MiniMax M1 80K
For detailed vLLM deployment instructions, please refer to our vLLM Deployment Guide. Special Note: Using vLLM versions below 0.9.2 may result in incompatibility or incorrect precision for the model. Alternatively, you can also deploy using Transformers directly. For detailed Transformers deployment instructions, you can see our MiniMax-M1 Transformers Deployment Guide.
- Input / output price
- $0.55 / $2.20 per 1M
- Context
- 1M tokens
- Released
- Jun 16, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
NovitaRetiring novita/minimax-m1-80k | $0.55/M | $2.20/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.55 per 1M
- Output
- $2.20 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better23tokens/sacross providers
Response latency
Lower is better1.9sacross providers
Benchmarks
7 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchhuggingface.co | 65% | huggingface.co | Jun 13, 2025 |
| SWE-bench Verifiedhuggingface.co | 56% | huggingface.co | Jun 13, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA Diamondhuggingface.co | 70% | huggingface.co | Jun 13, 2025 |
| Humanity's Last Exam (no tools)huggingface.co | 8.4% | huggingface.co | Jun 13, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2024huggingface.co | 86% | huggingface.co | Jun 13, 2025 |
| AIME 2025huggingface.co | 76.9% | huggingface.co | Jun 13, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-Prohuggingface.co | 81.1% | huggingface.co | Jun 13, 2025 |
Apps
Use MiniMax M1 80K in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
MiniMax M1 80K FAQ
Short answers, built from the data on this page.
MiniMax M1 80K is a model from MiniMax, released on Jun 16, 2025. For detailed vLLM deployment instructions, please refer to our vLLM Deployment Guide. Special Note: Using vLLM versions below 0.9.2 may result in incompatibility or incorrect precision for the model. Alternatively, you can also deploy using Transformers directly. For detailed Transformers deployment instructions, you can see our MiniMax-M1 Transformers Deployment Guide.
On the Respan gateway, MiniMax M1 80K costs $0.55 per 1M input tokens and $2.20 per 1M output tokens on Novita, after gateway discounts.
MiniMax M1 80K is served by Novita.
MiniMax M1 80K accepts up to 1M tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "minimax-m1-80k". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
MiniMax M1 80K has 7 published benchmark scores, including LiveCodeBench 65%, GPQA Diamond 70%, and AIME 2024 86%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.