Baltor Get started

Models

MiniMax-M2.7

By MiniMaxAI. 228.7 billion parameters, a context window of 204,800 tokens and the licence other.

Facts

Released
2026-04-09 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
228.7 billion counted from the safetensors weight files Hugging Face, read
Active parameters
11.0 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 204,800 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 in, text out Hugging Face, read
Good for
No source names a use.

Prices

Each provider's own price in US dollars per million tokens, as an openly licensed source lists it
ProviderInputOutputContextAs ofSource
Nvidia0 USD0 USD204,800 older than 30 days; check the providermodels.dev, read
Deep Infra0.250 USD1.00 USD196,608 older than 30 days; check the providermodels.dev, read
Pioneer0.279 USD1.20 USD204,800 older than 30 days; check the providermodels.dev, read
Abacus0.300 USD1.20 USD204,800 older than 30 days; check the providermodels.dev, read
CommandCode0.300 USD1.20 USD200,000 older than 30 days; check the providermodels.dev, read
GMI Cloud0.300 USD1.20 USD196,608 older than 30 days; check the providermodels.dev, read
Hugging Face0.300 USD1.20 USD204,800 older than 30 days; check the providermodels.dev, read
Together AI0.300 USD1.20 USD196,608 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_M56.5 GiB61.8 GiB67.6 GiB
UD-IQ2_XXS60.9 GiB66.4 GiB72.2 GiB
UD-IQ2_M65.3 GiB71.0 GiB76.8 GiB
UD-Q2_K_XL70.1 GiB76.1 GiB81.9 GiB
UD-IQ3_S77.9 GiB84.2 GiB90.0 GiB
UD-Q3_K_S87.2 GiB94.0 GiB99.8 GiB
UD-Q3_K_M94.3 GiB101 GiB107 GiB
UD-Q3_K_XL94.9 GiB102 GiB108 GiB
UD-Q4_K_S122 GiB131 GiB136 GiB
MXFP4_MOE127 GiB136 GiB141 GiB
UD-Q4_K_M131 GiB140 GiB145 GiB
UD-Q4_K_XL131 GiB140 GiB146 GiB
UD-Q5_K_S148 GiB158 GiB164 GiB
UD-Q5_K_M157 GiB168 GiB173 GiB
UD-Q5_K_XL158 GiB168 GiB174 GiB
UD-Q6_K175 GiB186 GiB192 GiB
UD-Q6_K_XL193 GiB205 GiB211 GiB
Q8_0226 GiB240 GiB246 GiB
UD-Q8_K_XL230 GiB244 GiB249 GiB
BF16426 GiB450 GiB456 GiB

Start it with a local runtime

  • Ollama
    ollama run hf.co/unsloth/MiniMax-M2.7-GGUF:UD-IQ1_M
  • LM Studio
    lms get unsloth/MiniMax-M2.7-GGUF
    lms server start
  • llama.cpp server
    llama-server -hf unsloth/MiniMax-M2.7-GGUF:UD-IQ1_M --jinja
  • vLLM
    vllm serve MiniMaxAI/MiniMax-M2.7
  • SGLang
    sglang serve --model-path MiniMaxAI/MiniMax-M2.7 --port 30000

Use it from your harness

Set up for Abacus with the model MiniMaxAI/MiniMax-M2.7. 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-M2.7": {
          "name": "MiniMax-M2.7"
        }
      }
    }
  }
}
  • 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-M2.7"
        }
      ]
    }
  }
}
  • 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.