Text GenerationMiniMax
MiniMax M3 API
MiniMax M3 — a capable large language model for long-context reasoning, tool use, and multilingual chat.
24H Status Monitor
24h success rate: 100%
Model:
Price: 2.4 credits per 1K input tokens · ≈ $0.0012-$0.0024 · 10 credits per 1K output tokens · ≈ $0.005-$0.01High stability with detailed usage records on the APIAny platform.
minimax-m3
113 (suggested: 2,000)
0.7
02
Sampling temperature.
4096
18192
Maximum output tokens.
USD estimate $0.0205-$0.041: highest recharge package uses $1 = 2,000 credits; entry package uses $1 = 1,000 credits.
Preview
No Task RunningLLMResult preview
History
Saved locally in this browser
0 running · 0 completed
Your generation history will appear here
Input
2.4 credits/1K
≈ $0.0012-$0.0024
Output
10 credits/1K
≈ $0.005-$0.01
Cache
3 credits/1K
≈ $0.0015-$0.003
Context
1M
Max output
8k
Pricing
Model ID
Type
Quality
Price
minimax-m3
Text Generation
Input tokens
2.4 credits per 1K input tokens · ≈ $0.0012-$0.0024
minimax-m3
Text Generation
Cache read tokens
3 credits per 1K cached input tokens · ≈ $0.0015-$0.003
minimax-m3
Text Generation
Output tokens
10 credits per 1K output tokens · ≈ $0.005-$0.01
minimax-m3
Text Generation
Minimum request
0.02 credits minimum · ≈ $0.00001-$0.00002
Model IDminimax-m3
TypeText Generation
QualityInput tokens
Price2.4 credits per 1K input tokens · ≈ $0.0012-$0.0024
Model IDminimax-m3
TypeText Generation
QualityCache read tokens
Price3 credits per 1K cached input tokens · ≈ $0.0015-$0.003
Model IDminimax-m3
TypeText Generation
QualityOutput tokens
Price10 credits per 1K output tokens · ≈ $0.005-$0.01
Model IDminimax-m3
TypeText Generation
QualityMinimum request
Price0.02 credits minimum · ≈ $0.00001-$0.00002
API
curl /v1/chat/completions \
-H "Authorization: Bearer sk-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [
{
"role": "user",
"content": "Summarize APIAny.AI's multi-channel model aggregation in three sentences, and give one production recommendation."
}
],
"temperature": 0.7,
"max_tokens": 4096
}'
