Mistral Large 3
LiveMistral AI256K context · Text, VisionBenchmark price · $0.5 input / $1.5 output per 1M tokens
Best discount now99.0%offYou pay 1.0% of reference.
Median discount75.0%offAcross 35 live offers.
Realized · 7 days95.5%avgRequest-weighted average.
Requests · 24h7,25035 offers from 9 sellers.
Current offers
35 of 65 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Amazon Bedrock
99%
$0.00500 in
$0.0150 out
679ms
77.0%
6.0%
$3
Amazon Bedrock
99%
$0.00500 in
$0.0150 out
679ms
77.0%
6.0%
$3
Amazon Bedrock
99%
$0.00500 in
$0.0150 out
679ms
77.0%
6.0%
$0.004
Amazon Bedrock
99%
$0.00500 in
$0.0150 out
679ms
77.0%
6.0%
$2
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$2
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$1
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$1
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$0.572
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$0.606
Amazon Bedrock
95%
$0.0248 in
$0.0742 out
679ms
77.0%
6.0%
$0.359
Total
Cumulative offers
Sold
$15
Discount trend
Realized · 7 days99.4%+2.1 pts vs last week
Best, twice dailyMedian 75.0%
Recent fills
23:1010 tokensAWS Bedrock100.0%
23:093,656 tokensAWS Bedrock99.0%
23:097,836 tokensAWS Bedrock99.0%
23:093,730 tokensAWS Bedrock99.0%
23:095,835 tokensAWS Bedrock99.0%
23:091,747 tokensAWS Bedrock99.1%
23:094,305 tokensAWS Bedrock99.0%
23:097,789 tokensAWS Bedrock99.0%
23:097,748 tokensAWS Bedrock99.0%
23:095,339 tokensAWS Bedrock99.0%
23:094,783 tokensAWS Bedrock99.0%
23:097,766 tokensAWS Bedrock99.0%
23:0912 tokensAWS Bedrock100.0%
23:084,771 tokensAWS Bedrock99.0%
23:0841,951 tokensAWS Bedrock99.0%
23:08594 tokensAWS Bedrock99.1%
23:084,293 tokensAWS Bedrock99.0%
23:0840,920 tokensAWS Bedrock99.0%
23:085,388 tokensAWS Bedrock99.0%
23:074,147 tokensAWS Bedrock99.0%
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 |
|---|---|---|---|---|---|
| AWS Bedrock | 5.55 s | 18.42 s | 99 tok/s | 77.0% | 100% |
AWS Bedrock100% of traffic
77.0% 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
- temperaturenumberSampling temperature
- top_pnumberNucleus sampling
- stopstring | arrayStop sequences
- seedintegerDeterministic sampling
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- response_formatobjectJSON mode or a JSON schema for structured output
- structured_outputsbooleanAccepts a JSON schema in response_format
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
Context window 256K tokens · Max output 32K 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="mistral-large-3", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1