Kimi K2.5 vs Kimi K3.1 Pro
Kimi K2.5 (MoonshotAI) and Kimi K3.1 Pro (MoonshotAI) are listed at different prices. Kimi K3.1 Pro costs less for input, $0.24 per 1M tokens against $0.50; Kimi K2.5 costs less for output, $2.50 per 1M tokens against $8.402. Kimi K3.1 Pro has the larger context window, 1,048,576 tokens against 262,144 for Kimi K2.5. Only Kimi K3.1 Pro supports a reasoning effort setting. Kimi K2.5 accepts text and images and produces text; Kimi K3.1 Pro accepts text, images and video and produces text.
MoonshotAI: Kimi K2.5 accepts text and images, while MoonshotAI: Kimi K3.1 Pro also accepts video. Both produce text and support tools, structured outputs, response formats, and reasoning; their context lengths are 262,144 and 1,048,576 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Kimi K2.5 | Kimi K3.1 Pro |
|---|---|---|
| Maker | MoonshotAI | MoonshotAI |
| Added to catalog | 27 Jan 2026 | 23 Oct 2026 |
| Input, per 1M tokens | $0.50 | $0.24 |
| Output, per 1M tokens | $2.50 | $8.402 |
| Cached input read, per 1M | $0.15 | $0.20 |
| Context windowTokens | 262,144 | 1,048,576 |
| Max outputTokens | 235,929 | 943,718 |
| Accepts | image, text | image, text, video |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Kimi K2.5 | Kimi K3.1 Pro |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0010 | $0.0026 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.015 | $0.013 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.020 | $0.024 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.079 | $0.049 |
Which to choose
Choose Kimi K2.5 if
- Output tokens cost less: $2.50 against $8.402 per 1M
- Cached input costs less: $0.15 against $0.20 per 1M
Choose Kimi K3.1 Pro if
- Input tokens cost less: $0.24 against $0.50 per 1M
- You need the larger context window: 1,048,576 tokens against 262,144
- You need longer answers in one response: 943,718 tokens against 235,929
- It has to read video, which the other model does not
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.