Prototype · closed beta
unOpen.AI
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Kimi · Moonshot AI
Kimi K2.5.
Kimi K2.5 is a Moonshot AI model, listed on 27 January 2026. It takes text and images and returns text, with a 262,144-token context window.
- Open weights
- 262k context
Specification
- Provider
- Moonshot AI
- Family
- Kimi
- Listed
- 27 January 2026
- Catalogue id
- moonshotai/kimi-k2.5
- Context window
- 262,144 tokens
- Maximum output
- 235,929 tokens
- Inputs and output
- Text and images in; text out
- Capabilities
- Tool calling, structured outputs and adjustable reasoning
- Weights
- Published: moonshotai/Kimi-K2.5
- Listed price
- $0.500 input, $2.50 output, $0.150 cached input per million tokens
Provider-published specifications as of 30 October 2026, not figures we measured. Model families move quickly — check the provider's own documentation before committing to a number.
Source: Kimi K2.5 in the OpenRouter catalogue, checked weekly. Confirm current terms in Moonshot AI's own documentation before you commit.
What it costs
Price the whole answer.
Illustrative calculation at listed rates: a batch of 10 million input tokens and 1 million output tokens costs $7.50 on Kimi K2.5. A thousand requests of 2,000 input and 500 output tokens each costs $2.25. Calculation: input millions × input rate + output millions × output rate; it excludes reasoning tokens, retries, tools, tax and review time.
Compare cost per accepted result, not per token: replay the same work on two or three candidates and count the answers you would actually ship. Our model-routing approach sends each request to the cheapest model that passes.
THE REST OF THE FAMILY
Other Kimi models.
Every Kimi model in the catalogue. Our Kimi page covers where the family fits and how we evaluate it.
| Kimi K2.5 open | 27 Jan 2026 | — | — | 262k | $0.500 | $2.50 |
|---|---|---|---|---|---|---|
| Kimi K3.1 Pro | 23 Oct 2026 | 46.0 | 30 | 1.05M | $2.00 | $10.00 |
| Kimi K3 open | 16 Jul 2026 | — | — | 1.05M | $0.192 | $15.00 |
| Kimi K2.7 Code open | 12 Jun 2026 | — | 48 | 262k | $0.600 | $3.50 |
| Kimi K2.6 open | 20 Apr 2026 | — | — | 262k | $0.650 | $3.41 |
| Kimi K2 Thinking open | 6 Nov 2025 | — | — | 262k | $0.600 | $2.50 |
| Kimi K2 0905 open | 5 Sep 2025 | — | — | 262k | $0.600 | $2.50 |
| Kimi K2 0711 open | 11 Jul 2025 | — | — | 131k | $0.570 | $2.30 |
Intelligence and coding: Artificial Analysis indices at the model's best reasoning setting, and its measured output speed. Context and prices: the OpenRouter catalogue list price in USD per million tokens. Released: the provider's date where Artificial Analysis records one, otherwise the date the catalogue first listed it. Refreshed weekly; not measured by QQuantum.ai. Select a heading to sort.
Questions
Questions about Kimi K2.5.
When was Kimi K2.5 listed?
Kimi K2.5 was listed on 27 January 2026 in the OpenRouter catalogue; the provider's own announcement may predate it.
What is the context window of Kimi K2.5?
262,144 tokens, with up to 235,929 output tokens per response, as listed in the OpenRouter catalogue on 30 October 2026. A long window is not the same as reliable recall across it; evaluate retrieval on your own documents.
How much does Kimi K2.5 cost?
The catalogue lists $0.500 per million input tokens and $2.50 per million output tokens, and $0.150 per million cached input tokens (checked 30 October 2026). Moonshot AI's own rates, batch discounts and cloud marketplaces can differ.
Can Kimi K2.5 run on our own hardware?
Its weights are published (on Hugging Face as moonshotai/Kimi-K2.5), so it can be self-hosted subject to its licence. Check the licence and size the serving stack before buying hardware.
