Requesty
Sign in

identity

open weights
MiniMax logo

minimax-m3MiniMax

from /1M in$0.30fireworks ai
context1.0M1.0M out
best ttft1.03sfireworks ai
price spread1.3x3 endpoints
endpoints
3
regions
2
best tok/s
232
api
chat
released
May 2026
eu routing
available

capabilities 5/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 1.3x more on tensorx ltd. than on fireworks ai. That is what the endpoints table is for.

endpoints

3 / 2 regions
Providers serving minimax-m3, with pricing and measured performance. Best value in each column is coloured.
#flags
1Fireworks AIGlobal512K$0.30$1.20$0.061.03s232.0zdr
2MiniMaxGlobal1M$0.30$1.20$0.061.83s130.0zdr
3TensorX Ltd.EU1.0M$0.40$2.00$0.101.11s37.0zdr
provider price, no markupper 1M tokensblank where no qualifying sample

measured

through Sep 12
median
837ms1.75s2.67s07-0608-0309-071.57s1.48s990ms
hover the plot for weekly values
time to first token per provider: current value, window low and high, and change across the window
providernowlowhighchange
Fireworks AI1.03s1.09s1.54s+8.6%
TensorX Ltd.1.11s990ms2.11s-13%
MiniMax1.83s1.51s2.52s-38%

median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.

Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond92.9
τ²-Bench88.9
Coding Index58.6
SciCode47.1
Terminal-Bench Hard42.4
Humanity's Last Exam39.0
Intelligence Index29.6
7 evalsmean56.9

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-06-01.

call it

model=
minimax-m3

requesty routes this id across every provider serving minimax-m3, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it

Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.

quickstart

openai compatible
main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="minimax-m3",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models

notes

reference

MiniMax M3 is a frontier multimodal model with a 1M token context window built on MiniMax Sparse Attention (MSA). It delivers frontier level performance on coding and agentic tasks, outperforming GPT 5.5 and Gemini 3.1 Pro on SWE Bench Pro and approaching Claude Opus 4.7. It natively handles image and video input and is the first open weight model to combine frontier coding, ultra long context, and native multimodality.

questions 7

Which providers serve minimax-m3?
minimax-m3 is available from 3 providers through Requesty: Fireworks AI, MiniMax, TensorX Ltd.. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does minimax-m3 cost?
Pricing starts at $0.30 per million input tokens and $1.20 per million output tokens on the cheapest provider. Prices vary by provider and region; the table above shows every endpoint. Requesty charges exactly what the upstream provider charges, with no markup.
Is minimax-m3 open weights?
Yes. minimax-m3 is an open-weights model from MiniMax, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of minimax-m3?
minimax-m3 supports up to 1.0M tokens of context, with up to 1.0M output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for minimax-m3?
In recent production traffic through Requesty, Fireworks AI had the lowest median time to first token (1.03s) for minimax-m3. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use minimax-m3 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "minimax-m3" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call minimax-m3 by its managed id or a provider id?
Use the managed id, "minimax-m3". Requesty picks which of the 3 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "minimax-m3@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "fireworks/minimax-m3" only when you need one specific deployment and want no failover.

more from minimax 5

Other MiniMax models
modelcontextfrom /Mproviders
minimax-m2.7-highspeed205K$0.602
minimax-m2.7200K$0.302
minimax-m2.5200K$0.284
minimax-m2.5-highspeed200K$0.601
minimax-m2200K$0.301

route minimax-m3 through one endpoint

One key for 3 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology

minimax-m33 providers3 endpointsfrom $0.30 /1M inctx 1.0Mttft 1.03sspread 1.3xupdated Sep 12