InferIndex
Language, English, EN
Account

ModelsMiniMaxMiniMax M3

MiniMax M3

minimax/minimax-m3131k 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.
$1.17
Offers
77
Providers
41

Cheapest right now

Ambient

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

directYou buy access straight from the company that runs the model on its servers. · 131k

$0.413 blended / 1M tokens

No change7D
in
$0.23
out
$0.96
Cached input
$0.05

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). #84 of 419Best rank in the source's rank spread, 84th to 116th, given the confidence intervals of all ranked models. 98th by score. 1,439 1,435 to 1,443Arena Score · 68,611 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #66 of 152Best rank in the source's rank spread, 66th to 74th, given the confidence intervals of all ranked models. 69th by score. 1,483 1,478 to 1,489Arena Score · 21,032 votes
  • Agent Arena aggregateThe Agent Arena aggregate score: a score of another kind (not an Arena score), on a scale of its own; it cannot be compared with the other series. #49 of 57Best rank in the source's rank spread, 49th to 52nd, given the confidence intervals of all ranked models. 51st by score. −0.102 −0.113 to −0.090IPS score · 3,541,903 observations

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 M3 costs from $0.413 per million tokens (at a 3:1 input:output mix): the lowest current price, at 2 providers, checked on ; 77 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 (49)

  • $0.413 · CoreWeave via Kilo Gateway · cannot be designated the cheapest
  • $0.42 · GMICloud via OpenRouter · another route of the same provider
  • $0.485 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.485 · DeepInfra via Hugging Face · another route of the same provider
  • $0.485 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.485 · DeepInfra via OpenRouter · another route of the same provider
  • $0.525 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.525 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Fireworks via Eden AI · 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 · Nebius via Eden AI · cannot be designated the cheapest
  • $0.525 · Nebius via LLM API · 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 · Parasail via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Tencent via Eden AI · cannot be designated the cheapest
  • $0.525 · Together via Eden AI · cannot be designated the cheapest
  • $0.525 · Together via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.525 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
  • $0.525 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.525 · Glama via Glama · cannot be designated the cheapest
  • $0.525 · Martian via Martian · cannot be designated the cheapest
  • $0.525 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.525 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.525 · Fireworks via Requesty · 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 · Tencent via Requesty · another route of the same provider
  • $0.525 · AtlasCloud via OpenRouter · another route of the same provider
  • $0.525 · Minimax via OpenRouter · another route of the same provider
  • $0.525 · Novita via OpenRouter · another route of the same provider
  • $0.525 · Together via OpenRouter · another route of the same provider
  • $0.526 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.53 · Poe via Poe · price converted from points
  • $0.55 · ModelRun via Kilo Gateway · cannot be designated the cheapest
  • $0.552 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.572 · Charm Hyper via Charm Hyper · cannot be designated the cheapest
  • $0.71 · Canopywave via LLM API · cannot be designated the cheapest
  • $0.80 · TensorX via Eden AI · cannot be designated the cheapest
  • $0.983 · Greenpt via Eden AI · cannot be designated the cheapest
  • $1.05 · Mara via Kilo Gateway · cannot be designated the cheapest
  • $1.05 · MiniMax via LLM API · cannot be designated the cheapest
  • $1.05 · StreamLake via Kilo Gateway · cannot be designated the cheapest
  • $1.05 · MiniMax via LLM Gateway · another route of the same provider
  • $1.10 · UCloud · 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$0.375, Vultr–
2026-10-03$0.375, Vultr–
2026-10-04$0.375, Vultr–
2026-10-05$0.375, Vultr–
2026-10-06$0.375, Vultr–
2026-10-07$0.375, Vultr–
2026-10-08$0.375, Vultr–
2026-10-09$0.375, Vultr–
2026-10-10$0.375, Vultr–
2026-10-11$0.375, Vultr–
2026-10-12$0.375, Vultr–
2026-10-13$0.375, Vultr–
2026-10-14$0.375, Vultr–
2026-10-15$0.375, Vultr–
2026-10-16$0.375, Vultr–
2026-10-17$0.375, Vultr–
2026-10-18$0.375, Vultr–
2026-10-19$0.413, Ambient–
2026-10-20$0.413, Ambient–
2026-10-21$0.413, Ambient–
2026-10-22$0.413, Ambient–
2026-10-23$0.413, Ambient–
2026-10-24$0.413, Ambient–
2026-10-25$0.413, Ambient–
2026-10-26$0.413, Ambient–
2026-10-27$0.413, Ambient–
2026-10-28$0.413, Ambient–
2026-10-29$0.413, Ambient–
2026-10-30$0.413, Ambient–
2026-10-31$0.413, Ambient–

Cheapest offer

Offers

The 25 cheapest of 77 offers

Offers for MiniMax M3, 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 Ambient 0.23  0.96 0.413 – 131k
2 CoreWeavevia Kilo Gateway 0.23  0.96 0.413 fp4 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
3 NanoGPT 0.23  0.96 0.413 – 512k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer existsPrice drop observed: The blended price is 21% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026
4 CoreWeavevia OpenRouter 0.23  0.96 0.413 fp4 262k 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.
5 GMICloudvia Vercel AI Gateway 0.24  0.96 0.42  fp8 1M
6 GMICloudvia OpenRouter 0.24  0.96 promo: Promotion announced by OpenRouter · −20% vs its usual price · Discount shown by the seller, no end date announced, seen on Oct 30, 20260.42  fp8 1M 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.
7 Avian 0.255 1.02 0.446 – 524k
8 DeepInfra 0.28  1.10 0.485 fp8 524k United States
9 DeepInfravia Eden AI 0.28  1.10 0.485 fp8 524k United States Unverified. No public page for this offer: listed, not designated cheapest
10 DeepInfravia Hugging Face 0.28  1.10 0.485 fp8 524k United States
11 DeepInfravia Kilo Gateway 0.28  1.10 0.485 fp8 524k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
12 Consensusprotocolvia LLM Gateway 0.28  1.10 0.485 – – 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 31). Offers are ranked with the 5% included.
13 DeepInfravia OpenRouter 0.28  1.10 0.485 fp8 524k United States 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.
14 AtlasCloud 0.30  1.20 0.525 fp8 524k
15 Novita 0.30  1.20 0.525 fp8 1M prompt up to 525K (524,288) tokens: up to 525K (524,288): $0.30 / $1.20; above that: $0.60 / $2.40 (Input / Output, per million tokens)
16 Arkanecloudvia Eden AI 0.30  1.20 0.525 – 1M Unverified. No public page for this offer: listed, not designated cheapest
17 AtlasCloudvia Kilo Gateway 0.30  1.20 0.525 fp8 524k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
18 Fireworksvia Eden AI 0.30  1.20 0.525 – 512k United States Unverified. No public page for this offer: listed, not designated cheapest
19 Fireworksvia Vercel AI Gateway 0.30  1.20 0.525 – 512k United States
20 GMICloudvia Kilo Gateway 0.30  1.20 0.525 fp8 1M Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
21 MiniMaxvia Eden AI 0.30  1.20 0.525 fp8 524k Unverified. No public page for this offer: listed, not designated cheapest
22 MiniMaxvia Kilo Gateway 0.30  1.20 0.525 – 524k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
23 MiniMaxvia Vercel AI Gateway 0.30  1.20 0.525 fp8 1M
24 Nebiusvia Eden AI 0.30  1.20 0.525 – 1M worldwide Unverified. No public page for this offer: listed, not designated cheapest
25 Nebiusvia LLM API 0.30  1.20 0.525 – – worldwideUnconfirmed. 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

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

Show all 77 offers

3 flex or batch offers hidden (lower priority, variable latency).

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. Ambient$28.20per month
  2. NanoGPT$28.20per month+$0.00 vs the cheapest
  3. GMICloud$28.80per month+$0.60 vs the cheapest

Host it yourself instead? See the break-even

Compare MiniMax M3 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-m3
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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