Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Kimi K2.5 by moonshotai is offered by 52 providers on this page. Public prices are shown for 44 of them. Its reference price is $0.56 per 1M input tokens and $3.50 per 1M output tokens. The lowest paid channel is NanoGPT at $0.30 / $1.90 per 1M, about 2.1× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 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 36 on the Intelligence Index, with 46.8 for coding and 21.7 for agentic tasks. Against its lowest blended price of $0.70 per 1M, that is roughly 51 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 81 tokens per second, with 2.76s to the first token. Running one task of the Artificial Analysis suite costs about $0.0964, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 256,000 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. 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 ⚠ | 98,304 | ||
| Alibaba Coding Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 32,768 | ||
| Alibaba Coding Plan | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 32,768 | ||
| SCNet Token Plan Kimi-K2.5 | Gateway | Subscription | $0 | — | 262,144 ⚠ | 262,144 | ||
| Tencent Coding Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 32,768 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 ⚠ | 98,304 | ||
| NanoGPT | Gateway | $0.30 | $1.90 | $0.15 | — | 256,000 | 65,536 | |
| DevPass (LLM Gateway) | Gateway | $0.405 | $1.98 | $0.225 | — | 262,144 ⚠ | 262,144 | |
| LLM Gateway | Gateway | $0.405 | $1.98 | $0.225 | — | 262,144 ⚠ | 262,144 | |
| Deep Infra moonshotai/Kimi-K2.5 | Cloud | $0.45 | $2.25 | $0.07 | — | 262,144 ⚠ | 32,768 | deprecated |
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.
6 more channels offer $0 (Alibaba Token Plan, Alibaba Coding Plan (China), Alibaba Coding Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 70.8 | resolved | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 13.1 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Mini-SWE-Agent | 20.95 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 25.77 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
13 / 52 providers expose no reasoning control (reasoning_options: []).