MiniMax M3 API
MiniMax's 2026 flagship. A natively multimodal model with a 1M context window built on sparse attention, scoring 91.6% on GPQA Diamond and 72.1% on TAU-Bench. Input is $0.30/1M up to 512K context and doubles beyond that, with cached input at $0.06.
💰 Save up to 70% vs official MiniMax pricingMiniMax M3 — cheaper than the official MiniMax API
Access MiniMax M3 through AI API Hub and pay less per token. Same OpenAI-compatible endpoint, lower cost.
Technical Specifications
| Provider | MiniMax |
| Model Family | MiniMax M3 |
| Release Date | 2026-06 |
| Context Window | 1M |
| Max Output Tokens | 131,072 |
| Input Price | $0.30 / 1M tokens |
| Output Price | $1.20 / 1M tokens |
| Vision Support | Yes ✓ |
| Function Calling | No |
| JSON Mode | No |
| Streaming | Yes ✓ |
| Fine Tuning | Not Available |
| Status | Active ✓ |
Overview
MiniMax M3 is MiniMax's current minimax model, released in 2026-06. MiniMax's 2026 flagship. A natively multimodal model with a 1M context window built on sparse attention, scoring 91.6% on GPQA Diamond and 72.1% on TAU-Bench. Input is $0.30/1M up to 512K context and doubles beyond that, with cached input at $0.06.
For developers, the headline numbers are a 1M context window and up to 131,072 output tokens per response — enough headroom for native multimodal and 1m context without chunking your input. Priced at $0.30/1M input and $1.20/1M output, it sits in the budget tier — ideal for high-volume pipelines where token cost dominates.
On the capability side, MiniMax M3 exposes 5 features: Vision, Video, Reasoning, Multilingual, Streaming. Note that fine-tuning isn't supported — you'll work with the base model. Vision support means you can pass images alongside text, handy for document parsing or UI automation.
The practical appeal of routing MiniMax M3 through AI API Hub is simplicity: one OpenAI-compatible endpoint, USDT & USDC payments, no credit card, and you're calling the API in under 30 seconds — just swap your base URL.
What Makes MiniMax M3 Different
How MiniMax M3 is used
MiniMax M3 is used for text-to-video and image-to-video generation. You send a prompt or reference image, receive a video clip back. Common pipelines: marketing asset generation, storyboarding, social content, and visual prototyping. It doesn't handle text chat — route text workloads to a language model.
Pricing position within MiniMax
MiniMax M3 is the cheapest active model in MiniMax's lineup at $0.30/1M input — no sibling undercuts it. The most expensive sibling costs $0.30/1M (0% more). At scale, routing high-volume calls here vs the flagship saves significantly.
MiniMax M3's role in the lineup
Within MiniMax's lineup, MiniMax M3 is the flagship — the most capable and most expensive option. It's part of the minimax family (2 active variants share this family). Use it when quality matters more than cost; switch to a cheaper sibling for high-volume or less demanding tasks.
Real-world use cases
Real-world deployments: marketing video generation from product descriptions, social media content creation, storyboarding for video production, and visual prototyping for design teams. MiniMax M3 outputs video clips directly — no separate rendering pipeline needed.
vs sibling models
What makes MiniMax M3 different from sibling models: compared to MiniMax M2.7 ($0.00/1M cheaper, 256K vs 1M context (smaller)). Choose MiniMax M3 when step-by-step reasoning matters more than speed.
API Examples
Python
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.apiyihe.org/v1"
)
response = client.chat.completions.create(
model="minimax-m3",
messages=[
{"role": "user", "content": "Hello"}
]
)
print(response.choices[0].message.content)JavaScript / Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.API_KEY,
baseURL: "https://api.apiyihe.org/v1"
});
const response = await client.chat.completions.create({
model: "minimax-m3",
messages: [
{ role: "user", content: "Hello" }
]
});
console.log(response.choices[0].message.content);cURL
curl https://api.apiyihe.org/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "minimax-m3",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Supported Features
| Vision / Image Input | ✅ Supported |
| Audio / Voice Input | ❌ Not Available |
| Function Calling | ❌ Not Available |
| JSON Mode | ❌ Not Available |
| Streaming | ✅ Supported |
| Fine-Tuning | ❌ Not Available |
| Multimodal | ❌ Not Available |
Benchmark Scores
| Benchmark | Score |
|---|---|
| MMLU | Not Publicly Available |
| GPQA | Not Publicly Available |
| SWE-Bench | Not Publicly Available |
| HumanEval | Not Publicly Available |
| GSM8K | Not Publicly Available |
| MATH | Not Publicly Available |
| MMMU | Not Publicly Available |
Pricing History
MiniMax M3 was released in 2026-06 by MiniMax and is currently publicly available via AI API Hub.
Current Pricing: $0.30 per 1M input tokens · $1.20 per 1M output tokens. Pay-as-you-go with no minimum commitment.
Pricing Model: Token-based billing (pay per use). No subscription fees. No hidden costs.
💡 MiniMax occasionally updates pricing. AI API Hub reflects current pricing in real-time. All prices in USD. Pay with USDT or USDC — no currency conversion fees.
Compare Alternatives
Frequently Asked Questions
What is MiniMax M3?
MiniMax M3 is MiniMax's current minimax model. MiniMax's 2026 flagship. A natively multimodal model with a 1M context window built on sparse attention, scoring 91.6% on GPQA Diamond and 72.1% on TAU-Bench. Input is $0.30/1M up to 512K context and doubles beyond that, with cached input at $0.06. It offers a 1M context window and supports Vision, Video, Reasoning. You can access it through AI API Hub using USDT or USDC — no credit card required.
How much does MiniMax M3 cost?
MiniMax M3 is priced at $0.30 per 1M input tokens and $1.20 per 1M output tokens, billed pay-as-you-go with no minimum. Through AI API Hub you can start with as little as $5 and scale from there.
MiniMax M3 vs GPT-6 Astra?
They're built for different jobs. MiniMax M3 costs $0.30/1M input with a 1M window; GPT-6 Astra runs $10.00/1M input with 1M. MiniMax M3 is the more cost-effective pick and still brings native multimodal. See the full side-by-side at /compare/minimax-m3-vs-gpt-6-astra/.
MiniMax M3 context window?
MiniMax M3 has a 1M context window, capable of processing up to 1,048,576 tokens in a single request. Maximum output tokens: 131,072.
Does MiniMax M3 support function calling?
No, MiniMax M3 does not natively support function calling. For function calling use cases, consider MiniMax's flagship models.
Is MiniMax M3 multimodal?
Partially — MiniMax M3 supports vision (image input) but not native audio processing.
MiniMax M3 API rate limits?
MiniMax M3 rate limits: 5K RPM. Higher tier plans offer increased throughput. For high-volume production use, consider MiniMax's faster variant models.
How to access MiniMax M3 API?
Access MiniMax M3 through AI API Hub: (1) Register at z.apiyihe.org/register?aff=ZVtr, (2) Deposit USDT/USDC, (3) Get your API key instantly, (4) Use the OpenAI-compatible endpoint https://api.apiyihe.org/v1 with model name "minimax-m3". Start building in under 30 seconds.