GPT-5.5
LiveOpenAI1M context · Text, Vision, Tools, ReasoningBenchmark price · $5 input / $30 output per 1M tokens
Best discount now97.5%offYou pay 2.5% of reference.
Median discount36.3%offAcross 70 live offers.
Realized · 7 days76.5%avgRequest-weighted average.
Requests · 24h6,99970 offers from 52 sellers.
Current offers
70 of 165 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
OpenAI
86%
$0.65 in
$3.90 out
1.2s
95.0%
88.6%
$119
Total
Cumulative offers
Sold
$148
Discount trend
Realized · 7 days97.7%−2.3 pts vs last week
Best, twice dailyMedian 36.3%
Recent fills
17:39338 tokensOpenAI direct86.5%
17:3919 tokensOpenAI direct86.3%
17:3964 tokensOpenAI direct86.5%
17:3919 tokensOpenAI direct86.3%
17:3919 tokensOpenAI direct86.3%
17:38276 tokensOpenAI direct86.5%
17:3868 tokensOpenAI direct86.5%
17:38101 tokensOpenAI direct86.5%
17:3773 tokensOpenAI direct86.5%
17:3759 tokensOpenAI direct86.5%
17:3664 tokensOpenAI direct86.4%
17:35268 tokensOpenAI direct86.5%
17:3567 tokensOpenAI direct86.5%
17:3566 tokensOpenAI direct86.4%
17:3461 tokensOpenAI direct86.3%
17:34274 tokensOpenAI direct86.4%
17:3463 tokensOpenAI direct86.4%
17:3319 tokensOpenAI direct86.3%
17:33276 tokensOpenAI direct86.4%
17:3363 tokensOpenAI direct86.4%
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 |
|---|---|---|---|---|---|
| OpenAI direct | 1.67 s | 18.42 s | 329 tok/s | 95.0% | 94% |
| Venice AI direct | 1.67 s | 4.11 s | - | 41.4% | 4% |
| AWS Bedrock | 916 ms | 2.25 s | - | 76.7% | 2% |
| InferHub | 2.25 s | - | 180 tok/s | 43.1% | 0% |
OpenAI direct94% of traffic
95.0% success
Venice AI direct4% of traffic
41.4% success
AWS Bedrock2% of traffic
76.7% success
InferHub0% of traffic
43.1% 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
- logit_biasobjectPer-token bias on the logits
- logprobsbooleanReturn token log probabilities
- top_logprobsintegerHow many top tokens to return probabilities for
Context window 1M tokens · Max output 128K 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="gpt-5.5", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1