Skip to main content

MiniMax M2.5 Highspeed

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

Input / output price
$0.60 / $2.40 per 1M
Context
205K tokens
Released
Feb 15, 2026
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-m2.5-highspeed".

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/minimax-m2-5-highspeed
$0.60/M$2.40/M
MiniMaxminimax/minimax-m2.5-highspeed
$0.60/M$2.40/M

Is a provider down? MiniMax status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.60 per 1M
Average output
$2.40 per 1M
Average cache read
$0.03 per 1M
Average cache write
$0.19 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.60/MConcentrate and MiniMax

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

5.1tokens/sacross providers

Faster than 10% of the other 599 models on the gateway

Response latency

Lower is better

0.8sacross providers

Faster than 72% of the other 780 models on the gateway

Apps

Use MiniMax M2.5 Highspeed 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 M2.5 Highspeed FAQ

Short answers, built from the data on this page.

MiniMax M2.5 Highspeed is a model from MiniMax, released on Feb 15, 2026. MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

On the Respan gateway, MiniMax M2.5 Highspeed costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on every provider, after gateway discounts.

MiniMax M2.5 Highspeed is available through 2 providers: Concentrate and MiniMax.

MiniMax M2.5 Highspeed 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-m2.5-highspeed". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

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.