Apixly · API pricing
minimax-m3
minimax-m3 · Text generation
Official standard price ≤512K
Gateway price for minimax-m3 ↓API integration · Text generation
Use a text model to produce responses from messages. Start with plain text; test tools, images, streaming and other optional features on your selected group before enabling them in an application.
- Request model ID
- minimax-m3
- Public groups
- ChineseLLM-stable
Create an Apixly API key, bind a group that lists this exact model, and keep the key in a server-side environment variable. Public prices exclude personal discounts; check the selected group before sending a request.
curl --fail-with-body --max-time 120 'https://apixly.ai/v1/chat/completions' \
-H "Authorization: Bearer $APIXLY_API_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "minimax-m3",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"stream": false
}'Start with one small request. Check the complete result and reported usage, then match the request to its charge in the console. For chat, inspect choices[0].message.content; embeddings return data and reranking returns results. A successful HTTP status alone is insufficient. This example makes no automatic retry.
Compare related models
Public quotes
Public prices
Providers
- Input/ 1M tokensDefault
- $0.54
- Output/ 1M tokensDefault
- $2.16
- Cache read/ 1M tokensDefault
- $0.108
- Cache write/ 1M tokensDefault
- $0.27
Default/ 1M tokens
Channel: ChineseLLM-stable
<=512K · ≤524,288 tokens/ 1M tokens
- Input/ 1M tokens<=512K · ≤524,288 tokens
- $0.54
- Output/ 1M tokens<=512K · ≤524,288 tokens
- $2.16
- Cache read/ 1M tokens<=512K · ≤524,288 tokens
- $0.108
- Cache write/ 1M tokens<=512K · ≤524,288 tokens
- $0.27
>512K · >524,288 tokens/ 1M tokens
- Input/ 1M tokens>512K · >524,288 tokens
- $1.08
- Output/ 1M tokens>512K · >524,288 tokens
- $4.32
- Cache read/ 1M tokens>512K · >524,288 tokens
- $0.216
- Cache write/ 1M tokens>512K · >524,288 tokens
- $0.27
Official prices and discounts use the same billing unit and tier.
Each price shows its own billing unit. Input, output, cache and reference media are charged separately where listed.