MoonshotAI: Kimi K2.5
Kimi K2.5 is a model from Moonshot AI that accepts text and image inputs and returns text. It offers a 262,144-token context window with up to 235,929 completion tokens, so long documents and lengthy generated outputs fit in a single call. It supports tool use and a reasoning mode. The listing does not specify structured output support or whether the weights are open, so confirm both before relying on them. At $0.50 per million input tokens and $2.50 per million output tokens, it belongs on shortlists for teams that need long context, image input, and tool calling without paying premium-tier rates. Its blended benchmark score of 64.3 rests on only two independent benchmarks: 62.9 on the AI Index and 55.2 on EQ-Bench. That coverage is thin, so treat its standing as provisional and run your own task-specific tests before committing.
Benchmark results
Independent, published benchmarks. Blended score 64.3 across 2 benchmarks, last refreshed 2026-11-01. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 62.9 |
| EQ-Bench | emotional understanding in dialogue | 55.2 |
- Model ID
- moonshotai/kimi-k2.5
- Vendor
- moonshotai
- Released
- January 2026
- Tokenizer
- Other
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 235,929 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.50/M input and $2.50/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.02 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.38 |
| A month of a busy support chatbot | 5M in / 2M out | $7.50 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-10-11 | $0.50 | $2.50 | 262,144 |
| 2026-09-01 | $0.45 | $2.25 | 262,144 |
| 2026-08-28 | $0.60 | $3.00 | 262,144 |
| 2026-08-27 | $0.45 | $2.25 | 262,144 |
| 2026-08-25 | $0.60 | $3.00 | 262,144 |
| 2026-08-19 | $0.45 | $2.25 | 262,144 |
| 2026-07-17 | $0.57 | $2.85 | 262,144 |
Category rankings
Where MoonshotAI: Kimi K2.5 places across the 1 category it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #15 | Image CaptioningVision · of 25 ranked | 120 |
Similar models
MoonshotAI: Kimi K3.1 Pro
MoonshotAI: Kimi K3
MoonshotAI: Kimi K3 (batch)
MoonshotAI: Kimi K2.7 Code
MoonshotAI: Kimi K2.6
MoonshotAI: Kimi K2 Thinking
Quick answers
- How much does MoonshotAI: Kimi K2.5 cost?
- $0.50 per million input tokens and $2.50 per million output tokens.
- What is MoonshotAI: Kimi K2.5's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does MoonshotAI: Kimi K2.5 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can MoonshotAI: Kimi K2.5 process images?
- Yes, it accepts image input.