BroadRouter

Kimi K2.7 Code API pricing

Updated

The cheapest standard price for Kimi K2.7 Code is CoreWeave Forge at USD 0.60 per 1M input tokens and USD 3 per 1M output tokens. The median across 12 standard prices is USD 0.90458 / USD 3.90. Moonshot AI's own API charges USD 0.95 / USD 4. Every price is read from the provider's own pricing page, checked 2026-11-15.

Moonshot AI · slug kimi-k2.7-code · up to 262,144 tokens of context · 12 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-07-01 (2 archived price points, 0 list-price changes): LLM API price history.

What does Moonshot AI charge for Kimi K2.7 Code?

Input
USD 0.95
Cached input
USD 0.19
Output
USD 4
Blended 3:1
USD 1.712

USD per 1M tokens on Moonshot AI (Kimi), model kimi-k2.7-code, standard tier. Source, checked 2026-11-14.

Other Moonshot AI tiers: fast USD 1.90 / USD 8 · batch USD 0.57 / USD 2.40.

Is a host cheaper than Moonshot AI? Yes. CoreWeave Forge charges USD 0.60 input and USD 3 output per 1M tokens, 30% below Moonshot AI's own USD 0.95 / USD 4 on the 3:1 blend.

Kimi K2.7 Code price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 43% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Kimi K2.7 Code API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1CoreWeave Forge cheapest
moonshotai/Kimi-K2.7-Code
Notes and source quote
“Moonshot AI Kimi K2.7 Code $0.60 $3.00 $0.12”
USD 0.60USD 0.12USD 3USD 1.20262,144not statedCoreWeave Forge page
checked 2026-11-15
re-checked 2026-11-16
2Parasail
Notes and source quote
“Kimi K2.7 Code $0.75 $3.50 $0.16”
USD 0.75USD 0.16USD 3.50USD 1.438not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
3Venice
kimi-k2-7-code
Notes and source quote
“| Kimi K2.7 Code | `kimi-k2-7-code` | $0.75 | $3.50 | $0.16 | — | Private |”
USD 0.75USD 0.16USD 3.50USD 1.438256,000INT4Venice page
checked 2026-11-15
re-checked 2026-11-16
4Featherless
moonshotai/Kimi-K2.7-Code
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.8 / CACHED $0.154 / OUTPUT $3.4”
USD 0.80USD 0.154USD 3.40USD 1.45262,144FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
5Chutes
moonshotai/Kimi-K2.7-Code
Notes and source quote
“Kimi-K2.7-Code moonshotai/Kimi-K2.7-Code $0.167 per 1M tokens $0.832 per 1M tokens $3.50 per 1M tokens 262K”
USD 0.832USD 0.167USD 3.50USD 1.499262,144not statedChutes page
checked 2026-11-15
re-checked 2026-11-16
6SiliconFlow
Notes and source quote

Context shown as 262K.

“Kimi-K2.7-Code 262K $0.85916 $0.17993 $3.8”
USD 0.85916USD 0.17993USD 3.80USD 1.594262,144not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
7Moonshot AI maker
kimi-k2.7-code
Notes and source quote

Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026.

“kimi-k2.7-code | $0.95 / MTok | $4.00 / MTok | $0.19 / MTok”
USD 0.95USD 0.19USD 4USD 1.712262,144not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16
8Alibaba Cloud
kimi-k2.7-code
Notes and source quote

International (Singapore) deployment. Singapore tab of the Kimi table.

“kimi-k2.7-code International $0.95 $4”
USD 0.95not publishedUSD 4USD 1.712not statednot statedAlibaba Cloud page
checked 2026-11-14
re-checked 2026-11-16
9Cloudflare Workers AI
@cf/moonshotai/kimi-k2.7-code
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/moonshotai/kimi-k2.7-code $0.950 per M input tokens $0.190 per M cached input tokens $4.000 per M output tokens”
USD 0.95USD 0.19USD 4USD 1.712not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
10GMI Cloud
moonshotai/kimi-k2.7-code
Notes and source quote
“Price (per 1M tokens) Input $0.95 Output $4.00 Cache Read $0.19 Cache Write -”
USD 0.95USD 0.19USD 4USD 1.712262,144FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
11Microsoft Azure
Notes and source quote

Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US.

“Kimi K2.7 Code $0.95 $0.19 $4”
USD 0.95USD 0.19USD 4USD 1.712not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
12Novita AI
moonshotai/kimi-k2.7-code
Notes and source quote
“Kimi K2.7 Code 256K $0.95 /Mt · Cache Read $0.19 /Mt $4 /Mt”
USD 0.95USD 0.19USD 4USD 1.712262,144not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
—Moonshot AI maker batch
kimi-k2.7-code
Notes and source quote

Batch API, billed at 60% of the standard price. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026.

“kimi-k2.7-code | $0.57 / MTok | $2.40 / MTok | $0.114 / MTok | — | —”
USD 0.57USD 0.114USD 2.40USD 1.027262,144not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16
—Moonshot AI maker fast
kimi-k2.7-code-highspeed
Notes and source quote

Highspeed variant, API model kimi-k2.7-code-highspeed. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026.

“kimi-k2.7-code-highspeed | $1.90 / MTok | $8.00 / MTok | $0.38 / MTok”
USD 1.90USD 0.38USD 8USD 3.425262,144not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Kimi K2.7 Code cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Kimi K2.7 Code, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
CoreWeave ForgeUSD 82.08USD 154.44USD 615.60
ParasailUSD 98.64USD 190.02USD 762.30
VeniceUSD 98.64USD 190.02USD 762.30
FeatherlessUSD 98.32USD 196.49USD 757.62
ChutesUSD 101.97USD 204.30USD 795.15
SiliconFlowUSD 109.05USD 214.29USD 849.27
Moonshot AI (maker)USD 116.46USD 233.28USD 907.20
Alibaba CloudUSD 157.50USD 288.00USD 2,070
Cloudflare Workers AIUSD 116.46USD 233.28USD 907.20
GMI CloudUSD 116.46USD 233.28USD 907.20
Microsoft AzureUSD 116.46USD 233.28USD 907.20
Novita AIUSD 116.46USD 233.28USD 907.20

For the support chatbot, the cheapest price (CoreWeave Forge, USD 82.08 a month) saves USD 30.67 against the median (USD 112.75). For the coding agent the gap is USD 262.63 a month (30% lower).

Which Kimi K2.7 Code provider is cheapest for your traffic?

CoreWeave Forge has the lowest input price (USD 0.60) and the lowest output price (USD 3), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Kimi K2.7 Code: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
CoreWeave ForgeUSD 1.20 cheapestUSD 1.02 cheapestUSD 0.876 cheapest
ParasailUSD 1.438USD 1.216USD 1.039
VeniceUSD 1.438USD 1.216USD 1.039
FeatherlessUSD 1.45USD 1.208USD 1.014
ChutesUSD 1.499USD 1.25USD 1.05
SiliconFlowUSD 1.594USD 1.34USD 1.136

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 6 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

11 of 12 providers publish a cached-input price below the input price: CoreWeave Forge (80% off), Parasail (79% off), Venice (79% off), Featherless (81% off), Chutes (80% off) and 6 more. Alibaba Cloud publishes none, so cached tokens there bill at the input price.

Context windows differ: 262,144 tokens at CoreWeave Forge, Featherless, Chutes and 4 more; 256,000 tokens at Venice. Parasail, Alibaba Cloud, Cloudflare Workers AI and Microsoft Azure do not state one. The cheapest row is not always the one that fits a long prompt.

What does Kimi K2.7 Code cost in other languages?

The same text needs a different number of tokens in each language. With the Kimi K3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Kimi K2.7 Code:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.130CoreWeave Forge
Arabic MSAUSD 0.288CoreWeave Forge
HindiUSD 0.341CoreWeave Forge
ChineseUSD 0.327CoreWeave Forge
CodeUSD 0.156CoreWeave Forge

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Moonshot AI model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.

Published benchmark results for Kimi K2.7 Code, with sources
BenchmarkResultSetting or noteSource
Kimi Code Bench v262.0not statedMoonshot AI model card, checked 2026-11-16
Program Bench53.6not statedMoonshot AI model card, checked 2026-11-16
MCP Atlas76.0not statedMoonshot AI model card, checked 2026-11-16
GPQA Diamond0.879Setting as listed by Epoch (no suffix); Epoch run kimi-k2.7-code, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16

Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Estimate your own bill

The Moonshot AI models whose cheapest standard price is closest to Kimi K2.7 Code's (USD 1.20 blended):

Moonshot AI models priced closest to Kimi K2.7 Code
ModelCheapest inputCheapest outputMax contextProviders
Kimi K2 Instruct 0905USD 0.60USD 2.50262,1442
Kimi K2 InstructUSD 0.57USD 2.30131,0722
Kimi K2 ThinkingUSD 0.80USD 1.20262,1446
Kimi K2.5USD 0.45USD 2.25262,1448
Kimi K2.6USD 0.39USD 1.80262,14413
Kimi K3USD 1.85USD 9.501,048,57618

Priced closest from other makers: DeepSeek V4 Pro (DeepSeek, USD 1.196) · Qwen3 235B A22B Thinking 2507 FP8 (Qwen, USD 1.212) · Hy4 Preview (Tencent, USD 1.251).

Compare Kimi K2.7 Code with

Also compared: vs GLM 5.3 · vs Kimi K2.6.

Every Kimi K2.7 Code price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Kimi K2.7 Code API cost per token?

From USD 0.60 per 1M input tokens (USD 0.0000006 per token) and USD 3 per 1M output tokens (USD 0.000003 per token) at the cheapest standard price. The median of 12 standard prices is USD 0.90458 input and USD 3.90 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Kimi K2.7 Code?

CoreWeave Forge, ranked on a blend of 3 input tokens to 1 output token (USD 1.20 per 1M). It is also the cheapest on both input and output. Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Kimi K2.7 Code cheaper from a host than from Moonshot AI?

Yes. CoreWeave Forge charges USD 0.60 input and USD 3 output per 1M tokens, 30% below Moonshot AI's own USD 0.95 / USD 4 on the 3:1 blend.

Does Kimi K2.7 Code have cached input pricing?

11 of 12 standard prices include one. The lowest is USD 0.12 per 1M at CoreWeave Forge; the median is USD 0.17993. Providers without one bill cached input at the input price. What cached input means.

What is the Kimi K2.7 Code context window?

Up to 262,144 tokens. 1 standard price comes with less, down to 256,000 tokens (Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on Kimi K2.7 Code?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 615.60 a month at CoreWeave Forge, USD 878.23 at the median price and USD 2,070 at Alibaba Cloud. Try your own numbers.

Is there a batch, flex or priority price for Kimi K2.7 Code?

Yes: batch from Moonshot AI at USD 0.57 / USD 2.40; fast from Moonshot AI at USD 1.90 / USD 8 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Kimi K2.7 Code free to use through an API?

No provider in our data lists a free price for Kimi K2.7 Code as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

How does Kimi K2.7 Code score on benchmarks?

As published, the Moonshot AI model card reports 62.0 on Kimi Code Bench v2 and 53.6 on Program Bench; Epoch AI measured 0.879 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity