Models
minimax-m3 — API, Pricing & Context Window | Vivgrid
minimax-m3 on Vivgrid: MiniMax's efficient coding model with a 512K context window, 128K max output, and very competitive pricing.
minimax-m3 is MiniMax's efficient coding model, combining a large 512K-token context window with 128K-token max output and very competitive token pricing. It's a strong value pick for long-context coding agents.
On Vivgrid, minimax-m3 is available through the unified, OpenAI-compatible endpoint and is accelerated in APAC, making it especially attractive for Asia-Pacific deployments.
Specifications
| Provider | MiniMax |
| Model ID | minimax-m3 |
| Best for | Coding |
| Context window | 512,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text |
| Tool / function calling | Yes |
| Knowledge cutoff | 2026-01 |
| Acceleration | 🌐 Global (Centralized) |
Pricing
Pricing in USD per 1M tokens, matching the provider's rates.
| Input | Cached input | Output |
|---|---|---|
| $1.20 | $0.24 | $2.40 |
Quick start
Call minimax-m3 through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.
curl https://api.vivgrid.com/v1/chat/completions \
-H "Authorization: Bearer $VIVGRID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [
{ "role": "user", "content": "Say hello in English, Chinese and Spanish." }
],
"stream": true
}'Ideal use cases
- Long-context coding agents on a budget
- APAC-based deployments needing low latency
- Tasks generating substantial code output
- High-volume engineering workloads
Related models
- minimax-m2.7 — the prior MiniMax generation
- glm-5.1 — alternative competitive coding model
- kimi-k2.6 — high-output coding model