Skip to main content

MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. $0.255 per million input tokens, $1.02 per million output tokens. 204,800 token context window, maximum output of 131,072 tokens. Higher uptime with 3 providers. Includes independent benchmarks from Artificial Analysis.

Input / output price
$0.255 / $1.02 per 1M
Context
205K tokens
Released
Oct 27, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "minimax/minimax-m2".

Read docs

Providers

4 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Bedrockbedrock/minimax-m2
$0.30/M$1.20/M
Concentrateconcentrate/minimax-m2
$0.30/M$1.20/M
MiniMaxminimax/minimax-m2
$0.30/M$1.20/M
OpenRouterRetiredopenrouter/minimax-m2
$0.255/M$1.02/M

Is a provider down? AWS Bedrock status, MiniMax status, OpenRouter status

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.29 per 1M
Average output
$1.15 per 1M
Average cache read
$0.01 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.30/MBedrock, Concentrate, and MiniMaxLowest$0.255/MOpenRouter

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 better

4.3tokens/sacross providers

Faster than 16% of the other 596 models on the gateway

Response latency

Lower is better

0.9sacross providers

Faster than 64% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 17 published scores from 4 sources, each linked to where it was published.

17.4/ 100

Respan Index#148 of 176

176 ranked models. The shaded band is this model's 95% interval, 13.8 to 26.4. Qwen3.5 4B and LongCat Flash Chat fall inside it, so the gap is within the margin of error.
MiniMax M2 by category: Coding 4.6, Agents 12.0, Reasoning 19.8, Knowledge & language 11.2 (estimated), Human preference 48.0
  1. 148MiniMax M217.4
  2. 147Qwen3.5 4B17.5
  3. 149LongCat Flash Chat16.8

Published scores

BenchmarkScore
SWE-bench Verifiedhuggingface.co69.4%
ArtifactsBenchhuggingface.co66.8%
SWE-bench Multilingualhuggingface.co56.5%
Terminal-Benchhuggingface.co46.3%
Multi-SWE-Benchhuggingface.co36.2%

Compare MiniMax M2: MiniMax M2 vs MiniMax M1, MiniMax M2 vs MiniMax M2.1, MiniMax M2 vs MiniMax M3.1 Flash, MiniMax M2 vs MiniMax M3, MiniMax M2 vs MiniMax M2.7

Apps

Use MiniMax M2 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 M2 FAQ

Short answers, built from the data on this page.

MiniMax M2 is a model from MiniMax, released on Oct 27, 2025. MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. $0.255 per million input tokens, $1.02 per million output tokens. 204,800 token context window, maximum output of 131,072 tokens. Higher uptime with 3 providers. Includes independent benchmarks from Artificial Analysis.

On the Respan gateway, MiniMax M2 costs from $0.255 per 1M input tokens and $1.02 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 4 providers, it costs $0.29 per 1M input tokens and $1.15 per 1M output tokens.

MiniMax M2 is available through 4 providers: Bedrock, Concentrate, MiniMax, and OpenRouter.

MiniMax M2 accepts up to 205K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "minimax/minimax-m2". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

MiniMax M2 scores 17.4 out of 100 on the Respan Index v1.1, ranking #148 of 176 models. By category: Coding 4.6, Agents 12.0, Reasoning 19.8, Knowledge & language 11.2 (estimated), and Human preference 48.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

MiniMax M2 has 17 published benchmark scores, including SWE-bench Verified 69.4%, τ²-Bench 77.2%, and HLE (w/ tools) 31.8%. 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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.