Start free trial

MiniMax: MiniMax M3

minimax/minimax-m3
CompareAPITry this model

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

Modalities
In / out per 1M$0.30 / $1.20
Context1M
ReleasedMay 31, 2026

Providers

13 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
DeepInfraus · fp8$0.28$1.10$0.061.11s31 tps100%
ModelRun [by Modular]fp8$0.30$1.30$0.050.55s109 tps99.92%
CoreWeavefp4$0.23$0.96$0.050.40s279 tps99.77%
NovitaAIfp8$0.30$1.20$0.062.04s100 tps99.75%
StreamLakefp8$0.30$1.20$0.062.53s91 tps99.75%
Parasailfp8$0.30$1.20$0.061.02s130 tps99.46%
GMICloudfp8$0.24$0.96$0.053.37s55 tps99.28%
Together$0.30$1.20$0.060.43s79 tps99.25%
MiniMax$0.30$1.20$0.061.58s75 tps99.04%
AtlasCloudfp8$0.30$1.20$0.061.98s110 tps98.78%
Venicefp8$0.30$1.20$0.060.80s114 tps97.56%
DeepInfraus · fp8$0.22$0.88$0.04——96.17%
MARA$0.60$2.40Variable1.21s41 tps43.75%

Market-wide measurements, refreshed every 15 minutes. They describe who serves MiniMax M3 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what MiniMax M3 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Cache read
$0.06
per 1M cached tokens
Included in every pass
MiniMax M3 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s100.0s200.0s300.0s400.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Together Parasail GMICloud DeepInfra (us) MiniMax CoreWeave NovitaAI AtlasCloud StreamLake ModelRun [by Modular] Venice DeepInfra (us) MARA
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Together Parasail GMICloud DeepInfra (us) MiniMax CoreWeave NovitaAI AtlasCloud StreamLake ModelRun [by Modular] Venice DeepInfra (us) MARA

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.47%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.22%
100% 88% 77% 65%
Oct 31, 6:10 PMNow

Apps

Tools that most often run MiniMax M3, by tokens this week.

Hello Minds, powered by EthoswarmRoleplay · 56.3% of tokens1492.0BHermes AgentPersonal Agent · 21.1% of tokens558.8BOpenClawPersonal Agent · 9.7% of tokens256.5BMiraPersonal Agent · 7.8% of tokens206.0BKilo CodeCli Agent · 5.2% of tokens138.5B

Activity

5125.5B tokens processed market-wide in the last month.

0100.0B200.0B300.0B400.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for MiniMax M3?
minimax/minimax-m3. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does MiniMax M3 hold?
1,048,576 tokens per request, of which up to 512,000 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does MiniMax M3 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.30 per 1M input tokens and $1.20 per 1M output tokens.
Who built MiniMax M3?
MiniMax, in the MiniMax family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion