MiniMax: MiniMax-M3

MiniMax multimodal model for long-context coding, perception, and agent planning

Source-linked minimax Open weights Released 2026-06-01

API record Report

InputT

OutputT

Input price$0.3/M

Output price$1.2/M

Context1.04858M

Max output512K

Providers37

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering MiniMax-M3
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Kenari	`minimax-m3`	1.04858M	512K	—	—	—	ReasoningTools	Docs ↗
MiniMax Token Plan (minimax.io)	`MiniMax-M3`	1.04858M	512K	—	—	—	ReasoningTools	Docs ↗
SCNet Token Plan	`MiniMax-M3`	1.04858M	512K	—	—	—	ReasoningTools	Docs ↗
MiniMax Token Plan (minimaxi.com)	`MiniMax-M3`	1.04858M	512K	—	—	—	ReasoningTools	Docs ↗
Nvidia	`minimaxai/minimax-m3`	1M	16.384K	—	—	—	ReasoningTools	Docs ↗
Volcengine Ark Coding Plan	`minimax-m3`	1.04858M	512K	—	—	—	ReasoningTools	Docs ↗
Vancine	`MiniMax-M3`	1.04858M	512K	$0.24	$0.96	$0.048	ReasoningTools	Docs ↗
Deep Infra	`MiniMaxAI/MiniMax-M3`	524.288K	512K	$0.28	$1.1	$0.056	ReasoningToolsJSON	Docs ↗
Hugging Face	`MiniMaxAI/MiniMax-M3`	524.288K	512K	$0.3	$1.2	—	ReasoningToolsJSON	Docs ↗
Together AI	`MiniMaxAI/MiniMax-M3`	524.288K	250K	$0.3	$1.2	$0.06	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`minimax/minimax-m3`	524.288K	512K	$0.3	$1.2	$0.06	ReasoningToolsJSON	Docs ↗
Pioneer	`MiniMaxAI/MiniMax-M3`	1M	131.072K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
OrcaRouter	`minimax/minimax-m3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
Abacus	`MiniMaxAI/MiniMax-M3`	1M	131.072K	$0.3	$1.2	—	ReasoningTools	Docs ↗
ClinePass	`cline-pass/minimax-m3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
Eden AI	`minimax/MiniMax-M3`	524.288K	512K	$0.3	$1.2	$0.06	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`minimax-m3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
MiniMax (minimax.io)	`MiniMax-M3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
OpenRouter	`minimax/minimax-m3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningToolsJSON	Docs ↗
Jalapeno Cloud	`MiniMax-M3`	524.288K	512K	$0.3	$1.2	—	ReasoningToolsJSON	Docs ↗
Nebius Token Factory	`MiniMaxAI/MiniMax-M3`	1.04858M	1.04858M	$0.3	$1.2	—	ReasoningTools	Docs ↗
Fireworks AI	`accounts/fireworks/models/minimax-m3`	512K	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
OpenCode Zen	`minimax-m3`	512K	128K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
Requesty	`minimax-m3`	1M	128K	$0.3	$1.2	$0.06	ReasoningToolsJSON	Docs ↗
MiniMax (minimaxi.com)	`MiniMax-M3`	1.04858M	512K	$0.3	$1.2	$0.06	ReasoningTools	Docs ↗
Charm Hyper	`minimax-m3`	512K	512K	$0.327	$1.307	$0.064	ReasoningTools	Docs ↗
CrossModel	`minimax/minimax-m3`	1.024M	512K	$0.33	$1.32	$0.066	ReasoningToolsJSON	Docs ↗
Wafer	`MiniMax-M3`	1.04858M	512K	$0.33	$1.32	$0.07	ReasoningToolsJSON	Docs ↗
Cortecs	`minimax-m3`	1.04858M	1.04858M	$0.395	$1.977	$0.099	ReasoningToolsJSON	Docs ↗
TensorX	`minimax/minimax-m3`	1.04858M	131.072K	$0.4	$2	$0.1	ReasoningTools	Docs ↗
Ofox	`minimax/minimax-m3`	1.04858M	512K	$0.6	$2.4	$0.12	ReasoningTools	Docs ↗
Merge Gateway	`minimax/minimax-m3`	512K	128K	$0.6	$2.4	—	ReasoningTools	Docs ↗
Synthetic	`hf:MiniMaxAI/MiniMax-M3`	524.288K	65.536K	$0.6	$1.2	$0.6	ReasoningToolsJSON	Docs ↗
Opper	`minimax/m3`	1.04858M	512K	$0.6	$2.4	$0.12	ReasoningTools	Docs ↗
ZenMux	`minimax/minimax-m3`	1.04858M	512K	$0.6	$2.4	—	ReasoningTools	Docs ↗
GMI Cloud	`MiniMaxAI/MiniMax-M3`	1.04858M	512K	$0.6	$2.4	$0.12	ReasoningTools	Docs ↗
302.AI	`MiniMax-M3`	1.04858M	512K	$0.72	$2.88	—	ReasoningTools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.24/M

Across 31 priced providers

Median input $0.3/M

Midpoint of listed rates

Highest input $0.72/M

3.0× the lowest listed rate

Output range $0.96 – $2.88

Per million output tokens

Vancine $0.24/MLowest

Deep Infra $0.28/M

Hugging Face $0.3/M

Together AI $0.3/M

Kilo Gateway $0.3/M

Pioneer $0.3/M

OrcaRouter $0.3/M

Abacus $0.3/M

ClinePass $0.3/M

Eden AI $0.3/M

DevPass (LLM Gateway) $0.3/M

MiniMax (minimax.io) $0.3/M

OpenRouter $0.3/M

Jalapeno Cloud $0.3/M

Nebius Token Factory $0.3/M

Fireworks AI $0.3/M

OpenCode Zen $0.3/M

Requesty $0.3/M

MiniMax (minimaxi.com) $0.3/M

Charm Hyper $0.327/M

CrossModel $0.33/M

Wafer $0.33/M

Cortecs $0.395/M

TensorX $0.4/M

Ofox $0.6/M

Merge Gateway $0.6/M

Synthetic $0.6/M

Opper $0.6/M

ZenMux $0.6/M

GMI Cloud $0.6/M

302.AI $0.72/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 512K to 1.04858M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

✓ Open weights Yes

Creator: MiniMax
Model family: minimax
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-06-01
Model ID: minimax/MiniMax-M3

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

Benchmark profile

Each axis is this model's percentile among the 4 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

OSWorld-Verified success rate · 2026-06-01 Source ↗

OSWorld-Verified #15 of 17

70.06

BrowseComp accuracy · 2026-06-01 Source ↗

BrowseComp #10 of 15

83.52

Terminal-Bench — 2.1 success rate · 2026-06-01 Source ↗

Terminal-Bench #8 of 12

66.0

MCP Atlas success rate · 2026-06-01 Source ↗

MCP Atlas #7 of 7

74.2

SWE-Bench Pro resolve rate · Claude Code · 2026-06-01 Source ↗

SWE-Bench Pro #2 of 3

59.0

SWE-Bench Verified resolved · Claude Code · 2026-06-01 Source ↗

80.5 2 models scored — too few for a distribution

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against OSWorld-Verified, the benchmark with the widest published coverage that this model appears in.

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Aug 26, 2026Max Output Tokens128000 → 512000

Aug 26, 2026Context Length512000 → 1048576

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/minimax/MiniMax-M3

curl

curl "https://model.kyssta.lol/api/v1/models/minimax/MiniMax-M3"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is MiniMax-M3?

MiniMax multimodal model for long-context coding, perception, and agent planning. It is published by MiniMax and catalogued here from Models.dev.

How much does MiniMax-M3 cost?

Listed input pricing starts at $0.24 per million tokens from Vancine, rising to $0.72 across 31 listed providers.

What is the context length of MiniMax-M3?

MiniMax-M3 accepts up to 1.04858M tokens of context and returns up to 512K output tokens.

Does MiniMax-M3 support tool calling and structured output?

Provider catalogs list support for tool calling, reasoning, and image input.

Which providers serve MiniMax-M3?

37 providers list this model: Kenari, MiniMax Token Plan (minimax.io), SCNet Token Plan, MiniMax Token Plan (minimaxi.com), Nvidia, Volcengine Ark Coding Plan and 31 more.

Are the weights for MiniMax-M3 open?

Yes. The weights are published and downloadable from Hugging Face.

When was MiniMax-M3 released?

The catalog records a release date of 2026-06-01, last verified Sep 11, 2026.

More models from MiniMax

View all →

MiniMax: MiniMax M2-her

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...

65.536K ctx $0.3/M in MiniMax: MiniMax M2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

204.8K ctx $0.3/M in MiniMax: MiniMax-01

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

1.00019M ctx $0.2/M in MiniMax: MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

204.8K ctx $0.3/M in