Model / inference API

Minimax

MiniMax sells its model API through the MiniMax Open Platform, and it suits developers who want M3 or M3.1 Flash directly from the maker at a low token rate.

Website (opens in a new tab)

Checked 2026-11-05

MiniMax sells its model API through the MiniMax Open Platform, and it suits developers who want M3 or M3.1 Flash directly from the maker at a low token rate. The pay-as-you-go page, as listed on 5 November 2026, prices per million tokens. M3.1 Flash is $0.15 input and $0.60 output, with cache reads at $0.015. M3 is $0.30 and $1.20 up to 512k input tokens, and $0.60 and $2.40 above that. Priority service costs 1.5 times standard, set with a service tier parameter. The page calls the M3 rates a permanent 50% discount, and it lists M Plan subscriptions and audio and video packages, which we did not read in detail. It does not mention a Token Plan or Coding Plan, so we say nothing about those. The catch is data: MiniMax's privacy overview says each product has its own policy and points enterprise API users to a separate document, which opened empty for us, so we cannot state training, retention or location. Figures come from MiniMax's pricing page. We have not run it ourselves. We would use it to cost M3.1 Flash for agent loops and compare against resellers.

Mentioned here

Questions

How much does Minimax cost?

Pay as you go, priced per model across text, video, audio and image, with prepaid packages for audio and video. The pricing pages list each model's unit price, for example 768P video at $0.04 (checked 5 November 2026).

Is Minimax OpenAI compatible?

Yes, it offers an OpenAI-compatible API, so most agents and SDKs can point at it by changing the base URL.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Moonshot AI

    Moonshot AI sells the Kimi API through its developer platform, now at platform.kimi.ai, and it suits teams who want Kimi K3 and K3.1 Pro with a 1,048,576-token context window straight from the maker.

    • Model / inference API
    • OpenAI compatible

  • Featherless

    Featherless is a flat-rate subscription for open models, not a per-token meter, and it suits hobbyists and small teams who want to switch between many open models for one monthly price.

    • Model / inference API
    • OpenAI compatible

  • Z.AI

    Z.ai sells the GLM model family through its open platform API, and it suits developers who want GLM 5.3 straight from the maker, with free small models for testing.

    • Model / inference API
    • OpenAI compatible

  • AI21

    AI21 sells the Jamba model family through an API, and it suits teams that want a long-context model from a vendor that says it does not train on customer inputs.

    • Model / inference API

  • Databricks

    Databricks sells model serving inside its data platform, so it suits teams that already keep data and pipelines on Databricks and want hosted open models next to them.

    • Model / inference API
    • OpenAI compatible

  • Nvidia

    NVIDIA's API platform at build.nvidia.com hosts models as NIM microservices on its DGX Cloud for trying out, and it suits developers who want to test Nemotron and other models before deciding where to run them.

    • Model / inference API