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
Overview
MiniMax M3 on Fireworks. $0.30/$1.20 per 1M; cached $0.06.
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.
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 supportedBenchmark performance
accuracy % · higher is better- AA Intelligence Index: 44.4 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 35.4 (Tool use, planning, autonomy)
- AA-Omniscience Index: 1.4 (−100–100)
- GDPval-AA v2: 1390.7 ELO (Real-world work tasks, human baseline = 1000)
- Ranks #49 of 67 benchmarked models by average score
- Ranks #73 of 150 comparably-measured models by percentile score, across 17 independent measurements
- Ranks #26 of 150 comparably-tested models by normalized performance per dollar
- Strongest at HumanEval — 82%, #15 of 45
100 tokens/sec output
Source: Vellum LLM Leaderboard (Jun 2026), MiniMax model card · updated Jun 29, 2026 · See full rankings →
Specifications
- Provider
- Fireworks
- Context window
- 1M tokens
- Modality
- text, image
- Parameters
- Proprietary
- Open source
- Yes — open weights available
- Released
- Jun 1, 2026
- Status
- Current
- Last updated
- Jun 25, 2026
- Tags
Availability verified: Aug 9, 2026 — listed on Fireworks's own page