InferIndex
Language, English, EN
Account

ModelsMoonshot AIKimi K2.5

Kimi K2.5

moonshotai/kimi-k2.5262k 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.
$1.20
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.
$1.59
Offers
48
Providers
28

Cheapest right now

DeepInfra

via Hugging FaceThe provider's published policy: prompts are not used for training.

262k

$0.90 blended / 1M tokens

+12.7%7D
in
$0.45
out
$2.25
Cached input
–
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

Public leaderboards

  • Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control).Thinking setting #65 of 419Best rank in the source's rank spread, 65th to 92nd, given the confidence intervals of all ranked models. 80th by score. 1,450 1,446 to 1,453Arena Score · 74,682 votes listed as “Kimi K2.5 (Thinking)”
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026).Thinking setting #80 of 152Best rank in the source's rank spread, 80th to 93rd, given the confidence intervals of all ranked models. 85th by score. 1,436 1,431 to 1,441Arena Score · 20,008 votes listed as “Kimi K2.5 (Thinking)”

Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours

Kimi K2.5 costs from $0.90 per million tokens (at a 3:1 input:output mix): the cheapest of 18 comparable offers, at DeepInfra, checked on ; 48 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 (30)

  • $0.762 · Embercloud via LLM API · cannot be designated the cheapest
  • $0.781 · NanoGPT via NanoGPT · cannot be designated the cheapest
  • $0.888 · Avian · cannot be designated the cheapest
  • $0.90 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.90 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.90 · Martian via Martian · cannot be designated the cheapest
  • $0.90 · DeepInfra via LLM Gateway · cannot be designated the cheapest
  • $0.90 · DeepInfra via Requesty · another route of the same provider
  • $0.993 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.993 · AtlasCloud via OpenRouter · another route of the same provider
  • $1.00 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $1.00 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $1.00 · Nebius via LLM Gateway · cannot be designated the cheapest
  • $1.08 · TensorX via Eden AI · cannot be designated the cheapest
  • $1.08 · Together via LLM Gateway · cannot be designated the cheapest
  • $1.11 · io.net · cannot be designated the cheapest
  • $1.14 · Novita via OpenRouter · another route of the same provider
  • $1.20 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $1.20 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $1.20 · Amazon Bedrock via Kilo Gateway · cannot be designated the cheapest
  • $1.20 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $1.20 · Novita via Hugging Face · another route of the same provider
  • $1.20 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $1.20 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $1.20 · Moonshot AI via Requesty · another route of the same provider
  • $1.20 · Amazon Bedrock via OpenRouter · another route of the same provider
  • $1.23 · Venice via OpenRouter · another route of the same provider
  • $1.24 · Qiniu · cannot be designated the cheapest
  • $1.24 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $1.30 · Venice via Kilo Gateway · cannot be designated the cheapest

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$0.70, NanoGPT–
2026-10-03$0.70, NanoGPT–
2026-10-04$0.70, NanoGPT–
2026-10-05$0.70, NanoGPT–
2026-10-06$0.70, NanoGPT–
2026-10-07$0.70, NanoGPT–
2026-10-08$0.70, NanoGPT–
2026-10-09$0.70, NanoGPT–
2026-10-10$0.70, NanoGPT–
2026-10-11$0.70, NanoGPT–
2026-10-12$0.70, NanoGPT–
2026-10-13$0.762, Embercloud–
2026-10-14$0.762, Embercloud–
2026-10-15$0.762, Embercloud–
2026-10-16$0.762, Embercloud–
2026-10-17$0.762, Embercloud–
2026-10-18$0.762, Embercloud–
2026-10-19$0.799, Embercloud–
2026-10-20$0.799, Embercloud–
2026-10-21$0.799, Embercloud–
2026-10-22$0.799, Embercloud–
2026-10-23$0.799, Embercloud–
2026-10-24$0.799, Embercloud–
2026-10-25$0.799, Embercloud–
2026-10-26$0.799, Embercloud–
2026-10-27$0.799, Embercloud–
2026-10-28$0.799, Embercloud–
2026-10-29$0.90, DeepInfra–
2026-10-30$0.90, DeepInfra–
2026-10-31$0.90, DeepInfra–

Cheapest offer

Offers

The 25 cheapest of 48 offers

Offers for Kimi K2.5, 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 Embercloudvia LLM API 0.356 1.98 0.762 – – Unconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LLM API (opens in a new tab)
2 NanoGPT 0.375 2.00 0.781 – 262k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
Go to offer at NanoGPT (opens in a new tab)
3 Avian 0.45  2.20 0.888 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Avian (opens in a new tab)
4 DeepInfravia Eden AI 0.45  2.25 0.90  – 262k United States 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
5 DeepInfravia Hugging Face 0.45  2.25 0.90  – 262k United States
See pricing at Hugging Face (opens in a new tab)
6 FastRouter 0.45  2.25 0.90  – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at FastRouter (opens in a new tab)
7 Martian 0.45  2.25 0.90  – – 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)
8 DeepInfravia LLM Gateway 0.45  2.25 0.90  – – United States Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
9 DeepInfravia Requesty 0.45  2.25 0.90  – 262k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
See pricing at Requesty (opens in a new tab)
10 AtlasCloud 0.49  2.50 0.993 int4 262k
See pricing at AtlasCloud (opens in a new tab)
11 AtlasCloudvia Kilo Gateway 0.49  2.50 0.993 int4 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)
12 AtlasCloudvia OpenRouter 0.49  2.50 0.993 int4 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)
13 SiliconFlowvia Kilo Gateway 0.50  2.50 1.00  int4 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)
14 Nous Portal 0.50  2.50 1.00  – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 9 price changes in 7 days. Over that period: input $0.49 – $0.50, output $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.
See pricing at Nous Portal (opens in a new tab)
15 Nebiusvia LLM Gateway 0.50  2.50 1.00  – – worldwide Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
16 SiliconFlowvia OpenRouter 0.50  2.50 1.00  int4 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)
17 TensorXvia Eden AI 0.50  2.80 1.08  int4 262k 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
18 Togethervia LLM Gateway 0.50  2.80 1.08  – – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
19 io.net 0.538 2.84 1.11  – 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
20 Novitavia OpenRouter 0.57  2.85 1.14  – 262k Price drop observed: The blended price is 5% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 30, 2026Fee 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)
21 Alibabavia LLM Gateway 0.574 3.01 1.18  fp8 – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
22 Cloudflare 0.60  3.00 1.20  – –
See pricing at Cloudflare (opens in a new tab)
23 Novita 0.60  3.00 1.20  – 262k
See pricing at Novita (opens in a new tab)
24 Amazon Bedrockvia Eden AI 0.60  3.00 1.20  – 262k 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
25 Amazon Bedrockvia Eden AI 0.60  3.00 1.20  – 262k United States 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

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.

  • Embercloud

    $0.762

    LLM API

    in
    $0.356
    out
    $1.98
    Precision
    –
    Context
    –

    Training terms not publishedUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • NanoGPT

    $0.781

    NanoGPT

    in
    $0.375
    out
    $2.00
    Precision
    –
    Context
    262k

    No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists

    Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

  • Avian

    $0.888

    direct

    in
    $0.45 
    out
    $2.20
    Precision
    –
    Context
    262k

    No training on promptsUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest

    See pricing See pricing at Avian (opens in a new tab)at Avian

  • DeepInfra

    $0.90

    Eden AI

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.90

    Hugging Face

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    262k

    No training on promptsUnited States

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • FastRouter

    $0.90

    FastRouter

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    262k

    Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Go to offer Go to offer at FastRouter (opens in a new tab)via FastRouter

  • Martian

    $0.90

    Martian

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    –

    Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Martian (opens in a new tab)via Martian

  • DeepInfra

    $0.90

    LLM Gateway

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    –

    No training on promptsUnited StatesFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • DeepInfra

    $0.90

    Requesty

    in
    $0.45 
    out
    $2.25
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    See pricing See pricing at Requesty (opens in a new tab)via Requesty

  • AtlasCloud

    $0.993

    direct

    in
    $0.49 
    out
    $2.50
    Precision
    int4
    Context
    262k

    Training terms not published

    See pricing See pricing at AtlasCloud (opens in a new tab)at AtlasCloud

  • AtlasCloud

    $0.993

    Kilo Gateway

    in
    $0.49 
    out
    $2.50
    Precision
    int4
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway

  • AtlasCloud

    $0.993

    OpenRouter

    in
    $0.49 
    out
    $2.50
    Precision
    int4
    Context
    262k

    Training terms not publishedFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • SiliconFlow

    $1.00

    Kilo Gateway

    in
    $0.50 
    out
    $2.50
    Precision
    int4
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway

  • Nous Portal

    $1.00

    Nous Portal

    in
    $0.50 
    out
    $2.50
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 9 price changes in 7 days. Over that period: input $0.49 – $0.50, output $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.backend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal

  • Nebius

    $1.00

    LLM Gateway

    in
    $0.50 
    out
    $2.50
    Precision
    –
    Context
    –

    Training terms not publishedworldwideFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • SiliconFlow

    $1.00

    OpenRouter

    in
    $0.50 
    out
    $2.50
    Precision
    int4
    Context
    262k

    Training terms not publishedFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • TensorX

    $1.08

    Eden AI

    in
    $0.50 
    out
    $2.80
    Precision
    int4
    Context
    262k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • Together

    $1.08

    LLM Gateway

    in
    $0.50 
    out
    $2.80
    Precision
    –
    Context
    –

    No training on promptsFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • io.net

    $1.11

    direct

    in
    $0.538
    out
    $2.84
    Precision
    –
    Context
    262k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: io.net (opens in a new tab)No public price page for this model

  • Novita

    $1.14

    OpenRouter

    in
    $0.57 
    out
    $2.85
    Precision
    –
    Context
    262k

    No training on promptsPrice drop observed: The blended price is 5% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 30, 2026Fee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Alibaba

    $1.18

    LLM Gateway

    in
    $0.574
    out
    $3.01
    Precision
    fp8
    Context
    –

    No training on promptsFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • Cloudflare

    $1.20

    direct

    in
    $0.60 
    out
    $3.00
    Precision
    –
    Context
    –

    No training on prompts

    See pricing See pricing at Cloudflare (opens in a new tab)at Cloudflare

  • Novita

    $1.20

    direct

    in
    $0.60 
    out
    $3.00
    Precision
    –
    Context
    262k

    No training on prompts

    See pricing See pricing at Novita (opens in a new tab)at Novita

  • Amazon Bedrock

    $1.20

    Eden AI

    in
    $0.60 
    out
    $3.00
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • Amazon Bedrock

    $1.20

    Eden AI

    in
    $0.60 
    out
    $3.00
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model
Show all 48 offers

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. DeepInfra$60.75per month
  2. AtlasCloud$66.90per month+$6.15 vs the cheapest
  3. SiliconFlow$67.50per month+$6.75 vs the cheapest

Host it yourself instead? See the break-even

Compare Kimi K2.5 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-k2.5
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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