ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

MiniMax-M3

by MiniMax

Current budget open weights cheap tier
Email me when MiniMax-M3 gets cheaper

Today's price · per 1M tokens

Input

$0.300

per 1M tokens

Output

$1.20

per 1M tokens

Blended

$0.525

blended $/1M — 3:1 weighted input:output

Cached input

$0.060

20% of input — prompt caching

Source: official MiniMax pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-09

Available on 3 hosts

cheapest blended first · $ per 1M tokens

MiniMax M3 is sold by 3 providers. Prices are per 1M tokens (blended = (3×input + 1×output) ÷ 4). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

MiniMax M3 price on every host still selling it, per 1M tokens, cheapest blended first
Host Input Output Blended vs first-party
Fireworks details → $0.300 $1.20 $0.525 0%
MiniMax first-party $0.300 $1.20 $0.525 —
Together details → $0.300 $1.20 $0.525 0%
Each host links to its provider page and official pricing. Prices refresh twice daily. MODELPRICEWATCH.COM · 2026-08-09

Overview

MiniMax's open-weight flagship built on its MSA sparse-attention architecture, combining frontier-level coding, a 1M-token context, and native multimodality. $0.30/$1.20 per 1M tokens.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 3/5
Text ✓ Image ✓ Audio Video ✓ PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 4/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal ✓ Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score63.1%
Perf per $/Mtok120.2
GPQA Diamond
93%
SWE-Bench Verified
45%
Terminal-Bench 2.1
66%
MCP Atlas
74.2%
BrowseComp
83.5%
OSWorld-Verified
70.1%
Humanity's Last Exam
22%
ARC-AGI 2
20%
AIME 2025
55%
MMMLU
76%
BFCL
65%
HumanEval
80.5%
MATH 500
70%
Independent composite scores
  • AA Intelligence Index: 45.4 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 36.1 (Tool use, planning, autonomy)
  • AA-Omniscience Index: 1.4 (−100–100)
  • GDPval-AA v2: 1389.8 ELO (Real-world work tasks, human baseline = 1000)
  • LMSYS Chatbot Arena: 1444.7 ELO (Human preference)
How it stacks up
  • Ranks #42 of 67 benchmarked models by average score
  • Ranks #65 of 150 comparably-measured models by percentile score, across 18 independent measurements
  • Ranks #22 of 150 comparably-tested models by normalized performance per dollar
  • Strongest at GPQA Diamond — 93%, #10 of 56

98.6 tokens/sec output 0.85s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 9, 2026 · See full rankings →

Specifications

Provider
MiniMax
Context window
1M tokens
Modality
text, image, video
Parameters
Proprietary
Open source
Yes — open weights available
Released
Jun 1, 2026
Status
Current
Last updated
Jun 25, 2026
Tags
open-weightsbudgetcachingmultimodal

Availability verified: Aug 9, 2026 — listed on MiniMax's own page

Try on MiniMax Official pricing page