Benchmarks
independent evaluations · source: ARC Prize, Artificial Analysis and Hugging Face leaderboards| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| ARC-AGI-2 | 5% | default | $0.17 | |
| CritPt | 1% | default | — | |
| EvalComputeProxyFrozen Aug 18, 2026 | 103.3 | default | — | |
| GPQA Diamond | 85% | default | — | |
| Humanity's Last Exam | 21% | default | — | |
| IFBench | 72% | default | — | |
| Long-Context Reasoning | 73% | default | — | |
| Omniscience | -38.9 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 43% | — | — | |
| SWE-bench Pro | 55% | default | — | |
| SWE-bench Verified | 76% | default | — | |
| TerminalBench Hard | 35% | default | — | |
| τ²-bench | 95% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.27 to $0.30 per 1M tokens across 10 providers, so the dearest route costs 11% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterRouted quote | $0.27 | $1.08 | 1 | ||||||||||||||||
Standardminimax/minimax-m2.5
| |||||||||||||||||||
| Baseten | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardbaseten/MiniMaxAI/MiniMax-M2.5
| |||||||||||||||||||
| Amazon Bedrock | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardbedrock/us-east-1/minimax.minimax-m2.5
| |||||||||||||||||||
| Friendliai | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardfriendliai/MiniMaxAI/MiniMax-M2.5
| |||||||||||||||||||
| Minimax | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardminimax/MiniMax-M2.5
| |||||||||||||||||||
| Nebius | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardnebius/MiniMaxAI/MiniMax-M2.5
| |||||||||||||||||||
| Novita | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardnovita/minimax/minimax-m2.5
| |||||||||||||||||||
| Tensormesh | $0.30 | $1.20 | 1 | ||||||||||||||||
Standardtensormesh/MiniMaxAI/MiniMax-M2.5
| |||||||||||||||||||
| Vercel is dearest at $0.60 / $2.40 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokensCost calculator
estimate your monthly spend on this modelModel IDs
copy the exact identifier for your platformFrequently asked questions
MiniMax M2.5 pricing, context and availabilityIs MiniMax M2.5 still available?
MiniMax M2.5 was deprecated on 2026-08-25, but 10 serving providers still list it.
How much does MiniMax M2.5 cost?
MiniMax M2.5 costs $0.27 per 1M input tokens as an OpenRouter routed quote, while Minimax lists it at $0.30 per 1M input, and $1.08 per 1M output tokens as an OpenRouter routed quote, while Minimax lists it at $1.20 per 1M output. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 10 serving providers, input prices range from $0.27 to $0.30 per 1M tokens.
What is the context window of MiniMax M2.5?
MiniMax M2.5 accepts up to 1M tokens of context and can return up to 197K output tokens.
Which providers serve MiniMax M2.5?
MiniMax M2.5 is available from 10 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.
What can MiniMax M2.5 do?
MiniMax M2.5 supports tool use, reasoning, prompt caching and structured output.
Other MiniMax models
compare pricing across the MiniMax lineupEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI