InferIndex
Language, English, EN
Account

ModelsMoonshot AIKimi K2 Thinking

Kimi K2 Thinking

moonshotai/kimi-k2-thinking262k context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$1.08
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$1.08
Offers
14
Providers
12

Cheapest right now

PPIO

directYou buy access straight from the company that runs the model on its servers. · 262k

$1.05 blended / 1M tokens

+0.3%7D
in
$0.601
out
$2.41
Cached input
–
See pricing See pricing at PPIO (opens in a new tab)at PPIO

Kimi K2 Thinking costs from $1.05 per million tokens (at a 3:1 input:output mix): the cheapest of 5 comparable offers, at PPIO, checked on ; 14 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (9)

  • $1.05 · Qiniu · cannot be designated the cheapest
  • $1.08 · io.net · cannot be designated the cheapest
  • $1.08 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $1.08 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $1.08 · Charm Hyper via Charm Hyper · cannot be designated the cheapest
  • $1.08 · Glama via Glama · cannot be designated the cheapest
  • $1.08 · Martian via Martian · cannot be designated the cheapest
  • $1.08 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $1.08 · Novita via OpenRouter · another route of the same provider

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

$1.08 blended / 1M tokens

in
$0.60
out
$2.50
Cached input
$0.15
Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.853, Vercel AI Gateway–
2026-10-03$0.853, Vercel AI Gateway–
2026-10-04$0.853, Vercel AI Gateway–
2026-10-05$0.853, Vercel AI Gateway–
2026-10-06$0.853, Vercel AI Gateway–
2026-10-07$0.853, Vercel AI Gateway–
2026-10-08$1.00, Alibaba–
2026-10-09$1.00, Alibaba–
2026-10-10$1.00, Alibaba–
2026-10-11$1.00, Alibaba–
2026-10-12$1.00, Alibaba–
2026-10-13$1.00, Alibaba–
2026-10-14$1.00, Alibaba–
2026-10-15$1.00, Alibaba–
2026-10-16$1.00, Alibaba–
2026-10-17$1.00, Alibaba–
2026-10-18$1.00, Alibaba–
2026-10-19$1.05, PPIO–
2026-10-20$1.05, PPIO–
2026-10-21$1.05, PPIO–
2026-10-22$1.05, PPIO–
2026-10-23$1.05, PPIO–
2026-10-24$1.05, PPIO–
2026-10-25$1.05, PPIO–
2026-10-26$1.05, PPIO–
2026-10-27$1.05, PPIO–
2026-10-28$1.05, PPIO–
2026-10-29$1.05, PPIO–
2026-10-30$1.05, PPIO–
2026-10-31$1.05, PPIO–

Cheapest offer

Offers

14 of 14 offers

Offers for Kimi K2 Thinking, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 PPIO 0.601 2.41 1.05 – 262k
See pricing at PPIO (opens in a new tab)
2 Qiniu 0.601 2.41 1.05 – 256k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Qiniu (opens in a new tab)
3 Featherless 0.60  2.50 1.08 – 33k
Go to offer at Featherless (opens in a new tab)
4 NanoGPT 0.60  2.50 1.08 – 262k
Go to offer at NanoGPT (opens in a new tab)
5 io.net 0.60  2.50 1.08 – 262k Unverified. No public page for this offer: listed, not designated cheapest
: io.net (opens in a new tab). No public price page for this model
6 Novita 0.60  2.50 1.08 bf16 262k
See pricing at Novita (opens in a new tab)
7 Amazon Bedrockvia Eden AI 0.60  2.50 1.08 – 256k Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
8 Novitavia Kilo Gateway 0.60  2.50 1.08 bf16 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
9 Charm Hyper 0.60  2.50 1.08 – – Unverified. No public page for this offer: listed, not designated cheapest
No public offer page
10 Glama 0.60  2.50 1.08 – 262k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
11 Martian 0.60  2.50 1.08 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
12 Neosantara 0.60  2.50 1.08 – 256k Singapore, Indonesia, United States
See pricing at Neosantara (opens in a new tab)
13 Nous Portal 0.60  2.50 1.08 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
14 Novitavia OpenRouter 0.60  2.50 1.08 bf16 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. PPIO$72.15per month
  2. Featherless$73.50per month+$1.35 vs the cheapest
  3. NanoGPT$73.50per month+$1.35 vs the cheapest

Host it yourself instead? See the break-even

Compare Kimi K2 Thinking with

Related models

More from Moonshot AI

All Moonshot AI models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=moonshotai/kimi-k2-thinking
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.