MiniMax M2.5 Highspeed
MiniMax M2.5 Highspeed is MiniMax's language model with a 205K context window and up to 131K output tokens, starting at $0.600 / 1M input and $2.40 / 1M output. An accelerated high-throughput variant of MiniMax M2.5 engineered for scenarios demanding extreme efficiency while preserving core intelligence and digital workspace capabilities.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 Vercel AI Gateway | $0.600 | $2.40 | $0.030 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiniMax M2.7 Highspeed | 205K | $0.600 | $2.40 | Available | |
| MiniMax M2.5 Highspeed | 205K | $0.600 | $2.40 | Current | |
| MiniMax M2.5 Lightning | — | 1.0M | $0.300 | $2.40 | Available |
| MiniMax M2.1 Lightning | 1.0M | $0.300 | $2.40 | Available | |
| MiniMax M2 Her | 66K | $0.300 | $1.20 | Available | |
| MiniMax M2 MaaS | — | 197K | $0.300 | $1.20 | Available |