🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

MiniMax M3 Released 2026-06-01

MiniMax chat code reasoning tools long-context
Input$0.3/M
Output$1.2/M
Cache read$0.06/M
Context1M
vs GPT-4o~94% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.132/M. Automatic prefix caching once a prompt passes 512 input tokens; cached reads bill at the discounted cache-hit rate, no code changes and no write fee. MSA sparse attention with 1M-token context (standard billing up to 512K input); ~428B/~23B active MoE; native multimodal (image + video input), computer use, adaptive thinking; automatic prefix caching from 512+ input tokens.

Use MiniMax M3 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About MiniMax M3

First open-weight combining coding, agents, multimodality
Up to 1M context, 512K guaranteed minimum
Multimodality trained from step zero

MiniMax M3 is MiniMax's frontier model positioned as the first open-weight release to combine three frontier capabilities: coding, agentic reasoning, and native multimodal understanding.

  • Built on the proprietary MiniMax Sparse Attention (MSA) architecture, it supports a context window of up to 1M tokens with a guaranteed minimum of 512K, targeting long-horizon agent tasks and whole-codebase comprehension.
  • Unlike bolt-on approaches, multimodality is trained from step zero for deep alignment between text and visual semantics.
  • Synthorai serves MiniMax M3 through its OpenAI-compatible endpoint.

Specs & limits

Max output (vendor spec)524,288
Modalitiestext + image + video → text
Parameters428B total · 23B active (MoE)
Featurestools · streaming · vision · reasoning · caching
LicenseMiniMax Community License ↗
NotableMSA sparse attention with 1M-token context (standard billing up to 512K input); ~428B/~23B active MoE; native multimodal (image + video input), computer use, adaptive thinking; automatic prefix caching from 512+ input tokens.
Prompt cachingautomatic · min 512-token prefix

per MiniMax official docs ↗

FAQ

Is the MiniMax M3 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.3/M input tokens, that credit alone covers roughly 416 requests of ~8K tokens against MiniMax M3.

What is MiniMax M3 best at?

First open-weight combining coding, agents, multimodality, plus up to 1M context, 512K guaranteed minimum and multimodality trained from step zero. See the About section for the full picture from the vendor's own release notes.

How much does MiniMax M3 cost?

MiniMax M3 costs $0.3 per million input tokens and $1.2 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.06/M.

Does MiniMax M3 support prompt caching?

Yes, automatically: MiniMax-served prompts cache with no code changes. Cached input tokens bill at $0.06/M vs $0.3/M uncached; prompts need a 512-token stable prefix to cache. Prompt caching guide →

How do I get access to MiniMax M3?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="minimax-m3", and you're done. One API key covers every model on the gateway.

Is MiniMax M3 open source?

Yes: the weights are published under the MiniMax Community License (official repository linked in the About section). Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →

Related models

Get your free API key Compare your cost →