Moonshot Kimi K2.5
by Moonshot AIChat
Kimi multimodal agent model for visual understanding, coding, and planning
- Context
- 262K tokens
- Max output
- 262,144 tokens
- Parameters
- 1.03T total
- Released
- 2026-01
- Weights
- Open
- Licence
- modified-mit
moonshotai/kimi-k2-5 · also seen as novita/kimi-k2.5, kimi/kimi-k2.5, kimi-k2.5@eu, moonshot/kimi-k2.5, +18 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-01
- Weights
- Opennot gated
- License
- modified-mit
- Input
- Text, Image, Video
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 262,144
- Providers
- 32 + 21 gateways, not counted as providers
- Epoch Capabilities Index
- 148 ± 1.5 against price
- Direct price range
- $0.45–$0.60 in · $2.25–$3.50 out per 1M tokens · 24 of 32 providers have a comparable price
More details
- Last updated
- 2026-06-11
- Knowledge cutoff
- 2025-01
- Weights link
- Hugging Face · moonshotai/Kimi-K2.5
- Parameters
- 1.03T total
- Developer country
- China
- Training compute
- 5.8×10²⁴ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.45 in / $2.25 out per 1M tokens at SiliconFlow on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Moonshot Kimi K2.5 |
|---|---|---|---|---|---|
| Gemma 2 27BGoogle | $0.65 | $0.65 | $0.65 | 8.2K | +1% |
| MiniMax-M2.5-highspeedMiniMax | $0.65 | $0.30 | $2.40 | 205K | +1% |
| GLM 4.6V OriginalZ.ai (Zhipu AI) | $0.65 | $0.60 | $0.90 | 128K | +1% |
| Moonshot Kimi K2 InstructMoonshot AI | $0.633 | $0.40 | $1.80 | 131K | −2% cheaper |
| Kimi K2 0711Moonshot AI | $0.633 | $0.40 | $1.80 | 128K | −2% cheaper |
| Kimi K2 InstructMoonshot AI | $0.633 | $0.40 | $1.80 | 262K | −2% cheaper |
| Nemotron 3 Ultra 550B A55BNVIDIA | $0.627 | $0.40 | $1.76 | 1M | −3% cheaper |
| Gemini 3.5 Flash LiteGoogle | $0.667 | $0.30 | $2.50 | 1.05M | +3% |
More from Moonshot AI
Newest Moonshot AI models in the catalogue. All Moonshot AI models
| Model | Released | Context | Listed price |
|---|---|---|---|
| kimi-for-coding | 2026-09-11 | 1.05M | from $1.00 |
| Kimi K3 | 2026-07-16 | 1.05M | from $1.85 |
| Kimi K2.7 Code HighSpeed | 2026-06-12 | 262K | from $0.66 |
| Kimi Latest | 2026-05-03 | 1.05M | $1.65 via NanoGPT |
| Kimi K2.6 | 2026-04-21 | 262K | from $0.45 |
| Kimi-K2.5-FW | 2026-01-27 | 262K | unpriced |
| Kimi K2.5 Free | 2026-01-27 | 262K | unpriced |
| Kimi K2 0711 Fast | 2025-12-15 | 131K | $0.40 via NanoGPT |