Kimi K2.5
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Cheapest input
$0.6
$/MTok · models.dev
Cheapest output
$3
$/MTok
Context
262K
tokens
Offers
3
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmoonshot/kimi-k2.5 | Merge Gateway | $0.6 | $3 | $0.1 | 262K |
| LiteLLMmoonshot/kimi-k2.5 | — | $0.6 | $3 | $0.1 | — |
| models.devmoonshot/kimi-k2.5 | CrossModel | $0.62 | $3.30 | $0.11 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2025-01Released: 2026-01Family: kimi-k2
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence35.4
- AA coding46.8
- AA agentic21.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.