How much does MiniMax M3 (batch) cost?

MiniMax M3 (batch) costs $0.224/M input tokens and $0.88/M output tokens, with separate rates for Cache Read at $0.0448/M tokens.

What is the context length of MiniMax M3 (batch)?

MiniMax M3 (batch) has a 524,288 token context window. It supports up to 512,000 completion tokens.

Does MiniMax M3 (batch) support tool calling and structured outputs?

Yes. MiniMax M3 (batch) accepts tools and tool_choice for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

What inputs and outputs does MiniMax M3 (batch) support?

MiniMax M3 (batch) accepts text, images, and video as input and returns text.

Which providers serve MiniMax M3 (batch)?

MiniMax M3 (batch) is served by 1 provider on OpenRouter: DeepInfra.

What other text models does MiniMax have?

MiniMax M3.1 Flash, MiniMax M2.7, and MiniMax M2.5 are other text models from MiniMax.

When was MiniMax M3 (batch) released?

MiniMax M3 (batch) was released on May 31, 2026.

MiniMax: MiniMax M3 (batch)

minimax/minimax-m3:batch

Model weights

Compare

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, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.

Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.

Modalities

In / out price

$0.224 / $0.88per 1M

Context

524K

Released

May 31, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).


	$0.224	$0.88	$0.0448	--	--	--

Input $0.224Output $0.88
-- tok/s-- uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0/M tokens

Output

$0/M tokens

MiniMax M3 (batch) — Price history

Price history

No effective price data for this selection

		$0.00	$0.00	55.1%	100.0%

Effective in $0.00Effective out $0.00
Token share
100.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Not enough uptime data to display yet.

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for MiniMax: MiniMax M3 (batch) (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	MiniMax-M3 Intelligence Index	18.9
Artificial Analysis	MiniMax-M3 Coding Index	58.6
Artificial Analysis	MiniMax-M3 Agentic Index	29.5
Artificial Analysis	MiniMax-M3 GPQA Diamond	92.9%
Artificial Analysis	MiniMax-M3 HLE	39.0%
Artificial Analysis	MiniMax-M3 IFBench	82.9%
Artificial Analysis	MiniMax-M3 τ²-Bench Telecom	88.9%
Artificial Analysis	MiniMax-M3 AA-LCR	83.0%
Artificial Analysis	MiniMax-M3 τ-Bench Banking	15.3%
Artificial Analysis	MiniMax-M3 GDPval-AA	37.5%
Artificial Analysis	MiniMax-M3 CritPt	3.7%
Artificial Analysis	MiniMax-M3 SciCode	47.1%
Artificial Analysis	MiniMax-M3 Terminal-Bench Hard	42.4%
Artificial Analysis	MiniMax-M3 Terminal-Bench 4.0	2.0%
Artificial Analysis	MiniMax-M3 Terminal-Bench 2.1	65.2%
Artificial Analysis	MiniMax-M3 AA-Omniscience Accuracy	44.9%
Artificial Analysis	MiniMax-M3 AA-Omniscience Non-Hallucination Rate	8.6%
Design Arena	MiniMax M3 Agents Arena Agenticgamedev Elo	1116
Design Arena	MiniMax M3 Agents Arena Androidnative Elo	1156
Design Arena	MiniMax M3 Agents Arena Blender3d Elo	1090
Design Arena	MiniMax M3 Agents Arena Codetovideo Elo	1202
Design Arena	MiniMax M3 Agents Arena Full Stack Elo	1175
Design Arena	MiniMax M3 Agents Arena Htmlslides Elo	1076
Design Arena	MiniMax M3 Agents Arena Mobile Apps Elo	1168
Design Arena	MiniMax M3 Agents Arena Pdf Elo	1264
Design Arena	MiniMax M3 Agents Arena Python-Pptxslides Elo	1171
Design Arena	MiniMax M3 Agents Arena Spreadsheet Elo	1159
Design Arena	MiniMax M3 Agents Arena Webapps Elo	1188
Design Arena	MiniMax M3 Models Arena 3D Elo	1189
Design Arena	MiniMax M3 Models Arena Asciiart Elo	1149
Design Arena	MiniMax M3 Models Arena Code Categories Elo	1236
Design Arena	MiniMax M3 Models Arena Data Visualization Elo	1229
Design Arena	MiniMax M3 Models Arena Game Development Elo	1200
Design Arena	MiniMax M3 Models Arena SVG Elo	1146
Design Arena	MiniMax M3 Models Arena UI Component Elo	1235
Design Arena	MiniMax M3 Models Arena Website Elo	1249
Vals AI	MiniMax-M3 Access to Justice Benchmark	69.8%
Vals AI	MiniMax-M3 Code Migration v1.1	20.9%
Vals AI	MiniMax-M3 CorpFin v2	68.1%
Vals AI	MiniMax-M3 CyberBench v1.1	65.0%
Vals AI	MiniMax-M3 EMB v1.1	59.8%
Vals AI	MiniMax-M3 Finance Agent v2.1	54.3%
Vals AI	MiniMax-M3 Vals Finance Index	48.4%
Vals AI	MiniMax-M3 Financial Coaching Bench	69.0%
Vals AI	MiniMax-M3 GPQA Diamond	92.7%
Vals AI	MiniMax-M3 Harvey's Legal Agent Benchmark v1	4.2%
Vals AI	MiniMax-M3 Immigration	57.5%
Vals AI	MiniMax-M3 Vals Inference Provider Index	53.5%
Vals AI	MiniMax-M3 LiveCodeBench	82.2%
Vals AI	MiniMax-M3 LegalBench	85.4%
Vals AI	MiniMax-M3 Legal Research Bench	29.8%
Vals AI	MiniMax-M3 MedCode	46.3%
Vals AI	MiniMax-M3 MedScribe	87.3%
Vals AI	MiniMax-M3 MMLU Pro	84.2%
Vals AI	MiniMax-M3 MMMU Pro	81.2%
Vals AI	MiniMax-M3 MortgageTax	68.4%
Vals AI	MiniMax-M3 ProofBench v1.1	18.0%
Vals AI	MiniMax-M3 Public Benefits Bench v1.1	64.1%
Vals AI	MiniMax-M3 SAGE	85.5%
Vals AI	MiniMax-M3 SkillsBench	51.5%
Vals AI	MiniMax-M3 SWE-bench	75.0%
Vals AI	MiniMax-M3 SWE-bench Multimodal	33.3%
Vals AI	MiniMax-M3 Tax Agent Bench	20.6%
Vals AI	MiniMax-M3 TaxEval v2	72.7%
Vals AI	MiniMax-M3 Terminal-Bench 4.0	1.0%
Vals AI	MiniMax-M3 Vals Index	36.5%
Vals AI	MiniMax-M3 Vals Multimodal Index	60.0%
Vals AI	MiniMax-M3 Vibe Code Bench 1-100	9.2%
Vals AI	MiniMax-M3 Vibe Code Bench v1.1	47.6%

Not currently available through EU in-region routing. In-region routing docs

More models from MiniMax

MiniMax H3 Image Highspeed

MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 Image model. It takes the same inputs and limits as MiniMax H3 Image: it creates images from text prompts and edits or composes images from 1 to 16 reference images, with output up to 20 megapixels and aspect ratios from 1:3 to 3:1.

Image$3 / $7.60

MiniMax H3 Image

MiniMax H3 Image is MiniMax's image generation and editing model. It creates images from text prompts and edits or composes images from 1 to 16 reference images, with output up to 20 megapixels and aspect ratios from 1:3 to 3:1.

Image$1.50 / $3.80

MiniMax M3.1 Flash

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.

Text1.0M context$0.075 / $0.30

H3 Max

MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with controlled first-frame or last-frame keyframes.

Videofrom $0.05/second

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer.

The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation.

Videofrom $0.13/second

Speech 2.8 HD

MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Speech$100/M characters

Speech 2.8 Turbo

MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.

Speech$60/M characters

MiniMax M3

Text1.0M context$0.23 / $0.96

MiniMax M3 (batch)

Text524K context$0.224 / $0.88

Hailuo 2.3

Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is suited for creative content production, cinematic scene generation, and character animation, with a focus on realistic motion and expressive character rendering.

Video$0.0817/second

MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.

Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

Text197K context$0.21 / $0.84

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 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

Text198K context$0.27 / $0.95

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 roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.

Text66K context

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 capability while maintaining exceptional latency, scalability, and cost efficiency.

Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.

To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.

Text205K context

MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.

The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.

Benchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.

To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.

Text205K context

MiniMax M1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it to process long sequences—up to 1 million tokens—while maintaining competitive FLOP efficiency. With 456 billion total parameters and 45.9B active per token, this variant is optimized for complex, multi-step reasoning tasks.

Trained via a custom reinforcement learning pipeline (CISPO), M1 excels in long-context understanding, software engineering, agentic tool use, and mathematical reasoning. Benchmarks show strong performance across FullStackBench, SWE-bench, MATH, GPQA, and TAU-Bench, often outperforming other open models like DeepSeek R1 and Qwen3-235B.

Text1M context

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 of up to 4 million tokens.

The text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model.

To read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2

Text1M context

MiniMax: MiniMax M3 (batch)

Providers

Pricing

Weighted average

MiniMax M3 (batch) — Price history

Performance

Uptime

Benchmarks

Apps

Activity

API

Frequently asked questions

Explore more models

More models from MiniMax

More models from MiniMax

MiniMax: MiniMax M3 (batch)

Providers

Pricing

Weighted average

MiniMax M3 (batch) — Price history

Performance

Uptime

Benchmarks

Apps

Activity

API

Frequently asked questions

What is MiniMax M3 (batch)?

How much does MiniMax M3 (batch) cost?

What is the context length of MiniMax M3 (batch)?

Does MiniMax M3 (batch) support tool calling and structured outputs?

What inputs and outputs does MiniMax M3 (batch) support?

Which providers serve MiniMax M3 (batch)?

What other text models does MiniMax have?

When was MiniMax M3 (batch) released?

Explore more models

More models from MiniMax

More models from MiniMax