LLMCost
moonshotai

MoonshotAI: Kimi K2.7 Code API Pricing

MoonshotAI: Kimi K2.7 Code costs $0.671 per 1M input tokens and $3.35 per 1M output tokens (cache reads: $0.180). Context window: 262K. Prices verified 2026-10-21 · source

🔔 Price alerts coming soon

Alternatives to consider

💰 Save money
Z.ai: GLM 5.3 Flash (batch)
$0.050 in / $0.180 out
Quality score: 41.8

94% cheaper with nearly identical quality (41.8 vs 43)

⬆️ Upgrade smart
Google: Gemini 3.7 Flash
$0.750 in / $3.75 out
Quality score: 56

+13 quality points for 12% more

🏠 Same provider
MoonshotAI: Kimi K2.5
$0.500 in / $2.50 out
Quality score: 23.5

Cheapest moonshotai model — 25% less per month

Price history
2026-08-23 → 2026-10-21 · 59 daily snapshots
inputoutputinput +0.2% over windowoutput -1.5%

Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.

Community adoption
108K
HF downloads
1K
Likes

High adoption means battle-tested weights, more fine-tunes/quants, and faster bug fixes. View on HuggingFace →

Pricing behavior
9 price changes in the last 59 daily snapshots
Changes roughly every 6.6 days
Last move (2026-09-30): input +2.3%
Net input drift: +0.2% since 2026-08-23

From our own daily snapshot archive — independent of provider announcements.

Intelligence & capability
via Artificial Analysis
43
Intelligence index · top 17% of 288 scored
60.8
Coding index
21
Agentic index
$1.3409
Blended $/1M (3:1 in:out)

Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.

Input / 1M tokens
$0.671
Output / 1M tokens
$3.35
Context window
262K
Max output
236K

Token economics

Token typePricevs base input
Standard input$0.671—
Cache read$0.180−73%
Output$3.35—

Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.

Reasoning behavior
Mode: Always on (mandatory)

Higher effort = deeper thinking = more reasoning tokens billed as output.

What would MoonshotAI: Kimi K2.7 Code cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$18.77
Coding agent5,0008,000 / 2,000$60.35
RAG pipeline30,0004,000 / 500$130.79
Doc summarizer2,00020,000 / 1,000$33.55

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

Compare MoonshotAI: Kimi K2.7 Code with

Popular head-to-heads — see all on the comparisons index.

Frequently asked questions

How much does MoonshotAI: Kimi K2.7 Code cost?

MoonshotAI: Kimi K2.7 Code costs $0.671 per 1M input tokens and $3.35 per 1M output tokens; cached input tokens cost $0.180 per 1M. Verified 2026-10-21 — provider source.

What is the context window?

262K tokens, with up to 236K output tokens per response. That's roughly 328 pages of text in a single request.

Does it support prompt caching?

Yes — cached input is $0.180/1M, about 73% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.

What's a cheaper alternative?

ScaleDown: Summarize saves about 98% on a typical workload with comparable quality.

Official resources