Kimi K2.5
Moonshot AI's flagship Kimi K2.5 MoE model (1.04T params, 32B active) with native vision, advanced reasoning, and 256K context.
- Input price
- $0.4592–$0.66list $0.57420% off
- Output price
- $2.4088–$3.30list $3.01120% off
- Context
- 262K
- Max output
- 262K
- Capability
- 149 (#63 of 82)
- Human preference
- 1445
- 30-day uptime
- —
- Released
- 2026-01-27
- Knowledge cutoff
- 2025-06
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
Prices vary by provider. Showing Alibaba Cloud (Model Studio Intl), the lowest. Pick a provider above to see its prices.
- Input
- $0.4592list $0.57420% off
- per 1M tokens
- Output
- $2.4088list $3.01120% off
- per 1M tokens
- Cache read
- $0.092list $0.11520% off
- per 1M tokens
- Explicit cache read
- $0.0456list $0.05720% off
- per 1M tokens
- Cache write (5 min)
- $0.5744list $0.71820% off
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.00259
- 3K input tokens
- Agent first turn
- $0.0586
- 100K tokens of context, none cached
- Each later agent turn
- $0.0116
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.278
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text