Models

minimax-m2.7

pinstripes · 1000K ctx · 12 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.329 Official list · Pinstripes
Avg price
$0.614 /1M · 1 outlier(s) excluded
providers
12
Tokens (24h)
26B
Volume (24h)
$12.3K est.
(3 × $0.255 + $0.550) ÷ 4 = $0.329/1M — 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 $0.255, 3:1 $0.329, 1:1 $0.403, output only $0.550 per 1M.

The board shows this model's cheapest measured offer ($0.329/1M); the smaller figure under it is the mean of the 19 offers listed below ($0.614/1M). Add those up and divide — it matches. 1 offer(s) above 10x the median were left out of the average and flagged ⚠ in the table below — they are still listed, and still compete for the cheapest price. 24h token volume (26B) 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
pinstripes Pricebook (LiteLLM) $0.255$0.550 Official list
Mara OpenRouter $0.240$0.960 1118ms 13 100% API-measured
deepinfra HuggingFace Router $0.250$1.00 903ms 75 API-measured
DeepInfra (fp8) OpenRouter $0.250$1.00 1776ms 23 97.3% API-measured
Novita (fp8) OpenRouter $0.270$1.08 4191ms 10 99.9% API-measured
novita HuggingFace Router $0.300$1.20 1421ms 36 API-measured
fireworks-ai HuggingFace Router $0.300$1.20 869ms 165 API-measured
novita-ai Novita AI $0.300$1.20 API-measured
requesty Requesty $0.300$1.20 API-measured
GMICloud (fp8) OpenRouter $0.300$1.20 2422ms 36 97.8% API-measured
Minimax (fp8) OpenRouter $0.300$1.20 1210ms 47 99.5% API-measured
AtlasCloud (fp8) OpenRouter $0.300$1.20 2125ms 33 97.6% API-measured
Fireworks OpenRouter $0.300$1.20 587ms 141 API-measured
SambaNova (minimax-m2.7-dedicated) OpenRouter $0.300$1.50 3555ms 138 96.4% API-measured
DeepInfra (turbo) OpenRouter $0.380$1.70 2255ms 61 99.9% API-measured
Groq OpenRouter $0.600$1.80 279ms 230 99.2% API-measured
sambanova Pricebook (LiteLLM) $0.600$2.40 Official list
Minimax (highspeed) OpenRouter $0.600$2.40 727ms 66 97.3% API-measured
SambaNova OpenRouter $0.600$2.40 2158ms 29 96.3% API-measured
burncloud ⚠ outlier burncloud $75.00$75.00 API-measured

Volume trend

27B 30d d-29 · 18B tokensd-28 · 20B tokensd-27 · 19B tokensd-26 · 20B tokensd-25 · 18B tokensd-24 · 15B tokensd-23 · 14B tokensd-22 · 19B tokensd-21 · 0 tokensd-20 · 0 tokensd-19 · 16B tokensd-18 · 0 tokensd-17 · 16B tokensd-16 · 15B tokensd-15 · 18B tokensd-14 · 0 tokensd-13 · 0 tokensd-12 · 0 tokensd-11 · 0 tokensd-10 · 0 tokensd-9 · 20B tokensd-8 · 0 tokensd-7 · 0 tokensd-6 · 23B tokensd-5 · 23B tokensd-4 · 26B tokensd-3 · 24B tokensd-2 · 25B tokensd-1 · 27B tokensd-0 · 26B tokens

Last 30 days: 18B → 26B (+48%); range 0–27B 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-m2.7.json. Free reuse requires attribution to tkx.org.

About

Minimax-m2.7 is an AI model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language processing tasks, listed under the org tag "pinstripes".

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

FAQ

How much does minimax-m2.7 cost?

Cheapest measured offer right now: $0.255/1M input, $0.55/1M output via pinstripes — across 12 tracked providers, refreshed hourly.

Who serves minimax-m2.7?

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-m2.7 used?

minimax-m2.7 routed 26B 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