MiniMax M3.1 Flash
LiveMiniMax1M context · Text, Vision, Video, Tools, ReasoningBenchmark price · $0.15 input / $0.6 output per 1M tokens
Best discount now95.0%offYou pay 5.0% of reference.
Median discount91.0%offAcross 88 live offers.
Realized · 7 days81.7%avgRequest-weighted average.
Requests · 24h51,30188 offers from 30 sellers.
Current offers
88 of 137 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Together AI
93%
$0.0103 in
$0.0412 out
1.7s
99.4%
93.2%
$166
Total
Cumulative offers
Sold
$195
Discount trend
Realized · 7 days98.6%−1.3 pts vs last week
Best, twice dailyMedian 91.0%
Recent fills
17:405,300 tokensTogether AI93.1%
17:40241,450 tokensTogether AI93.1%
17:40469,625 tokensTogether AI93.1%
17:39240,610 tokensTogether AI93.1%
17:39469,316 tokensTogether AI93.1%
17:39239,527 tokensTogether AI93.1%
17:39466,517 tokensTogether AI93.1%
17:39239,364 tokensTogether AI93.1%
17:39626 tokensTogether AI93.3%
17:39139,221 tokensTogether AI93.1%
17:39638,281 tokensTogether AI93.1%
17:3963,901 tokensTogether AI93.1%
17:391,528 tokensTogether AI92.5%
17:394,834 tokensTogether AI93.1%
17:39235,186 tokensTogether AI93.1%
17:39637,907 tokensTogether AI93.1%
17:39234,855 tokensTogether AI93.1%
17:3961,680 tokensTogether AI93.1%
17:39637,707 tokensTogether AI93.1%
17:38465,893 tokensTogether AI93.1%
Times in UTCSettled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Together AI direct | 4.11 s | 33.57 s | 243 tok/s | 99.4% | 86% |
| InferHub | 7.49 s | 45.32 s | 134 tok/s | 91.3% | 8% |
| Venice AI direct | 7.49 s | 33.57 s | 329 tok/s | 99.8% | 4% |
| OpenRouter | 5.55 s | 33.57 s | 99 tok/s | 99.6% | 2% |
Together AI direct86% of traffic
99.4% success
InferHub8% of traffic
91.3% success
Venice AI direct4% of traffic
99.8% success
OpenRouter2% of traffic
99.6% success
Use this modelChange your base URL.
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 ↗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 ↗
from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="minimax-m3-1-flash", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1