GLM-5.2, MiniMax-M3 and Kimi K2.7 are now live. Try them now
Sign Up
minimax

minimax-m3

Open-weight model built for coding, long-context agent work and multimodal input.

minimax 1M context ★ Featured
Get API Key View Pricing

Value rank

#10 of 23

intelligence per dollar in our catalogue

Context rank

#1 tied

1M token window

Agentic strength

89%

tau2-bench tool-use success

Benchmarks

Independent scores by Artificial Analysis, compared with the strongest models in our catalogue.

Intelligence index

glm-5.2
51.1
minimax-m3
44.4
deepseek-v4-pro
44.3
kimi-k2.6
42.8
kimi-k2.7-code
41.9

Coding index

glm-5.2
50.7
deepseek-v4-pro
47.5
kimi-k2.6
47.1
kimi-k2.7-code
45.8
minimax-m3
43.4

Agentic (tau2-bench)

deepseek-v4-pro
96.2%
kimi-k2.6
95.9%
minimax-m3
88.9%

Best for

Where this model earns its keep.

Long-document analysis Coding and engineering Vision and image-aware tasks Prompt-cached workloads

The numbers

Pricing is live from our platform. Prices per 1M tokens, zero data retention on every request.

Input price$0.40
Cache read price$0.10
Output price$2.00
Context window1M tokens
Intelligence / coding index44.4 / 43.4
Agentic: tau2 / terminal-bench89% / 42%
GPQA / MMLU-Pro93% / -

Or consider

Close alternatives in the catalogue.

deepseek-v4-pro

Intelligence 44.3 · agentic 96%

kimi-k2.6

Intelligence 42.8 · agentic 96%

kimi-k2.7-code

Intelligence 41.9 · agentic -

Quick start

OpenAI-compatible. Switch in one line.

# pip install openai
client = OpenAI(base_url="https://api.tensorx.ai/v1", api_key="tsx-...")
r = client.chat.completions.create(
    model="minimax/minimax-m3",
    messages=[{"role": "user", "content": "Hello"}],
)

Benchmark data from the Artificial Analysis Intelligence Index v4.1, measured independently. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.