BroadRouter
Get started

Kimi K3.1 Pro API pricing

Updated

Among the 13 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Kimi K3.1 Pro is DeepInfra (promotional) at USD 1.90 per 1M input tokens and USD 9.50 per 1M output tokens. The median across 13 standard prices is USD 2 / USD 10. Moonshot AI's own API charges USD 2 / USD 10.

Moonshot AI · slug kimi-k3.1-pro · up to 1,048,576 tokens of context · 13 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.

What does Moonshot AI charge for Kimi K3.1 Pro?

Input
USD 2
Cached input
USD 0.20
Output
USD 10
Blended 3:1
USD 4

USD per 1M tokens on Moonshot AI (Kimi), model kimi-k3.1-pro, standard tier. Source, checked 2026-11-14.

Other Moonshot AI tiers: fast USD 4 / USD 20 · batch USD 1.20 / USD 6.

Is a host cheaper than Moonshot AI? Yes. DeepInfra charges USD 1.90 input and USD 9.50 output per 1M tokens, 5% below Moonshot AI's own USD 2 / USD 10 on the 3:1 blend (a promotional price).

Kimi K3.1 Pro model facts

Facts from Moonshot AI's model card for moonshotai/Kimi-K3.1-Pro and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Kimi K3.1 Pro: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (moonshotai/Kimi-K3.1-Pro) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 96 .safetensors files listed”
LicenceKimi K3.1 Pro LicenseMoonshot AI model card, checked 2026-11-16
Quote
“Kimi K3.1 Pro is released under the Kimi K3.1 Pro License.”
Total parameters2.8TMoonshot AI model card, checked 2026-11-16
Quote
“Total Parameters … 2.8T”
Active parameters per token104BMoonshot AI model card, checked 2026-11-16
Quote
“Activated Parameters … 104B”
Context length1 million tokensMoonshot AI model card, checked 2026-11-16
Quote
“With a 1-million-token context window”
Input and outputImage and text in, text out (the card's task tag is image-text-to-text)Moonshot AI model card metadata, checked 2026-11-16
Quote
“pipeline_tag: image-text-to-text”
Tool callingYesMoonshot AI model card, checked 2026-11-16
Quote
“For multi-turn conversations and tool calls, Kimi K3.1 Pro requires the complete assistant message”
First published on Hugging Face (not necessarily the release date)2026-11-02Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2026-11-02T04:13:51.000Z"”

Kimi K3.1 Pro 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 5% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Kimi K3.1 Pro API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest promo
moonshotai/Kimi-K3.1-Pro
Notes and source quote

Promotional price, 5% off list (list 2.0 in / 10.0 out).

“$1.90 in $9.50 out $0.19 cached / 1M tokens”
USD 1.90USD 0.19USD 9.50USD 3.801,048,576not statedDeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2AkashML promo
moonshotai/Kimi-K3.1-Pro
Notes and source quote

Labelled "Limited Trial" on AkashML.

“Price (per 1M Tokens) Input Output Cache Read Kimi K3.1 Pro $1.75 $10.00 $0.18”
USD 1.75USD 0.18USD 10USD 3.8131,048,576not statedAkashML page
checked 2026-11-15
re-checked 2026-11-16
3Moonshot AI maker
kimi-k3.1-pro
Notes and source quote

Cache writes are billed separately (5m and 1h TTL).

“kimi-k3.1-pro | $2.00 / MTok | $10.00 / MTok | $0.20 / MTok | $2.00 / MTok | $4.00 / MTok”
USD 2USD 0.20USD 10USD 41,048,576not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16
4Alibaba Cloud
kimi-k3.1-pro
Notes and source quote

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

“kimi-k3.1-pro International $2 Cached input: $0.2 $10”
USD 2USD 0.20USD 10USD 4not statednot statedAlibaba Cloud page
checked 2026-11-14
re-checked 2026-11-16
5Baseten
Notes and source quote

Context from the model library page (https://www.baseten.co/library/kimi-k31-pro/), stated as 1M / 1,048,576.

“Kimi K3.1 Pro $2.00 $0.20 $10.00”
USD 2USD 0.20USD 10USD 41,048,576not statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
6DigitalOcean
Notes and source quote

DigitalOcean-hosted.

“Kimi K3.1 Pro — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$10.00$0.20”
USD 2USD 0.20USD 10USD 4not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
7Featherless
moonshotai/Kimi-K3.1-Pro
Notes and source quote

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

“PRICING: INPUT $2 / CACHED $0.2 / OUTPUT $10”
USD 2USD 0.20USD 10USD 4262,144MXFP4Featherless page
checked 2026-11-15
re-checked 2026-11-16
8Fireworks AI
accounts/fireworks/models/kimi-k3p1-pro
Notes and source quote
“Kimi K3.1 Pro | $2.00 / $0.20 / $10.00 | $3.00 / $0.30 / $15.00”
USD 2USD 0.20USD 10USD 41,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
9GMI Cloud
moonshotai/kimi-k3.1-pro
Notes and source quote
“Price (per 1M tokens) Input $2.00 Output $10.00 Cache Read $0.20 Cache Write -”
USD 2USD 0.20USD 10USD 41,048,576FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
10Novita AI
moonshotai/kimi-k3.1-pro
Notes and source quote

Cache write (5m) 2 per 1M.

“Kimi K3.1 Pro 1M $2 /Mt · Cache Read $0.2 /Mt · Cache Write(5m) $2 /Mt · Cache Write(1h) $4 /Mt $10 /Mt”
USD 2USD 0.20USD 10USD 41,048,576not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
11Parasail
Notes and source quote
“Kimi K3.1 Pro $2.00 $10.00 $0.20”
USD 2USD 0.20USD 10USD 4not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
12Together AI
Notes and source quote
“Kimi K3.1 Pro $2.00 $0.20 (cached) $10.00”
USD 2USD 0.20USD 10USD 4not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
13Venice
kimi-k3-1-pro
Notes and source quote
“| Kimi K3.1 Pro | `kimi-k3-1-pro` | $2.00 | $10.00 | $0.20 | — | Private |”
USD 2USD 0.20USD 10USD 41,000,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
—Moonshot AI maker batch
kimi-k3.1-pro
Notes and source quote

Batch API, billed at 60% of the standard price. Cache writes are billed separately (5m and 1h TTL).

“kimi-k3.1-pro | $1.20 / MTok | $6.00 / MTok | $0.12 / MTok | $1.20 / MTok | $2.40 / MTok”
USD 1.20USD 0.12USD 6USD 2.401,048,576not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot promo
moonshotai/Kimi-K3.1-Pro
Notes and source quote

Flex service tier (0.8× standard). Promotional price, 5% off list (list 2.0 in / 10.0 out).

“Flex (0.8×) $1.52 $7.60 $0.152”
USD 1.52USD 0.152USD 7.60USD 3.041,048,576not statedDeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority promo
moonshotai/Kimi-K3.1-Pro
Notes and source quote

Priority service tier (1.5× standard). Promotional price, 5% off list (list 2.0 in / 10.0 out).

“Priority (1.5×) $2.85 $14.25 $0.285”
USD 2.85USD 0.285USD 14.25USD 5.701,048,576not statedDeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI priority
accounts/fireworks/models/kimi-k3p1-pro
Notes and source quote

Priority mode.

“Kimi K3.1 Pro | Priority $3.00 / $0.30 / $15.00”
USD 3USD 0.30USD 15USD 61,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—Moonshot AI maker fast
kimi-k3.1-pro-highspeed
Notes and source quote

Highspeed variant, API model kimi-k3.1-pro-highspeed. Cache writes are billed separately (5m and 1h TTL).

“kimi-k3.1-pro-highspeed | $4.00 / MTok | $20.00 / MTok | $0.20 / MTok | $4.00 / MTok | $8.00 / MTok”
USD 4USD 0.20USD 20USD 81,048,576not statedMoonshot AI page
checked 2026-11-14
re-checked 2026-11-16
—Novita AI fast
moonshotai/kimi-k3.1-pro-highspeed
Notes and source quote

Kimi K3.1 Pro Highspeed variant. Cache write (5m) 4 per 1M.

“Kimi K3.1 Pro Highspeed 1M $4 /Mt · Cache Read $0.2 /Mt · Cache Write(5m) $4 /Mt · Cache Write(1h) $8 /Mt $20 /Mt”
USD 4USD 0.20USD 20USD 81,048,576not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock fast
Notes and source quote

Only the Highspeed variant is listed. US cross-region (US CRIS) row; Global CRIS is $4.00 / $20.00 / cache read $0.20. Cache write (30 min) $5.50.

“Kimi K3.1 Pro - Highspeed … US CRIS $4.40 $22.00 $0.22 $5.50”
USD 4.40USD 0.22USD 22USD 8.80not statednot statedAmazon Bedrock 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 K3.1 Pro 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 K3.1 Pro, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfra (promo)USD 249.66USD 475.38USD 1,659
AkashML (promo)USD 252.72USD 456.96USD 1,648
Moonshot AI (maker)USD 262.80USD 500.40USD 1,746
Alibaba CloudUSD 262.80USD 500.40USD 1,746
BasetenUSD 262.80USD 500.40USD 1,746
DigitalOceanUSD 262.80USD 500.40USD 1,746
FeatherlessUSD 262.80USD 500.40USD 1,746
Fireworks AIUSD 262.80USD 500.40USD 1,746
GMI CloudUSD 262.80USD 500.40USD 1,746
Novita AIUSD 262.80USD 500.40USD 1,746
ParasailUSD 262.80USD 500.40USD 1,746
Together AIUSD 262.80USD 500.40USD 1,746
VeniceUSD 262.80USD 500.40USD 1,746

For the support chatbot, the cheapest price (DeepInfra, USD 249.66 a month) saves USD 13.14 against the median (USD 262.80). For the coding agent the gap is USD 98.10 a month (6% lower). The winner changes with the workload: AkashML wins the cache-heavy agent, DeepInfra the chatbot.

Which Kimi K3.1 Pro provider is cheapest for your traffic?

AkashML has the lowest input price (USD 1.75) and DeepInfra the lowest output price (USD 9.50). They cost the same at 3.3 input tokens per output token. With more input than that, as with long prompts or retrieval, AkashML is cheaper; with less, as with long answers, DeepInfra is.

Kimi K3.1 Pro: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfraUSD 3.80 cheapestUSD 3.159 cheapestUSD 2.646 cheapest
AkashMLUSD 3.813USD 3.224USD 2.753
Moonshot AI (maker)USD 4USD 3.325USD 2.785
Alibaba CloudUSD 4USD 3.325USD 2.785
BasetenUSD 4USD 3.325USD 2.785
DigitalOceanUSD 4USD 3.325USD 2.785

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 7 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.

All 13 providers publish a cached-input price below the input price: DeepInfra (90% off), AkashML (90% off), Moonshot AI (90% off), Alibaba Cloud (90% off), Baseten (90% off) and 8 more.

Context windows differ: 1,048,576 tokens at DeepInfra, AkashML, Moonshot AI and 4 more; 1,000,000 tokens at Venice; 262,144 tokens at Featherless. Alibaba Cloud, DigitalOcean, Parasail and Together AI do not state one. The cheapest row is not always the one that fits a long prompt.

What does Kimi K3.1 Pro 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 K3.1 Pro:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.435Alibaba Cloud
Arabic MSAUSD 0.959Alibaba Cloud
HindiUSD 1.14Alibaba Cloud
ChineseUSD 1.09Alibaba Cloud
CodeUSD 0.519Alibaba Cloud

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.

Estimate your own bill

The Moonshot AI models whose cheapest standard price is closest to Kimi K3.1 Pro's (USD 3.80 blended):

Moonshot AI models priced closest to Kimi K3.1 Pro
ModelCheapest inputCheapest outputMax contextProviders
Kimi K3USD 1.85USD 9.501,048,57618
Kimi K2.7 CodeUSD 0.60USD 3262,14412
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

Priced closest from other makers: Claude Sonnet 5 (Anthropic, USD 4) · Claude Sonnet 5.5 (Anthropic, USD 4) · Gemini 4 Argon (Google, USD 4).

Compare Kimi K3.1 Pro with

Also compared: vs Kimi K3.

Every Kimi K3.1 Pro 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 K3.1 Pro API cost per token?

From USD 1.75 per 1M input tokens (USD 0.00000175 per token) and USD 9.50 per 1M output tokens (USD 0.0000095 per token) at the lowest standard prices we found, which can come from different providers. The median of 13 standard prices is USD 2 input and USD 10 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 K3.1 Pro?

Among the 13 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 3.80 per 1M). For input alone the lowest price is USD 1.75 (AkashML); for output alone, USD 9.50 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Kimi K3.1 Pro cheaper from a host than from Moonshot AI?

Yes. DeepInfra charges USD 1.90 input and USD 9.50 output per 1M tokens, 5% below Moonshot AI's own USD 2 / USD 10 on the 3:1 blend (a promotional price).

Does Kimi K3.1 Pro have cached input pricing?

All 13 standard prices include one. The lowest is USD 0.18 per 1M at AkashML; the median is USD 0.20. Providers without one bill cached input at the input price. What cached input means.

What is the Kimi K3.1 Pro context window?

Up to 1,048,576 tokens. 2 standard prices come with less, down to 262,144 tokens (Featherless and 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 K3.1 Pro?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,648 a month at AkashML, USD 1,746 at the median price and USD 1,746 at Venice. Try your own numbers.

Is there a batch, flex or priority price for Kimi K3.1 Pro?

Yes: batch from Moonshot AI at USD 1.20 / USD 6; flex / spot from DeepInfra at USD 1.52 / USD 7.60; priority from DeepInfra at USD 2.85 / USD 14.25; fast from Moonshot AI at USD 4 / USD 20 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 K3.1 Pro free to use through an API?

No provider in our data lists a free price for Kimi K3.1 Pro as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is Kimi K3.1 Pro open source, with open weights, and what is its licence?

Moonshot AI publishes the weights on Hugging Face as moonshotai/Kimi-K3.1-Pro, in a public repository with no access gate. The licence, as the Moonshot AI model card states it: Kimi K3.1 Pro License. Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Moonshot AI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does Kimi K3.1 Pro have?

Total parameters, as the Moonshot AI model card states them: 2.8T. Active parameters per token: 104B. (checked 2026-11-16; BroadNet did not verify these figures.)

Does Kimi K3.1 Pro support tool calling?

Yes, according to the Moonshot AI model card: “For multi-turn conversations and tool calls, Kimi K3.1 Pro requires the complete assistant message” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.

How do I call Kimi K3.1 Pro with the OpenAI SDK?

BroadNet does not serve Kimi K3.1 Pro. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: Alibaba Cloud Model Studio (https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, model kimi-k3.1-pro), DeepInfra (https://api.deepinfra.com/v1/openai, model moonshotai/Kimi-K3.1-Pro), Fireworks AI (https://api.fireworks.ai/inference/v1, model accounts/fireworks/models/kimi-k3p1-pro) and Together AI (https://api.together.ai/v1). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity