MiMo V2.5 API — pricing and access
Généraliste texte, chat et agentic
- Input
- $0.250 USD / 1M tokens
- Output
- $0.500 USD / 1M tokens
- Context
- 256k
- Available on
- Dev and above
- Provider
- Xiaomi
Try MiMo V2.5 in the playground
MiMo V2.5 is a text and agentic generalist available from the Dev plan, with a 256k window and a very low price per token for that tier. It's a solid default for an assistant that needs to read large documents — contracts, transcripts, knowledge bases — while still being able to trigger a handful of tool calls.
Against Hunyuan Hy3, positioned on the same generalist-agentic niche but available from Starter, MiMo V2.5 needs a higher plan for fairly similar reasoning: picking it mostly makes sense for its wider context window. Against MiniMax M3, a Dev-tier neighbor, MiMo V2.5 stays less precise on multi-step agentic tasks, but cheaper and wider in context.
It is not the right choice for a coding agent that has to sustain a long, complex development session: Kimi K2.6 is specifically built for that. It also isn't a flagship reasoning model: for deep analysis, DeepSeek V4 Pro or Qwen3.7 Max are better placed.
Measured on Velqa
- Time to first token
- 0.99 s
- Throughput
- 64.3 tokens/s
Median of 5 streamed calls against api.velqa.dev, 2026-08-10.
Results announced by the provider
- Claw-Eval (general subset) : 62.3 source (2026-04-22)
Call it
OpenAI-compatible endpoint — change the base URL and the model id, nothing else.
curl https://api.velqa.dev/v1/chat/completions \
-H "Authorization: Bearer $VELQA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mimo-v2.5",
"messages": [{"role": "user", "content": "Hello"}]
}'Related models
FAQ
- How much does MiMo V2.5 cost on Velqa?
- MiMo V2.5 costs $0.250 per million input tokens and $0.500 per million output tokens, in USD. It is included from the Dev plan up.
- Can I use MiMo V2.5 without a subscription?
- Yes. MiMo V2.5 can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.
- Is MiMo V2.5 compatible with the OpenAI API?
- Yes. Point your client at https://api.velqa.dev/v1 and set the model to "mimo-v2.5" — MiMo V2.5 answers on the standard chat completions endpoint, streaming included.
