Last refreshed 2026-06-30. Next refresh: weekly.
Why use MiniMax M3 on MiniMax?
MiniMax offers MiniMax M3 with pay-as-you-go pricing at $0.30/1M input tokens. MiniMax is a multimodal foundation model and API platform for text, speech, video, image, and music generation with agent tools.
Compare MiniMax M3 across 2 providers to find the best fit for your use caseInput / 1M
$0.30
Output / 1M
$1.20
Cache
read $0.060
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: MiniMax-M3Model ID
MiniMax-M3Request example
Curated snippets for this provider are not sourced yet. Use MiniMax documentation with model ID
MiniMax-M3.Gotchas
- Use provider model ID "MiniMax-M3", not the LLMReference slug "minimax-m3".
Compare MiniMax M3 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| MiniMax | $0.30 | $1.20 |
| OpenRouter | $0.30 | $1.20 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $1.20 |
| Image input | $1.00 |
| Video input | $1.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt Caching
About MiniMax M3
MiniMax M3 is MiniMax's current API flagship (released June 1, 2026) with MiniMax Sparse Attention for economical 1M-token context, native multimodality, and agentic coding. Benchmark rows in LLMReference separate vendor-reported SWE-bench Pro, Terminal-Bench 2.1, MCP-Atlas, and BrowseComp scores (source: minimax.io) from third-party rows — inspect evaluator, variant, and source on each benchmark cell before comparing to leaderboard claims.
Get Started
Model Specs
Released2026-06-01
Context1m
ArchitectureDecoder Only