Scheduled for retirement on Apr 16, 2027. Still available at the prices below until then.
Context
262K
Max output
262K
Serving providers
15
Cheapest input
$0.65 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
47 t/s
tokens / second
Time to first token
2.78s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-BriefcaseUndated | 16% | default | — | |||||||||||||||||
| AIME 2026 | 96% | default | — | |||||||||||||||||
| APEX Agents | 28% | default | — | |||||||||||||||||
| Automation Bench | 0.1 | default | — | |||||||||||||||||
| CritPt | 8% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 2257.5 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1190.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 91% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Harvey Lab | 0.8 | default | — | |||||||||||||||||
| Humanity's Last Exam | 37% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 76% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 31% | default | — | |||||||||||||||||
| Long-Context Reasoning | 81% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 79% | default | — | |||||||||||||||||
| Omniscience | 5.3 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.6 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 52% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SWE-bench Pro | 59% | default | — | |||||||||||||||||
| SWE-bench Verified | 80% | default | — | |||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 44% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 66% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 23% | default | — | |||||||||||||||||
| τ²-bench | 96% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
We cannot tell whether this benchmark is still being published. Treat these scores as undated.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.65 to $1.20 per 1M tokens across 15 providers, so the dearest route costs 85% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | $0.65 | $3.41 | 1 | |||||||||||||
Standardmoonshotai/kimi-k2.6
| ||||||||||||||||
| WandbCheapest | $0.65 | $3.41 | 1 | |||||||||||||
Standardwandb/moonshotai/Kimi-K2.6
| ||||||||||||||||
| DeepInfra | $0.75 | $3.50 | 1 | |||||||||||||
Standarddeepinfra/moonshotai/Kimi-K2.6
| ||||||||||||||||
| Novita | $0.80 | $3.40 | 1 | |||||||||||||
Standardnovita/moonshotai/kimi-k2.6
| ||||||||||||||||
| Aihubmix | $0.95 | $4.00 | 1 | |||||||||||||
Standardaihubmix/kimi-k2.6
| ||||||||||||||||
| Azure | $0.95 | $4.00 | 1 | |||||||||||||
Standardazure_ai/kimi-k2.6
| ||||||||||||||||
| Baseten | $0.95 | $4.00 | 1 | |||||||||||||
Standardbaseten/moonshotai/Kimi-K2.6
| ||||||||||||||||
| Cloudflare | $0.95 | $4.00 | 1 | |||||||||||||
Standardcloudflare/@cf/moonshotai/kimi-k2.6
| ||||||||||||||||
| Together AI is dearest at $1.20 / $4.50 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 32% since first tracked
Cost calculator
estimate your monthly spend on this model$403
estimated / month
Model IDs
copy the exact identifier for your platformwandb/moonshotai/Kimi-K2.6moonshotai/kimi-k2.6deepinfra/moonshotai/Kimi-K2.6novita/moonshotai/kimi-k2.6fireworks_ai/accounts/fireworks/models/kimi-k2p6moonshot/kimi-k2.6cloudflare/@cf/moonshotai/kimi-k2.6azure_ai/kimi-k2.6nebius/moonshotai/Kimi-K2.6aihubmix/kimi-k2.6moonshotai/kimi-k2.6baseten/moonshotai/Kimi-K2.6tensormesh/moonshotai/Kimi-K2.6sail/moonshotai/Kimi-K2.6together_ai/moonshotai/Kimi-K2.6
Frequently asked questions
Kimi K2.6 pricing, context and availabilityIs Kimi K2.6 still available?
Yes. Kimi K2.6 is scheduled for retirement on 2027-04-16.
How much does Kimi K2.6 cost?
Kimi K2.6 costs $0.65 per 1M input tokens from Wandb, and $3.40 per 1M output tokens from Novita. Across 15 serving providers, input prices range from $0.65 to $1.20 per 1M tokens.
What is the context window of Kimi K2.6?
Kimi K2.6 accepts up to 262K tokens of context and can return up to 262K output tokens.
Which providers serve Kimi K2.6?
Kimi K2.6 is available from 15 serving providers, each with its own pricing and model ID. Wandb is currently the cheapest.
What can Kimi K2.6 do?
Kimi K2.6 supports image input (vision), tool use, reasoning, prompt caching and structured output.
Other Moonshot models
compare pricing across the Moonshot lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI