Models

MiniMax M3

minimax ↗ · 1049K ctx · 12 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.420 via OpenRouter
Avg price
$0.516 /1M
providers
12
Tokens (24h)
253B
Volume (24h)
$133.1K est.
(3 × $0.240 + $0.960) ÷ 4 = $0.420/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.240, 3:1 $0.420, 1:1 $0.600, output only $0.960 per 1M.

The board shows this model's cheapest measured offer ($0.420/1M); the smaller figure under it is the mean of the 18 offers listed below ($0.516/1M). Add those up and divide — it matches. 24h token volume (253B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
GMICloud (fp8) OpenRouter $0.240$0.960 2076ms 22 99.8% API-measured
0g-teetls 0G Router $0.270$1.08 API-measured
fireworks_ai Pricebook (LiteLLM) $0.300$1.20 Official list
minimax Pricebook (LiteLLM) $0.300$1.20 Official list
novita HuggingFace Router $0.300$1.20 982ms 99 API-measured
together HuggingFace Router $0.300$1.20 1291ms 15 API-measured
fireworks-ai HuggingFace Router $0.300$1.20 708ms 108 API-measured
deepinfra HuggingFace Router $0.300$1.20 385ms 33 API-measured
novita-ai Novita AI $0.300$1.20 API-measured
requesty Requesty $0.300$1.20 API-measured
Novita (fp8) OpenRouter $0.300$1.20 1747ms 55 99.7% API-measured
Venice (fp8) OpenRouter $0.300$1.20 1096ms 148 99.6% API-measured
Minimax (fp8) OpenRouter $0.300$1.20 1088ms 71 97.9% API-measured
AtlasCloud (fp8) OpenRouter $0.300$1.20 1651ms 19 99.8% API-measured
Together OpenRouter $0.300$1.20 824ms 42 99.8% API-measured
Morph OpenRouter $0.300$1.20 2294ms 21 99.9% API-measured
DeepInfra (fp8) OpenRouter $0.300$1.20 2480ms 4 99.9% API-measured
Parasail (fp8) OpenRouter $0.300$1.20 1325ms 62 90.8% API-measured

Volume trend

680B 30d d-29 · 529B tokensd-28 · 662B tokensd-27 · 666B tokensd-26 · 680B tokensd-25 · 652B tokensd-24 · 594B tokensd-23 · 516B tokensd-22 · 489B tokensd-21 · 615B tokensd-20 · 580B tokensd-19 · 592B tokensd-18 · 564B tokensd-17 · 568B tokensd-16 · 498B tokensd-15 · 397B tokensd-14 · 258B tokensd-13 · 348B tokensd-12 · 344B tokensd-11 · 312B tokensd-10 · 267B tokensd-9 · 262B tokensd-8 · 257B tokensd-7 · 302B tokensd-6 · 320B tokensd-5 · 305B tokensd-4 · 304B tokensd-3 · 276B tokensd-2 · 235B tokensd-1 · 215B tokensd-0 · 253B tokens

Last 30 days: 529B → 253B (-52%); range 215B–680B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/minimax-m3.json. Free reuse requires attribution to tkx.org.

About

Minimax-M3 is an AI model that specializes in decision-making and optimization tasks. It is served by multiple inference providers on AI model marketplaces, making it accessible for various applications that require strategic planning and risk management.

AI-generated summary from public information — is this yours?

FAQ

How much does MiniMax M3 cost?

Cheapest measured offer right now: $0.24/1M input, $0.96/1M output via GMICloud (fp8) — across 12 tracked providers, refreshed hourly.

Who serves MiniMax M3?

12 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is MiniMax M3 used?

MiniMax M3 routed 253B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings