prices are shown for 57 of them. Its official list price is $0.95 per 1M input tokens and $4.00 per 1M output tokens. The lowest paid channel is routing.run at $0.275 / $1.10 per 1M, about 4.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel and 4 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 25.8 on the Intelligence Index, with 60.8 for coding and 21 for agentic tasks. Against its lowest blended price of $0.481 per 1M, that is roughly 54 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 99 tokens per second, with 2.94s to the first token. Running one task of the Artificial Analysis suite costs about $0.5412, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 200,000 to 271,360, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | ||
| Volcengine Ark Coding Plan | Gateway | Subscription | $0 | — | 262,144 | 262,144 | ||
| SCNet Token Plan Kimi-K2.7-Code | Gateway | Subscription | $0 | — | 262,144 | 262,144 | ||
| Kenari kimi-k2-7-code | Gateway | Free | — | — | 262,144 | 262,144 | ||
| routing.run | Gateway | $0.28 | $1.10 | — | — | 200,000 ⚠ | 32,000 | |
| CrofAI | Gateway | $0.55 | $2.25 | $0.05 | — | 262,144 | 262,144 | |
| Cortecs | Gateway | $0.66 | $3.30 | $0.18 | — | 262,144 | 262,144 | |
| Kilo Gateway | Gateway | $0.67 | $3.35 | $0.18 | — | 262,144 | 235,929 | |
| OpenRouter | Gateway | $0.67 | $3.35 | $0.18 | — | 262,144 | 235,929 | |
| Moonshot AI (China)Official | First-party | $0.95 | $4.00 | $0.19 | — | 262,144 | 262,144 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 34 of 62 providers.
34 / 62 providers expose no reasoning control (reasoning_options: []).
5 more channels offer $0 (Alibaba Token Plan, Alibaba Token Plan (China), Volcengine Ark Coding Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Kimi Code Bench | harness: Kimi Code CLI · vv2 | 62 | — | Source ↗ |
| Program Bench | harness: Kimi Code CLI | 53.6 | — | Source ↗ |
| MLS Bench Lite | harness: Kimi Code CLI | 35.1 | — | Source ↗ |
| MCP Atlas | harness: Kimi Code CLI | 76 | success rate | Source ↗ |
| MCP Mark Verified | harness: Kimi Code CLI | 81.1 | success rate | Source ↗ |
| Kimi Claw 24/7 Bench | harness: Kimi Code CLI | 46.9 | — | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.