This model was retired on 2026-08-27. The pricing below is the last-known rate, kept for migration reference.
Kimi K2.7 CodeDeprecated
VisionTool useReasoningPrompt cachingStructured output
Context
262K
Max output
262K
Serving providers
7
Cheapest input
$0.66 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
46 t/s
tokens / second
Time to first token
2.81s
latency
Headline indices
Intelligence Index
43.0
of 100
Coding Index
60.8
of 100
Agentic Index
30.3
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| Automation Bench | 0.2 | default | — | |
| CritPt | 10% | default | — | |
| EvalComputeProxy | 2037.4 | default | — | |
| GDPval | 1189.9 | default | — | |
| GPQA Diamond | 90% | default | — | |
| Harvey Lab | 0.9 | default | — | |
| Humanity's Last Exam | 35% | default | — | |
| IFBench | 63% | default | — | |
| Long-Context Reasoning | 75% | default | — | |
| Mlcr Overall | 0.2 | default | — | |
| Omniscience | -10.2 | default | — | |
| Omniscience Accuracy | 0.4 | default | — | |
| Omniscience Non Hallucination | 0.2 | default | — | |
| SciCode | 47% | default | — | |
| TerminalBench Hard | 45% | default | — | |
| TerminalBench v2.1 | 67% | default | — | |
| τ-bench Banking | 20% | default | — | |
| τ²-bench | 90% | default | — |
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | $0.66 | $3.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepInfra | $0.68 | $3.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Wandb | $0.71 | $3.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Cloudflare | $0.95 | $4.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Together AI | $0.95 | $4.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Novita | $0.95 | $4.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Dashscope | $0.95 | $4.00 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 31% since first tracked
Cost calculator
estimate your monthly spend on this model$404
estimated / month
Model IDs
copy the exact identifier for your platformmoonshotai/kimi-k2.7-codedeepinfra/moonshotai/Kimi-K2.7-Codewandb/moonshotai/Kimi-K2.7-Codecloudflare/@cf/moonshotai/kimi-k2.7-codetogether_ai/moonshotai/Kimi-K2.7-Codenovita/moonshotai/kimi-k2.7-codedashscope/kimi-k2.7-code
Frequently asked questions
Kimi K2.7 Code pricing, context and availabilityIs Kimi K2.7 Code still available?
Kimi K2.7 Code was retired on 2026-08-27. The pricing on this page is the last-known rate, kept for migration reference.
How much did Kimi K2.7 Code cost?
Kimi K2.7 Code's last-known pricing, before it was retired on 2026-08-27, was $0.66 per 1M input tokens and $3.40 per 1M output tokens.
What was the context window of Kimi K2.7 Code?
Kimi K2.7 Code had a 262K token context window and could return up to 262K output tokens.
What could Kimi K2.7 Code do?
Kimi K2.7 Code supported image input (vision), tool use, reasoning, prompt caching and structured output.
Other Moonshot models
compare pricing across the Moonshot lineupPopular comparisons
head-to-head pages featuring Kimi K2.7 Code
Kimi K2.7 Code vs Claude Fable 5side-by-side pricing & benchmarks Kimi K2.7 Code vs Claude Opus 4.8side-by-side pricing & benchmarks Kimi K2.7 Code vs Claude Sonnet 5side-by-side pricing & benchmarks
Kimi K2.7 Code vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Kimi K2.7 Code vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks 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