Tencent: Hy4 preview
LiveTencent1M context · Text, Tools, ReasoningBenchmark price · $0.834 input / $2.5 output per 1M tokens
Best discount now88.0%offYou pay 12.0% of reference.
Median discount17.0%offAcross 18 live offers.
Realized · 7 days19.7%avgRequest-weighted average.
Requests · 24h5918 offers from 12 sellers.
Current offers
18 of 23 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
InferHub
88%
$0.0999 in
$0.30 out
-
-
-
-
InferHub
88%
$0.1000 in
$0.30 out
-
-
-
-
InferHub
88%
$0.1000 in
$0.30 out
-
-
-
-
InferHub
88%
$0.1000 in
$0.30 out
-
-
-
-
InferHub
88%
$0.10 in
$0.30 out
-
-
-
-
InferHub
85%
$0.13 in
$0.38 out
-
-
-
-
InferHub
68%
$0.27 in
$0.80 out
-
-
-
-
InferHub
68%
$0.27 in
$0.80 out
-
-
-
-
Venice AI
19%
$0.67 in
$2.00 out
916ms
100.0%
11.1%
$0.015
OpenRouter
14%
$0.72 in
$2.15 out
-
-
-
-
Total
Cumulative offers
Sold
$0.015
Discount trend
Realized · 7 days20.2%
Best, twice dailyMedian 17.0%
Recent fills
13:1938 tokensVenice AI19.0%
13:07162 tokensVenice AI20.0%
13:07335 tokensVenice AI19.9%
12:1438 tokensVenice AI19.0%
12:08163 tokensVenice AI19.9%
11:0938 tokensVenice AI19.0%
11:07334 tokensVenice AI20.0%
11:07164 tokensVenice AI20.2%
10:07163 tokensVenice AI19.9%
10:0438 tokensVenice AI19.0%
09:07164 tokensVenice AI20.2%
09:07335 tokensVenice AI19.9%
08:5938 tokensVenice AI
07:5438 tokensVenice AI
07:13754 tokensVenice AI
07:13673 tokensVenice AI
07:1344 tokensVenice AI
07:13235 tokensVenice AI
07:13267 tokensVenice AI
07:13132 tokensVenice AI
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 |
|---|---|---|---|---|---|
| Venice AI direct | 1.67 s | - | - | 100.0% | 100% |
Venice AI direct100% of traffic
100.0% 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
- max_completion_tokensintegerSame as max_tokens
- temperaturenumberSampling temperature
- stopstring | arrayStop sequences
- 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
Context window 1M tokens · Max output 64K 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="hy4-preview", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1