InferIndex
Language, English, EN
Account

ModelsMiniMaxMiniMax M2.5

MiniMax M2.5

minimax/minimax-m2.5198k 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.
$0.525
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.
$0.63
Offers
68
Providers
34

Cheapest right now

Venice

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

198k

$0.44 blended / 1M tokens

-6.9%7D
in
$0.27
out
$0.95
Cached input
$0.03

Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

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). #165 of 419Best rank in the source's rank spread, 165th to 192nd, given the confidence intervals of all ranked models. 179th by score. 1,391 1,387 to 1,395Arena Score · 42,783 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #95 of 152Best rank in the source's rank spread, 95th to 113th, given the confidence intervals of all ranked models. 107th by score. 1,386 1,378 to 1,395Arena Score · 7,594 votes

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

MiniMax M2.5 costs from $0.44 per million tokens (at a 3:1 input:output mix): the cheapest of 23 comparable offers, at Venice, checked on ; 68 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 (45)

  • $0.39 · Glama via Glama · cannot be designated the cheapest
  • $0.40 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.44 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.44 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.45 · Embercloud via LLM API · cannot be designated the cheapest
  • $0.473 · Avian · cannot be designated the cheapest
  • $0.473 · Martian via Martian · cannot be designated the cheapest
  • $0.521 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.521 · AtlasCloud via OpenRouter · another route of the same provider
  • $0.525 · Amazon Bedrock via LLM API · cannot be designated the cheapest
  • $0.525 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.525 · DigitalOcean via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · MiniMax via Eden AI · cannot be designated the cheapest
  • $0.525 · MiniMax via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Novita via Hugging Face · another route of the same provider
  • $0.525 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Novita via LLM API · cannot be designated the cheapest
  • $0.525 · StreamLake via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · TensorX via Eden AI · cannot be designated the cheapest
  • $0.525 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.525 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.525 · Novita via LLM Gateway · another route of the same provider
  • $0.525 · MiniMax via Requesty · another route of the same provider
  • $0.525 · Nebius via LLM Gateway · cannot be designated the cheapest
  • $0.525 · Together via LLM Gateway · cannot be designated the cheapest
  • $0.525 · Minimax via OpenRouter · another route of the same provider
  • $0.525 · Novita via OpenRouter · another route of the same provider
  • $0.53 · Poe via Poe · price converted from points
  • $0.552 · UCloud · cannot be designated the cheapest
  • $0.552 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.61 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.62 · io.net · cannot be designated the cheapest
  • $0.63 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.63 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.983 · Greenpt via Eden AI · cannot be designated the cheapest
  • $1.05 · MiniMax via Kilo Gateway · cannot be designated the cheapest
  • $1.05 · Novita via LLM API · cannot be designated the cheapest
  • $1.05 · FastRouter via FastRouter · cannot be designated the cheapest
  • $1.05 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $1.05 · Vercel AI Gateway via Vercel AI Gateway · priority tier
  • $1.05 · MiniMax via LLM Gateway · priority tier
  • $1.05 · MiniMax via Requesty · priority tier
  • $1.05 · Minimax via OpenRouter · priority tier
  • $1.10 · Qiniu · 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$0.39, Glama–
2026-10-03$0.39, Glama–
2026-10-04$0.39, Glama–
2026-10-05$0.39, Glama–
2026-10-06$0.39, Glama–
2026-10-07$0.39, Glama–
2026-10-08$0.39, Glama–
2026-10-09$0.39, Glama–
2026-10-10$0.39, Glama–
2026-10-11$0.39, Glama–
2026-10-12$0.39, Glama–
2026-10-13$0.39, Glama–
2026-10-14$0.39, Glama–
2026-10-15$0.39, Glama–
2026-10-16$0.39, Glama–
2026-10-17$0.39, Glama–
2026-10-18$0.39, Glama–
2026-10-19$0.44, Venice–
2026-10-20$0.44, Nous Portal–
2026-10-21$0.44, Venice–
2026-10-22$0.44, Venice–
2026-10-23$0.44, Venice–
2026-10-24$0.473, StreamLake–
2026-10-25$0.473, NanoGPT–
2026-10-26$0.44, Venice–
2026-10-27$0.44, Venice–
2026-10-28$0.44, Venice–
2026-10-29$0.44, Venice–
2026-10-30$0.44, Venice–
2026-10-31$0.44, Venice–

Cheapest offer

Offers

The 25 cheapest of 68 offers

Offers for MiniMax M2.5, 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 Glama 0.22  0.90 0.39  – 197k Unverified. No public page for this offer: listed, not designated cheapest
2 DeepInfravia Eden AI 0.15  1.15 0.40  – 197k United States Unverified. No public page for this offer: listed, not designated cheapest
3 Venicevia Kilo Gateway 0.27  0.95 0.44  – 198k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
4 Nous Portal 0.27  0.95 0.44  – 205k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 10 price changes in 7 days. Over that period: input $0.27 – $0.30, output $0.95 – $1.20 per million tokens. An offer whose price changes this often is not selected as the cheapest.
5 Venicevia OpenRouter 0.27  0.95 0.44  – 198k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
6 Embercloudvia LLM API 0.20  1.20 0.45  – – 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
7 NanoGPT 0.27  1.08 0.473 – 205k
8 Avian 0.27  1.08 0.473 – 197k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
9 Martian 0.27  1.08 0.473 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
10 StreamLakevia OpenRouter 0.27  1.08 0.473 – 200k Price drop observed: The blended price is 10% 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 31). Offers are ranked with this fee included.
11 Inceptronvia Requesty 0.28  1.10 0.485 – 197k European Union Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.
12 CloudFerro 0.291 1.16 0.508 – – European Union
13 AtlasCloud 0.295 1.20 0.521 fp8 197k
14 Featherless 0.295 1.20 0.521 – 205k
15 AtlasCloudvia Kilo Gateway 0.295 1.20 0.521 fp8 197k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
16 AtlasCloudvia OpenRouter 0.295 1.20 0.521 fp8 197k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
17 Novita 0.30  1.20 0.525 fp8 205k
18 Amazon Bedrockvia LLM API 0.30  1.20 0.525 – – 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
19 Arkanecloudvia Eden AI 0.30  1.20 0.525 – 196k Unverified. No public page for this offer: listed, not designated cheapest
20 DigitalOceanvia Kilo Gateway 0.30  1.20 0.525 – 66k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
21 GMICloudvia Kilo Gateway 0.30  1.20 0.525 fp8 197k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
22 MiniMaxvia Eden AI 0.30  1.20 0.525 fp8 205k Unverified. No public page for this offer: listed, not designated cheapest
23 MiniMaxvia Kilo Gateway 0.30  1.20 0.525 – 205k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
24 Novitavia Hugging Face 0.30  1.20 0.525 fp8 205k
25 Novitavia Kilo Gateway 0.30  1.20 0.525 fp8 205k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

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.

  • Glama

    $0.39

    Glama

    in
    $0.22 
    out
    $0.90
    Precision
    –
    Context
    197k

    No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

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

    in
    $0.15 
    out
    $1.15
    Precision
    –
    Context
    197k

    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
  • Venice

    $0.44

    Kilo Gateway

    in
    $0.27 
    out
    $0.95
    Precision
    –
    Context
    198k

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

  • Nous Portal

    in
    $0.27 
    out
    $0.95
    Precision
    –
    Context
    205k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 10 price changes in 7 days. Over that period: input $0.27 – $0.30, output $0.95 – $1.20 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.

  • Venice

    $0.44

    OpenRouter

    in
    $0.27 
    out
    $0.95
    Precision
    –
    Context
    198k

    No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

  • LLM API

    in
    $0.20 
    out
    $1.20
    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

  • NanoGPT

    $0.473

    NanoGPT

    in
    $0.27 
    out
    $1.08
    Precision
    –
    Context
    205k

    No training on prompts

  • Avian

    $0.473

    direct

    in
    $0.27 
    out
    $1.08
    Precision
    –
    Context
    197k

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

  • Martian

    $0.473

    Martian

    in
    $0.27 
    out
    $1.08
    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.

  • OpenRouter

    in
    $0.27 
    out
    $1.08
    Precision
    –
    Context
    200k

    Training terms not publishedPrice drop observed: The blended price is 10% 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 31). Offers are ranked with this fee included.

  • Inceptron

    $0.485

    Requesty

    in
    $0.28 
    out
    $1.10
    Precision
    –
    Context
    197k

    Prompts may be used for trainingEuropean UnionFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.

  • direct

    in
    $0.291
    out
    $1.16
    Precision
    –
    Context
    –

    No training on promptsEuropean Union

  • direct

    in
    $0.295
    out
    $1.20
    Precision
    fp8
    Context
    197k

    Training terms not published

  • direct

    in
    $0.295
    out
    $1.20
    Precision
    –
    Context
    205k

    Training terms not published

  • Kilo Gateway

    in
    $0.295
    out
    $1.20
    Precision
    fp8
    Context
    197k

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

  • OpenRouter

    in
    $0.295
    out
    $1.20
    Precision
    fp8
    Context
    197k

    Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

  • Novita

    $0.525

    direct

    in
    $0.30 
    out
    $1.20
    Precision
    fp8
    Context
    205k

    No training on prompts

  • LLM API

    in
    $0.30 
    out
    $1.20
    Precision
    –
    Context
    –

    No training on promptsUnconfirmed. 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

  • Eden AI

    in
    $0.30 
    out
    $1.20
    Precision
    –
    Context
    196k

    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
  • Kilo Gateway

    in
    $0.30 
    out
    $1.20
    Precision
    –
    Context
    66k

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

  • GMICloud

    $0.525

    Kilo Gateway

    in
    $0.30 
    out
    $1.20
    Precision
    fp8
    Context
    197k

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

  • MiniMax

    $0.525

    Eden AI

    in
    $0.30 
    out
    $1.20
    Precision
    fp8
    Context
    205k

    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
  • MiniMax

    $0.525

    Kilo Gateway

    in
    $0.30 
    out
    $1.20
    Precision
    –
    Context
    205k

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

  • Novita

    $0.525

    Hugging Face

    in
    $0.30 
    out
    $1.20
    Precision
    fp8
    Context
    205k

    No training on prompts

  • Novita

    $0.525

    Kilo Gateway

    in
    $0.30 
    out
    $1.20
    Precision
    fp8
    Context
    205k

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

Show all 68 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. Venice$30.45per month
  2. NanoGPT$32.40per month+$1.95 vs the cheapest
  3. StreamLake$32.40per month+$1.95 vs the cheapest

Host it yourself instead? See the break-even

Compare MiniMax M2.5 with

Related models

More from MiniMax

All MiniMax 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=minimax/minimax-m2.5
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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