Context
262K
Max output
262K
Serving providers
6
Cheapest input
$0.50 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize, Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
48 t/s
tokens / second
Time to first token
28.52s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AIME 2026 | 96% | default | — | |||||||||||||
| APEX Agents | 12% | default | — | |||||||||||||
| ARC-AGI-2 | 12% | default | $0.280 | |||||||||||||
| CritPt | 3% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 4448.1 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 1008.5 | default | — | |||||||||||||
| GPQA Diamond | 88% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 29% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 70% | default | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 65% | default | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 75% | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -8.1 | default | — | |||||||||||||
| ||||||||||||||||
| SciCode | 49% | default | — | |||||||||||||
| ||||||||||||||||
| SWE-bench Pro | 51% | default | — | |||||||||||||
| SWE-bench Verified | 71% | default | — | |||||||||||||
| TerminalBench Hard | 35% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 46% | default | — | |||||||||||||
| τ-bench Banking | 14% | default | — | |||||||||||||
| τ²-bench | 96% | default | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.50 to $0.60 per 1M tokens across 6 providers, so the dearest route costs 20% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Together AICheapest | $0.50 | $2.80 | 1 | |||||||||||||
| ||||||||||||||||
| Azure | $0.60 | $3.00 | 1 | |||||||||||||
| ||||||||||||||||
| Baseten | $0.60 | $3.00 | 1 | |||||||||||||
| ||||||||||||||||
| Moonshot | $0.60 | $3.00 | 1 | |||||||||||||
| ||||||||||||||||
| OpenRouter | $0.60 | $3.00 | 1 | |||||||||||||
| ||||||||||||||||
| Wandb | $0.60 | $3.00 | 1 | |||||||||||||
| ||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 17% since first tracked
Cost calculator
estimate your monthly spend on this model$324
estimated / month
Model IDs
copy the exact identifier for your platformtogether_ai/moonshotai/Kimi-K2.5azure_ai/kimi-k2.5baseten/moonshotai/Kimi-K2.5moonshot/kimi-k2.5openrouter/moonshotai/kimi-k2.5wandb/moonshotai/Kimi-K2.5
Frequently asked questions
Kimi K2.5 pricing, context and availabilityHow much does Kimi K2.5 cost?
Kimi K2.5 costs $0.50 per 1M input tokens and $2.80 per 1M output tokens at its cheapest provider via Together AI. Across 6 serving providers, input prices range from $0.50 to $0.60 per 1M tokens.
What is the context window of Kimi K2.5?
Kimi K2.5 accepts up to 262K tokens of context and can return up to 262K output tokens.
Which providers serve Kimi K2.5?
Kimi K2.5 is available from 6 serving providers, each with its own pricing and model ID. Together AI is currently the cheapest.
What can Kimi K2.5 do?
Kimi K2.5 supports image input (vision), tool use, reasoning and structured output.
Other Moonshot models
compare pricing across the Moonshot lineupKimi K2 Instruct$0.50/1M · 6 providersKimi K2 Thinking$0.60/1M · 6 providersKimi K2 Instruct 0905$0.50/1M · 5 providersKimi K2 Thinking 251104$0.00/1M · 1 providerKimi Latest 8k$0.20/1M · 1 providerMoonshot V1 8k$0.20/1M · 1 providerMoonshot V1 8k 0430$0.20/1M · 1 providerMoonshot V1 8k Vision Preview$0.20/1M · 1 provider
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI