Loading
Loading
Model record / Moonshot
kimi-k2.5
Access kimi-k2.5 from Moonshot through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationVision inputReasoningStreaming35% below list
What you pay
Current catalog rates.
Input / 1M tokens$0.60 list$0.39
Output / 1M tokens$3.00 list$1.95
Cached input / 1M tokens$0.065
Current discount35%
Observed reliability
96.99
Successful provider-reaching requests
Output speed
29.8
Median tokens per second over sustained generations
p95 first token (ms)
20,605
p50 5841 ms · total p95 89489 ms
Evidence strength
—
established
At a glance
- Provider
- Moonshot
- Model ID
- kimi-k2.5
- Type
- Text generation
- Endpoint
- /v1/chat/completions
- Vision input
- Supported
- Image editing
- Not supported
- Video input
- Not supported
- Reasoning
- Supported
- Streaming
- Supported
- Context window
- 256,000 tokens
- Maximum output
- 262,144 tokens
Send a request
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
kimi-k2.5
Growing confidenceThis model averaged 33.6% below comparable direct provider prices across the selected range. Its strongest observed window was 3:00 PM–10:00 AM in UTC.
Last 7 days
Average saved
33.6%
Last 7 days
Cheapest time
3:00 PM–10:00 AM
35.0% average savings
Hourly coverage
24/24
40 total observations
Signal quality
Growing
Ready for planning
Typical unit savings$0.20 / 1M input tokens$1.01 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#60
of 90 ranked models
Last 7 days
#61
of 91 ranked models
Last 30 days
#69
of 93 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.
