Qwen 3 235B A22B Instruct 2507
LiveAlibaba128K context · Text, ToolsBenchmark price · $0.14 input / $0.75 output per 1M tokens
Best discount now99.6%offYou pay 0.4% of reference.
Median discount83.8%offAcross 154 live offers.
Realized · 7 days99.0%avgRequest-weighted average.
Requests · 24h1,181154 offers from 55 sellers.
Current offers
154 of 249 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.245
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.095
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.140
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.055
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.055
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.060
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.026
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.025
Amazon Bedrock
99%
$0.00057 in
$0.00347 out
503ms
74.5%
17.8%
$0.011
Amazon Bedrock
99%
$0.00140 in
$0.00750 out
503ms
74.5%
17.8%
-
Total
Cumulative offers
Sold
$0.713
Discount trend
Realized · 7 days99.8%+0.1 pts vs last week
Best, twice dailyMedian 83.8%
Recent fills
16:37107 tokensAWS Bedrock100.0%
16:351,540 tokensAWS Bedrock99.4%
16:351,727 tokensAWS Bedrock99.5%
16:351,599 tokensAWS Bedrock99.4%
16:341,506 tokensAWS Bedrock99.3%
16:3421 tokensAWS Bedrock100.0%
16:3015 tokensAWS Bedrock100.0%
16:2811 tokensAWS Bedrock100.0%
16:23108 tokensAWS Bedrock100.0%
16:2015 tokensAWS Bedrock100.0%
16:17108 tokensAWS Bedrock100.0%
16:111,711 tokensAWS Bedrock99.4%
16:101,632 tokensAWS Bedrock99.1%
16:1015 tokensAWS Bedrock100.0%
16:101,547 tokensAWS Bedrock99.4%
16:094,061 tokensAWS Bedrock99.7%
16:094,867 tokens99.0%
16:094,884 tokensAWS Bedrock99.7%
16:094,935 tokensAWS Bedrock99.6%
16:094,993 tokensAWS Bedrock99.6%
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 | 2.25 s | 7.49 s | 444 tok/s | 74.5% | 100% |
AWS Bedrock100% of traffic
74.5% 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
- top_kintegerTop-k sampling
- min_pnumberDrops tokens below this share of the top token’s probability
- 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
- reasoning_effortstringHow hard to think, as a string such as "high"
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
- include_reasoningbooleanStripped before the request reaches the provider
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
- repetition_penaltynumberPenalises repeated tokens
- logit_biasobjectPer-token bias on the logits
- logprobsbooleanReturn token log probabilities
Context window 128K tokens · Max output 16K 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="qwen3-235b-a22b-2507", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1