MiniMax M3.1 Flash

Name: MiniMax M3.1 Flash
Brand: MiniMax
SKU: minimax-m3-1-flash
Availability: InStock

Live

MiniMax1M context · Text, Vision, Video, Tools, Reasoning

Use this model

Best discount now10.0%offYou pay 90.0% of reference.

Median discount10.0%offAcross 1 live offer.

Realized · 7 days10.2%avgRequest-weighted average.

Requests · 24h2,6891 offer from 1 seller.

Current offers

1 of 8 offers

Availability

Providers

Sort by

ProviderDiscountPriceLatencyUptimeSold

Venice AI

10%

$0.17 in

$0.68 out

3.0s

99.9%

Total

Cumulative offers

Sold

Discount trend

Realized · 7 days

47.1%

Best, twice dailyMedian 10.0%

Recent fills

20:32211,710 tokensVenice AI direct10.0%

20:32629 tokensVenice AI direct9.9%

20:32210,659 tokensVenice AI direct10.0%

20:32208,123 tokensVenice AI direct10.0%

20:32207,812 tokensVenice AI direct10.0%

20:32207,422 tokensVenice AI direct10.0%

20:31205,698 tokensVenice AI direct10.0%

20:31638 tokensVenice AI direct10.2%

20:31204,811 tokensVenice AI direct10.0%

20:31635 tokensVenice AI direct10.3%

20:31203,206 tokensVenice AI direct10.0%

20:31202,851 tokensVenice AI direct10.0%

20:31633 tokensVenice AI direct10.0%

20:31201,878 tokensVenice AI direct10.0%

20:31201,330 tokensVenice AI direct10.0%

20:30201,072 tokensVenice AI direct10.0%

20:30200,597 tokensVenice AI direct10.0%

20:30199,803 tokensVenice AI direct10.0%

20:30199,186 tokensVenice AI direct10.0%

20:30197,219 tokensVenice AI direct10.0%

Settled on Base in USDC.Times in UTC

Performance by provider route · 24h

Measured on Surplus traffic

Route	p50 latency	p95 latency	Throughput	Success rate	ShareShare of traffic
Venice AI direct	7.49 s	33.57 s	180 tok/s	99.9%	100%

Venice AI direct100% of traffic

99.9% success

p50 7.49 s · p95 33.57 s · 180 tok/s

Use this model

Change your base URL.
Keep your code.

Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.

Read the quickstart ↗

Build with agents

Parameters this model acceptsPOST /v1/chat/completions

modelstringThis model’s id
messagesarrayThe conversation, as role and content pairs
streambooleanSend the answer as server-sent events
max_tokensintegerMost output tokens to generate
toolsarrayFunctions the model may call, in the OpenAI format
tool_choicestring | objectauto, required, none, or one named function
reasoning_effortstringHow hard to think, as a string such as "high"
reasoningobjectReasoning options as an object, such as {"effort": "high"}

Context window 1M tokens · Max output 131K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗

curl https://api.surplusintelligence.ai/v1/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3-1-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl $SURPLUS_BASE_URL/chat/completions \
  -H "Authorization: Bearer $SURPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3-1-flash",
    "messages": [{"role": "user",
                  "content": "Hello"}]
  }'

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

MiniMax M3.1 Flash

Discount trend

Recent fills

Performance by provider route · 24h

Change your base URL.Keep your code.

Related models

Change your base URL.
Keep your code.