Specs & substance
- Developed by
- MiniMax
- Model family
- MiniMax
- Use case
- Multimodal agentic
- Modality
- Text + Vision + Video
- Context window
- 1M tokens
- Architecture
- MoE + MSA
- Version
- M3.1 Flash
- License
- MiniMax Community License
- Pricing
- $0.15 in · $0.60 out · $0.015 cache read
- Released
- Oct 2026
- Endpoint
- parasail-minimax-m31-flash
MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. It takes text, image, and video input and returns text, with a context window of up to 1M tokens.
It keeps M3’s core MoE architecture and changes three things: MiniMax Sparse Attention replaces full attention in the first three layers, the routed experts and attention paths are quantized during training, and DSpark speculative decoding replaces the earlier EAGLE-like MTP head. The model has roughly 428B total parameters with 23B activated per token; the release includes the DSpark draft head for compatible serving implementations.
Parasail serves MiniMax M3.1 Flash on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.
Measured on the work that matters
MiniMax M3.1 Flash model-card results alongside selected comparison models.
All scores are self-reported by MiniMax in the MiniMax-M3.1-Flash model card on Hugging Face ; the comparison columns are those MiniMax reports in its model card, which names each benchmark harness in its evaluation notes. Where a benchmark is reported both with and without tool augmentation, we show the lower, no-tools number.
Drop-in via the OpenAI SDK
Point any OpenAI-compatible client at Parasail and change the model name. That's it.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.parasail.io/v1"
)
response = client.chat.completions.create(
model="parasail-minimax-m31-flash",
messages=[
{"role": "user", "content": "Implement Hello World in Python"}
],
stream=True,
stream_options={"include_usage": True},
top_p=0.95,
max_tokens=1000,
temperature=1
)
for chunk in response:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.parasail.io/v1"
)
response = client.chat.completions.create(
model="parasail-minimax-m31-flash",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "What is broken in this UI screenshot?"},
{"type": "image_url", "image_url": {"url": "https://example.com/screenshot.png"}}
]
}
],
max_tokens=1000
)
print(response.choices[0].message.content)curl https://api.parasail.io/v1/chat/completions \
-H "Authorization: Bearer $PARASAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "parasail-minimax-m31-flash",
"messages": [{"role": "user", "content": "Implement Hello World in Python"}],
"stream": true,
"max_tokens": 1000
}'Explore the library
MiniMax M3
Highly efficient MoE model delivering strong reasoning at exceptionally low cost.
MiniMax M2.5
Cost-effective large model with strong general capabilities and long context.
DeepSeek V4.1 Flash
Multimodal 552B-parameter MoE with 1M-token context, compressed KV cache, and efficient agentic reasoning.
Kimi K3
Moonshot's 2.8T-parameter open-weight multimodal agentic model — frontier reasoning, native vision, and a 1M-token context window.
Run MiniMax M3.1 Flash on Parasail.
Call it on an OpenAI-compatible endpoint at $0.15 in and $0.60 out per million tokens, or ask us about dedicated capacity.