Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent workKimi K3 by moonshotai is offered by 131 providers on this page. Public prices are shown for 122 of them. Its official list price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is UplinkSwitch at $0.90 / $4.50 per 1M, about 3.3× 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 2 free ($0) channels and 6 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 17.4 on the Intelligence Index, with 37 for Strategy & Ops, its strongest domain. Against its lowest blended price of $1.80 per 1M, that is roughly 10 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 44 tokens per second, with 4.15s to the first token. Running one task of the Artificial Analysis suite costs about $2.3688, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 262,144 to 1,113,088, 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.
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 |
|---|---|---|---|---|---|---|---|---|
| Kimi For Coding (kimi.com) k3-256k | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 262,144 | ||
| Kimi For Coding (kimi.com) k3 | Gateway | Subscription | $0 | $0 | 1,048,576 | 1,048,576 | ||
| Nvidia | Cloud | Free | — | — | 1,048,576 | 1,048,576 | deprecated | |
| Kimi For Coding (kimi.ai) k3-256k | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 262,144 | ||
| Kimi For Coding (kimi.ai) k3 | Gateway | Subscription | $0 | $0 | 1,048,576 | 1,048,576 | ||
| SCNet Token Plan Kimi-K3 | Gateway | Subscription | $0 | — | 1,048,576 | 1,048,576 | ||
| SenseNova (China) | Gateway | Free | $0 | — | 1,048,576 | 65,536 | ||
| Volcengine Ark Coding Plan | Gateway | Subscription | $0 | — | 1,048,576 | 1,048,576 | ||
| UplinkSwitch | Gateway | $0.90 | $4.50 | $0.12 | — | 1,048,576 | 1,048,576 | |
| NanoGPT | Gateway | $0.45 | $9.60 | $0.13 | — | 1,048,576 | 943,718 | |
| Moonshot AI (China)Official | First-party | $2.99 | $14.94 | $0.30 | $2.99 | 1,048,576 | 1,048,576 |
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 66 of 131 providers.
10 / 131 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| priority | Fireworks AI | $3.00 | $15.00 | $0.30 | — |
| priority | AbliteratedLLM | $3.38 | $16.88 | $0.34 | — |
| priority | Fireworks AI | $3.75 | $18.75 | $0.38 | — |
8 more channels offer $0 (Kimi For Coding (kimi.com), Kimi For Coding (kimi.com), Nvidia etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| DeepSWE | harness: Kimi Code · variant: max effort · v1.1 | 67.5 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Kimi Code · variant: max effort · v2.1 | 88.3 | accuracy | Source ↗ |
| FrontierSWE | harness: Kimi Code · variant: max effort | 81.2 | dominance score | Source ↗ |
| Program Bench | harness: Kimi Code · variant: max effort | 77.8 | score | Source ↗ |
| SWE Marathon | harness: Claude Code · variant: max effort · v1.1 | 42 | resolve rate | Source ↗ |
| GDPval-AA | variant: max effort · vv2 | 1668 | Elo | Source ↗ |
| AA-Briefcase | variant: max effort | 1548 | Elo | Source ↗ |
| AutomationBench | variant: max effort · dataset: 600-task public subset | 30.8 | success rate | Source ↗ |
| JobBench | variant: max effort | 52.9 | score | Source ↗ |
| SpreadsheetBench | harness: Claude Code · variant: max effort · v2 | 34.8 | score | Source ↗ |
| BrowseComp | variant: max effort, context compaction | 91.2 | accuracy | Source ↗ |
| CharXiv Reasoning | variant: max effort, with tools | 91.3 | accuracy | Source ↗ |
| ZeroBench | variant: max effort, with tools | 41 | pass@5 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.