MiniMax: MiniMax M1
minimax/minimax-m1MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference.
Modalities
In / out per 1M$0.55 / $2.20
Context1M
ReleasedJun 17, 2025
Providers
2 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.40 | $2.20 | Variable | 1.43s | 46 tps | 100% | |
| $0.55 | $2.20 | Variable | 1.88s | 36 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves MiniMax M1 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what MiniMax M1 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.55
per 1M tokens
Output
$2.20
per 1M tokens
Cache read
—
not published
Included in every pass
MiniMax M1 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.
0.0s1.0s2.0s3.0s4.0s
Oct 16, 6 AMOct 16, 1 PMOct 17, 6 AMOct 18, 6 AMOct 18, 6 PMOct 19, 6 AM
MiniMax NovitaAI
0 tok/s25 tok/s50 tok/s75 tok/s100 tok/s
Oct 16, 6 AMOct 16, 1 PMOct 17, 6 AMOct 18, 6 AMOct 18, 6 PMOct 19, 6 AM
MiniMax NovitaAI
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 87.7%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 88.49%
100% 81% 63% 45%
Oct 18, 11:40 AMNow
Apps
Tools that most often run MiniMax M1, by tokens this week.
Activity
836.7M tokens processed market-wide in the last month.
050.0M100.0M150.0M200.0M
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for MiniMax M1?
minimax/minimax-m1. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does MiniMax M1 hold?
1,000,000 tokens per request, of which up to 40,000 can be the response.
What can it accept and return?
Input: text. Output: text.
What does MiniMax M1 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.55 per 1M input tokens and $2.20 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2024. Anything later has to come from your prompt or a tool call.
Who built MiniMax M1?
MiniMax, in the MiniMax family.
Explore
Other models your pass can call.
