Baltor Get started

Models

MiniMax-M3

By MiniMaxAI. 427.0 billion parameters, a context window of 1,048,576 tokens and the licence other.

Facts

Released
2026-06-02 the day the repository was first published on Hugging Face Hugging Face, read
Licence
other the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
427.0 billion counted from the safetensors weight files Hugging Face, read
Active parameters
5.8 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 1,048,576 tokens the maximum position embeddings in the model configuration model configuration, read
Longest output
Unknown
Tool calling
Unknown
Structured output
Unknown
Reasoning controls
Unknown
Inputs and outputs
text, image in, text out Hugging Face, read
Good for
  • Vision: Hugging Face files it under image-text-to-text Hugging Face, read

Prices

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
Nvidia0 USD0 USD1,000,000 older than 30 days; check the providermodels.dev, read
CoreWeave0.230 USD0.960 USD262,144 older than 30 days; check the providermodels.dev, read
Deep Infra0.280 USD1.10 USD524,288 older than 30 days; check the providermodels.dev, read
Lilac0.280 USD1.10 USD1,048,576 older than 30 days; check the providermodels.dev, read
Abacus0.300 USD1.20 USD1,000,000 older than 30 days; check the providermodels.dev, read
CommandCode0.300 USD1.20 USD1,000,000 older than 30 days; check the providermodels.dev, read
Hugging Face0.300 USD1.20 USD524,288 older than 30 days; check the providermodels.dev, read
Nebius Token Factory0.300 USD1.20 USD1,048,576 older than 30 days; check the providermodels.dev, read
Pioneer0.300 USD1.20 USD1,000,000 older than 30 days; check the providermodels.dev, read
SiliconFlow0.300 USD1.20 USD1,048,576 older than 30 days; check the providermodels.dev, read
Together AI0.300 USD1.20 USD524,288 older than 30 days; check the providermodels.dev, read
inferenceapis0.390 USD1.56 USD524,288LiteLLM, read
GMI Cloud0.600 USD2.40 USD1,048,576 older than 30 days; check the providermodels.dev, read

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
UD-IQ1_M120 GiB128 GiB131 GiB
UD-IQ2_XXS126 GiB133 GiB136 GiB
UD-IQ2_M126 GiB134 GiB136 GiB
UD-Q2_K_XL134 GiB142 GiB145 GiB
UD-IQ3_XXS149 GiB158 GiB161 GiB
UD-IQ3_S164 GiB173 GiB176 GiB
UD-Q3_K_M182 GiB193 GiB195 GiB
UD-Q3_K_XL182 GiB193 GiB196 GiB
UD-IQ4_XS194 GiB205 GiB208 GiB
UD-IQ4_NL198 GiB209 GiB212 GiB
UD-Q4_K_S232 GiB245 GiB247 GiB
MXFP4_MOE240 GiB253 GiB256 GiB
UD-Q4_K_M247 GiB261 GiB263 GiB
UD-Q4_K_XL248 GiB261 GiB264 GiB
UD-Q5_K_S279 GiB294 GiB297 GiB
UD-Q5_K_M297 GiB313 GiB316 GiB
UD-Q5_K_XL297 GiB314 GiB317 GiB
UD-Q6_K331 GiB349 GiB352 GiB
UD-Q6_K_XL361 GiB381 GiB384 GiB
Q8_0422 GiB445 GiB448 GiB
UD-Q8_K_XL433 GiB456 GiB459 GiB
BF16794 GiB835 GiB838 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/MiniMax-M3-GGUF:UD-IQ1_M
  • LM Studio
    lms get unsloth/MiniMax-M3-GGUF
    lms server start
  • llama.cpp server
    llama-server -hf unsloth/MiniMax-M3-GGUF:UD-IQ1_M --jinja
  • vLLM
    vllm serve MiniMaxAI/MiniMax-M3
  • SGLang
    sglang serve --model-path MiniMaxAI/MiniMax-M3 --port 30000

Use it from your harness

Set up for Abacus with the model MiniMaxAI/MiniMax-M3. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "abacus": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Abacus",
      "options": {
        "baseURL": "https://routellm.abacus.ai/v1",
        "apiKey": "{env:ABACUS_API_KEY}"
      },
      "models": {
        "MiniMaxAI/MiniMax-M3": {
          "name": "MiniMax-M3"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "abacus": {
      "baseUrl": "https://routellm.abacus.ai/v1",
      "api": "openai-completions",
      "apiKey": "$ABACUS_API_KEY",
      "models": [
        {
          "id": "MiniMaxAI/MiniMax-M3"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Abacus documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Abacus documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Other ways to reach it

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

Two more publishers are linked, never copied, because their terms do not allow it:

  • Artificial Analysis publishes its own intelligence, speed and price measurements.
  • OpenRouter lists current prices and uptime for each provider it routes to.