aiticker

MiniMax · Released May 31, 2026

MiniMax M3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

ReasoningOpen weightsVision
  • Top 26%GPQA Diamond
Compare in showdown → OpenRouter ↗ All MiniMax models
Released
May 31 2026
Context window
1M 512K out
Input / 1M tokens
$0.30 from Free
Output / 1M tokens
$1.20 from Free

Where to run it

64 providers compared

Free to try on OpenCode — free endpoints are often limited-time and rate-limited. Included in MiniMax Token Plan (minimax.io), SCNet Token Plan, Volcengine Ark Coding Plan, MiniMax Token Plan (minimax.cn), OpenCode Go. Cheapest: Vultr at $0.20 / $0.90 per 1M input / output tokens — 70% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
OpenCodefree · may be limited-time Free Free Free200K32K— Free
MiniMax Token Plan (minimax.io)subscription plan Plan Plan Plan1M524K— Plan
SCNet Token Plansubscription plan Plan Plan Plan1M512K— Plan
Volcengine Ark Coding Plansubscription plan Plan Plan Plan1M512K— Plan
MiniMax Token Plan (minimax.cn)subscription plan Plan Plan Plan1M524K— Plan
OpenCode Gosubscription plan Plan Plan Plan1M131K— Plan
Vultr $0.20 $0.90 —524K512K— Cheapest
DeepInfraFP8 $0.22 $0.88 $0.045524K131K100%24h +3%
EmpirioLabs AI $0.23 $0.90 $0.0451M524K— +5%
CoreWeaveFP4 $0.23 $0.96 $0.05262K236K99.7%24h +10%
NanoGPT $0.23 $0.96 $0.05512K80K— +10%
Ambient $0.23 $0.96 $0.05262K262K— +10%
GMICloudFP8 $0.24 $0.96 $0.0481M524K99.5%24h +12%
Vancine $0.24 $0.96 $0.0481M512K— +12%
DeepInfraFP8 $0.28 $1.10 $0.056524K131K100%24h +29%
Boundless $0.28 $1.10 $0.0561M512K— +29%
Lilac $0.28 $1.10 $0.051M1M— +29%
DevPass (LLM Gateway) $0.28 $1.10 $0.051M512K— +29%
AIHubMix $0.29 $1.15 —1M512K— +34%
IteraCompute $0.30 $1.19 $0.051M524K— +39%
NovitaFP8 $0.30 $1.20 $0.061M131K100%24h +40%
ParasailFP8 $0.30 $1.20 $0.061M524K99.9%24h +40%
MinimaxFP8 $0.30 $1.20 $0.06524K512K99.9%24h +40%
Together $0.30 $1.20 $0.06524K472K99.1%24h +40%
AtlasCloudFP8 $0.30 $1.20 $0.06524K524K99%24h +40%
StreamLakeFP8 $0.30 $1.20 $0.061M512K98.6%24h +40%
VeniceFP8 $0.30 $1.20 $0.06524K66K97.4%24h +40%
Cortecs $0.30 $1.20 $0.061M1M— +40%
Kilo Gateway $0.30 $1.20 $0.06524K512K— +40%
Vercel AI Gateway $0.30 $1.20 $0.06512K512K— +40%
LLM Gateway $0.30 $1.20 $0.061M131K— +40%
Nebius Token Factory $0.30 $1.20 $0.301M1M— +40%
Pioneer $0.30 $1.20 $0.061M131K— +40%
Together AI $0.30 $1.20 $0.06524K524K— +40%
Requesty $0.30 $1.20 $0.061M128K— +40%
SiliconFlow $0.30 $1.20 $0.061M131K— +40%
Jalapeno Cloud $0.30 $1.20 $0.06524K512K— +40%
Fireworks AI $0.30 $1.20 $0.06512K512K— +40%
ZenMux $0.30 $1.20 $0.061M512K— +40%
Novita AI $0.30 $1.20 $0.061M131K— +40%
ClinePass $0.30 $1.20 $0.061M512K— +40%
Abacus $0.30 $1.20 —1M131K— +40%
Tempr Gateway $0.30 $1.20 $0.061M512K— +40%
Hugging Face $0.30 $1.20 —524K512K— +40%
MiniMax (minimax.io) $0.30 $1.20 $0.061M524K— +40%
CommandCode $0.30 $1.20 $0.061M512K— +40%
Merge Gateway $0.30 $1.20 $0.061M128K— +40%
OrcaRouter $0.30 $1.20 $0.061M512K— +40%
OpenCode $0.30 $1.20 $0.06512K128K— +40%
Eden AI $0.30 $1.20 $0.06524K512K— +40%
Standard Compute $0.30 $1.20 $0.061M50K— +40%
MiniMax (minimax.cn) $0.31 $1.25 $0.0631M524K— +46%
ModelRunFP8 $0.30 $1.30 $0.051M944K99.8%24h +47%
Charm Hyper $0.33 $1.31 $0.064512K512K— +53%
Wafer $0.33 $1.32 $0.071M512K— +54%
CrossModel $0.33 $1.32 $0.0661.02M512K— +54%
Kenari $0.36 $1.43 $0.0691M512K— +67%
Synthetic $0.60 $1.20 $0.60524K66K— +100%
TensorX $0.40 $2.00 $0.101M131K— +113%
SambaNova $0.60 $2.40 $0.061M944K93.3%24h +180%
Mara $0.60 $2.40 —1M944K82.4%24h +180%
Ollama Cloud $0.60 $2.40 $0.12512K131K— +180%
Ofox $0.60 $2.40 $0.121M512K— +180%
Inco $0.60 $2.40 $0.121M512K— +180%
Opper $0.60 $2.40 $0.121M131K— +180%
302.AI $0.72 $2.88 $0.141M512K— +236%

Value

Price vs. performance

7 models score higher for the same price or lesson GPQA Diamond, e.g. DeepSeek V4.1 Flash 1017.
23.2%47.6%72.0%96.4% $0.001$0.01$0.10$1.00$10.00$100.00 DeepSeek V4.1 Flash 1017 (DeepSeek) — 93.2% · $0.15/1M in Gemini 4 Argon (Google) — 96.4% · $2.00/1M in Claude Haiku 5.5 (Anthropic) — 89.6% · $0.10/1M in Mistral Large 4 (Mistral) — 88.1% · $1.36/1M in GPT-6.1 Sol (OpenAI) — 95.4% · $2.00/1M in Claude Sonnet 5.5 (Anthropic) — 95.6% · $2.00/1M in GPT-6 Luna (OpenAI) — 90.5% · $0.10/1M in GPT-6 Sol (OpenAI) — 94.3% · $2.00/1M in Claude Opus 5.5 (Anthropic) — 90.6% · $4.00/1M in Grok 4.7 (xAI) — 92.7% · $2.00/1M in DeepSeek V4.1 Flash (DeepSeek) — 93.2% · $0.30/1M in GPT-6 Astra (OpenAI) — 95.8% · $10.00/1M in Qwen3.8 Max (0902) (Qwen) — 92.7% · $2.00/1M in Gemini 3.8 Flash (Google) — 95.4% · $0.82/1M in GLM 5.3 Flash (Z.ai) — 90.1% · $0.005/1M in GLM 5.3 (Z.ai) — 90.9% · $0.70/1M in Gemini 3.7 Flash (Google) — 94.8% · $0.75/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 91.7% · $0.66/1M in Grok 4.6 (xAI) — 94.0% · $2.00/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 91.0% · $0.044/1M in Qwen3.7 Flash (Qwen) — 82.3% · $0.03/1M in Claude Opus 5 (Anthropic) — 93.9% · $5.00/1M in Gemini 3.6 Flash (Google) — 94.1% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 83.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 93.1% · $0.24/1M in GPT-5.6 Luna (OpenAI) — 91.6% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 93.3% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 93.5% · $4.00/1M in Grok 4.5 (xAI) — 93.4% · $2.00/1M in Claude Sonnet 5 (Anthropic) — 90.5% · $2.00/1M in GLM 5.2 (Z.ai) — 91.9% · $0.034/1M in Kimi K2.7 Code (Moonshot AI) — 87.9% · $0.67/1M in Claude Fable 5 (Anthropic) — 85.9% · $10.00/1M in Qwen3.7 Plus (Qwen) — 87.9% · $0.32/1M in Claude Opus 4.8 (Anthropic) — 91.0% · $5.00/1M in Qwen3.7 Max (Qwen) — 90.9% · $1.48/1M in Gemini 3.5 Flash (Google) — 92.8% · $1.50/1M in Gemini 3.1 Flash Lite (Google) — 81.8% · $0.25/1M in Grok 4.3 (xAI) — 88.8% · $1.25/1M in Qwen3.5 Plus 2026-04-20 (Qwen) — 84.9% · $0.30/1M in Qwen3.6 Flash (Qwen) — 83.3% · $0.19/1M in Qwen3.6 35B A3B (Qwen) — 84.9% · $0.10/1M in Qwen3.6 27B (Qwen) — 85.9% · $0.25/1M in GPT-5.5 (OpenAI) — 90.7% · $5.00/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 91.7% · $0.44/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 91.0% · $0.091/1M in Kimi K2.6 (Moonshot AI) — 90.8% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 90.1% · $5.00/1M in GLM 5.1 (Z.ai) — 89.9% · $1.40/1M in Gemma 4 26B A4B (Google) — 73.2% · $0.09/1M in Gemma 4 31B (Google) — 75.8% · $0.20/1M in Qwen3.6 Plus (Qwen) — 88.4% · $0.33/1M in GPT-5.4 Nano (OpenAI) — 78.5% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 86.9% · $0.75/1M in Mistral Small 4 (Mistral) — 47.5% · $0.15/1M in Qwen3.5-9B (Qwen) — 79.0% · $0.08/1M in GPT-5.4 Pro (OpenAI) — 94.6% · $30.00/1M in GPT-5.4 (OpenAI) — 93.3% · $2.50/1M in Gemini 3.1 Flash Lite Preview (Google) — 81.8% · $0.25/1M in Qwen3.5-35B-A3B (Qwen) — 83.5% · $0.14/1M in Gemini 3.1 Pro Preview (Google) — 94.4% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 87.4% · $3.00/1M in Qwen3.5 397B A17B (Qwen) — 86.4% · $0.50/1M in GLM 5 (Z.ai) — 87.8% · $1.00/1M in Claude Opus 4.6 (Anthropic) — 90.5% · $5.00/1M in GLM 4.7 Flash (Z.ai) — 60.5% · $0.061/1M in GLM 4.7 (Z.ai) — 83.3% · $0.54/1M in Gemini 3 Flash Preview (Google) — 89.4% · $0.50/1M in GPT-5.2 (OpenAI) — 91.4% · $1.75/1M in Ministral 3 8B 2512 (Mistral) — 27.2% · $0.15/1M in Ministral 3 3B 2512 (Mistral) — 25.3% · $0.10/1M in Mistral Large 3 2512 (Mistral) — 51.3% · $0.50/1M in Claude Opus 4.5 (Anthropic) — 86.1% · $5.00/1M in GPT-5.1 (OpenAI) — 87.6% · $1.25/1M in Claude Haiku 4.5 (Anthropic) — 71.2% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 82.3% · $3.00/1M in GPT-5 (OpenAI) — 86.2% · $1.25/1M in GPT-5 Mini (OpenAI) — 75.0% · $0.25/1M in GPT-5 Nano (OpenAI) — 69.4% · $0.05/1M in gpt-oss-120b (OpenAI) — 75.8% · $0.15/1M in gpt-oss-20b (OpenAI) — 60.8% · $0.018/1M in Claude Opus 4.1 (Anthropic) — 77.3% · $15.00/1M in Qwen3 30B A3B Instruct 2507 (Qwen) — 55.6% · $0.09/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 80.0% · $0.45/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 70.7% · $0.09/1M in Gemini 2.5 Pro (Google) — 85.3% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 85.3% · $1.25/1M in R1 0528 (DeepSeek) — 76.3% · $0.50/1M in Qwen3 30B A3B (Qwen) — 61.7% · $0.12/1M in Qwen3 14B (Qwen) — 63.8% · $0.12/1M in Qwen3 32B (Qwen) — 65.7% · $0.08/1M in o3 (OpenAI) — 81.8% · $2.00/1M in o4 Mini (OpenAI) — 79.6% · $1.10/1M in GPT-4.1 (OpenAI) — 66.9% · $2.00/1M in GPT-4.1 Mini (OpenAI) — 65.8% · $0.40/1M in GPT-4.1 Nano (OpenAI) — 48.9% · $0.10/1M in Gemma 3 4B (Google) — 23.2% · $0.04/1M in Gemma 3 12B (Google) — 39.5% · $0.05/1M in Gemma 3 27B (Google) — 47.7% · $0.08/1M in Qwen-Plus (Qwen) — 48.1% · $0.26/1M in o3 Mini (OpenAI) — 77.0% · $1.10/1M in Phi 4 (Microsoft) — 56.1% · $0.07/1M in DeepSeek V3 (DeepSeek) — 71.2% · $0.26/1M in o1 (OpenAI) — 76.8% · $15.00/1M in Llama 3.3 70B Instruct (Meta) — 47.4% · $0.10/1M in GPT-4o (2024-11-20) (OpenAI) — 49.2% · $2.50/1M in Mistral Large 2407 (Mistral) — 51.3% · $2.00/1M in Llama 3.2 1B Instruct (Meta) — 23.9% · $0.027/1M in GPT-4o (2024-08-06) (OpenAI) — 49.2% · $2.50/1M in Llama 3.1 70B Instruct (Meta) — 44.2% · $0.40/1M in Llama 3.1 8B Instruct (Meta) — 27.0% · $0.05/1M in GPT-4o-mini (OpenAI) — 37.7% · $0.15/1M in GPT-4o-mini (2024-07-18) (OpenAI) — 37.7% · $0.15/1M in Gemma 2 27B (Google) — 36.5% · $0.65/1M in GPT-4o (OpenAI) — 49.2% · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 49.2% · $5.00/1M in GPT-4 Turbo (OpenAI) — 46.6% · $10.00/1M in Mistral Large (Mistral) — 51.3% · $2.00/1M in GPT-3.5 Turbo (older v0613) (OpenAI) — 28.0% · $1.00/1M in GPT-3.5 Turbo (OpenAI) — 28.0% · $0.50/1M in GPT-4 (OpenAI) — 35.7% · $30.00/1M in MiniMax M3 (MiniMax) — 90.9% · $0.30/1M in MiniMax M3

MiniMax M3 Other MiniMax Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

14 benchmark scores

BenchmarkScoreRankLeader
FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues 14.7% #40of 41 Claude Opus 5.554.6%
GBAEvalSoftware engineering · Build a Game Boy Advance emulator from scratch 0.9% #16of 23 Claude Opus 579.6%
SciCodeSoftware engineering · Research-coding problems from the natural sciences 47.1% #56of 102 Claude Opus 5.566.9%
APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law 37.7% #42of 51 Gemini 4 Argon82.4%
OSWorld 2.0Agents & computer use · Long real-world desktop and web tasks 4.6% #7of 9 Claude Opus 531.4%
Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) $2,158 #44of 61 GPT-6 Astra$15,515
WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) 1487 #48of 90 Claude Opus 5.51820
GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions 90.9% #31of 122 Gemini 4 Argon96.4%
SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people 45.8% #37of 58 Claude Fable 581.9%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 3.7% #61of 111 GPT-5.6 Sol32.3%
Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles 13.0% #69of 83 GPT-6 Astra76.0%
LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts 33.7% #73of 123 Claude Sonnet 5.568.3%
ProofBenchMaths · Graduate maths proofs verified in Lean 4 18.0% #54of 70 Claude Sonnet 5.5100.0%
OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 71.1% #80of 120 Gemini 4 Argon100.0%

Specs

Details

Model ID
minimax/minimax-m3
Developer
MiniMax
Release date
May 31, 2026 ·
Context window
1,048,576 tokens
Max output
512,000 tokens
API price
$0.30 / $1.20 per 1M input / output tokens
Providers
64
Input types
text, image, video
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.