How much does MiniMax M3 cost on Velqa?

MiniMax M3 costs $0.353 per million input tokens and $1.410 per million output tokens, in USD. It is included from the Dev plan up.

Can I use MiniMax M3 without a subscription?

Yes. MiniMax M3 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 MiniMax M3 compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "minimax-m3" — MiniMax M3 answers on the standard chat completions endpoint, streaming included.

MiniMax M3 API — pricing and access

Raisonnement agentic, meilleur rapport perf/prix

Input: $0.353 USD / 1M tokens
Output: $1.410 USD / 1M tokens
Context: 131k
Available on: Dev and above
Provider: MiniMax

MiniMax M3 targets the production agent: an assistant chaining search, API calls, and multi-step decisions, with the best price-to-performance ratio in the catalog for that kind of task. It's available from the Dev plan and its 131k window covers most agent sessions without needing a wider context.

Against MiMo V2.5, a Dev-tier neighbor, MiniMax M3 reasons better on complex agentic tasks but offers a shorter context window — MiMo V2.5 remains the better pick for ingesting a very large document. Against Hunyuan Hy3, available from Starter with a similar positioning, MiniMax M3 justifies its higher plan with sturdier handling of long chains of tool calls.

It is not the right choice when context needs to exceed 131k tokens: MiMo V2.5 or Hunyuan Hy3, both at 256k, fit better. It also isn't a specialist for coding on an existing codebase: Kimi K2.6 is better suited to that specific use.

Measured on Velqa

Time to first token: 1.14 s
Throughput: 89.3 tokens/s

Median of 5 streamed calls against api.velqa.dev, 2026-08-10.

Results announced by the provider

SWE-Bench Pro : 59.0 % source (2026-06-01)

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": "minimax-m3",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does MiniMax M3 cost on Velqa?: MiniMax M3 costs $0.353 per million input tokens and $1.410 per million output tokens, in USD. It is included from the Dev plan up.
Can I use MiniMax M3 without a subscription?: Yes. MiniMax M3 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 MiniMax M3 compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "minimax-m3" — MiniMax M3 answers on the standard chat completions endpoint, streaming included.