MiniMax M3
MiniMax M3 is MiniMax's frontier open-weight coding model, combining frontier-level coding and agentic performance with ultra-long context and native multimodality.
input · usd / 1m tok
$0.30
output · usd / 1m tok
$1.20
context window
524.3ktokens
modalities · in → out
takes text and image in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $0.30over 512k · $0.60
- output
- $1.20over 512k · $2.40
- cache read
- $0.06over 512k · $0.12
brackets are by input tokens per request: a request over a threshold is billed at that bracket's rates for all of its tokens. cache creation can have a separate charge.
providers
Different companies host MiniMax M3. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
Azure AI Foundry
Azure AI Foundry serving options endpoint location routes Central US 1 East US 2 1 North Central US 1 East US 1 locations describe provider endpoints; they do not guarantee where inference runs.
- MiniMax
- Fireworks
specifications
takes text and image in, gives text outminimaxai/minimax-m3
- creatorMiniMax
- model typeText generation
- context window524,300 tokens
- maximum outputnot published
- input
takes text and image in, gives text out
- outputtext
- tool callingnot verified
- releasedjun 1, 2026
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="minimaxai/minimax-m3",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
29.2#54 of 114 models on the gateway
- coding index58.6#36 of 66
- agentic index29.5#28 of 54
- omniscience1.4#37 of 90
- gpqa92.9%#9 of 82
- humanity’s last exam39.0%#32 of 93
- GPQA92.9%
- Tau288.9%
- AA-LCR83.0%
- IFBench82.9%
- MMMU-Pro78.6%
- SciCode47.1%
- Terminal-Bench Hard42.4%
- Humanity’s Last Exam39.0%
- AutomationBench Partial21.3%
- Tau Banking15.3%
- AnalystAgent10.0%
- GDP.pdf All-pass9.8%
- Multilingual LCR4.4%
- CritPt3.7%
- Harvey LAB0.0%
- Intelligence Index29.22
- Omniscience Index1.35
- GDPval Elo1242.47
- legal index (API)31.5
- coding index (API)58.6
- agentic index (API)29.5
- economics index (API)43.7
- engineering index (API)31.2
- intelligence index (API)29.2
- strategy and ops index (API)25
- finance and accounting index (API)30.1
- healthcare and medical index (API)29.7
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-21.
compare MiniMax M3 with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- anthropic/claude-opus-5-5$4.00 / $20.00compare →
- moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
- openai/gpt-6-astra$10.00 / $50.00compare →
- meta/muse-wonder$4.00 / $20.00compare →
frequently asked questions
What is MiniMax M3?
MiniMax M3 is MiniMax's frontier open-weight coding model, combining frontier-level coding and agentic performance with ultra-long context and native multimodality. It introduces MiniMax Sparse Attention for fast long-context prefill, accepts image and video input, and can operate a desktop computer.
How much does MiniMax M3 cost?
MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens through the Impossibl API. Cache reads cost $0.06 per million tokens. These base rates apply through 512,000 total input tokens per request. Above 512,000 input tokens, the long-context rates in the pricing table apply to the whole request. All rates are in USD.
What is the context length of MiniMax M3?
MiniMax M3 has a 524,300-token context window through the Impossibl API.
What inputs and outputs does MiniMax M3 support?
MiniMax M3 accepts text and image as input. MiniMax M3 returns text.
How do I use MiniMax M3 through an API?
MiniMax M3 is available through the Impossibl API. Use minimaxai/minimax-m3 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was MiniMax M3 released?
MiniMax released MiniMax M3 on June 1, 2026.
this page describes MiniMax M3 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →