Tencent: Hy4
LiveTencent1M context · Text, Vision, Tools, ReasoningBenchmark price · $0.417 input / $1.25 output per 1M tokens
Best discount now85.0%offYou pay 15.0% of reference.
Median discount34.5%offAcross 12 live offers.
Realized · 7 days58.0%avgRequest-weighted average.
Requests · 24h14712 offers from 8 sellers.
Current offers
12 of 17 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
InferHub
85%
$0.0625 in
$0.19 out
4.1s
98.9%
79.2%
$0.185
InferHub
85%
$0.0625 in
$0.19 out
4.1s
98.9%
79.2%
-
InferHub
82%
$0.0712 in
$0.21 out
4.1s
98.9%
79.2%
-
InferHub
82%
$0.0712 in
$0.21 out
4.1s
98.9%
79.2%
-
InferHub
54%
$0.19 in
$0.56 out
4.1s
98.9%
79.2%
-
InferHub
54%
$0.19 in
$0.56 out
4.1s
98.9%
79.2%
-
OpenRouter
14%
$0.36 in
$1.08 out
1.7s
98.3%
26.5%
$0.002
InferHub
4%
$0.40 in
$1.19 out
4.1s
98.9%
79.2%
-
InferHub
4%
$0.40 in
$1.19 out
4.1s
98.9%
79.2%
-
InferHub
4%
$0.40 in
$1.19 out
4.1s
98.9%
79.2%
-
Total
Cumulative offers
Sold
$0.191
Discount trend
Realized · 7 days85.1%
Best, twice dailyMedian 34.5%
Recent fills
13:1938 tokensOpenRouter13.8%
13:1498,447 tokens85.1%
13:1397,366 tokens85.1%
13:1394,185 tokens85.1%
13:1338 tokensOpenRouter13.8%
13:1095,552 tokensInferHub85.1%
13:0995,384 tokens85.1%
13:0990,119 tokens85.1%
13:0891,010 tokensInferHub85.1%
13:0890,833 tokensInferHub85.1%
13:07163 tokensOpenRouter13.6%
13:07337 tokensOpenRouter14.3%
13:0787,607 tokens85.1%
13:0588,940 tokensInferHub85.1%
13:0588,761 tokens85.1%
13:0586,830 tokensInferHub85.1%
13:0379,361 tokensInferHub85.1%
13:0281,199 tokens85.1%
13:0281,052 tokensInferHub85.1%
13:0174,805 tokensInferHub85.1%
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 |
|---|---|---|---|---|---|
| InferHub | 10.11 s | - | - | 98.9% | 61% |
| OpenRouter | 2.25 s | - | - | 98.3% | 39% |
InferHub61% of traffic
98.9% success
OpenRouter39% of traffic
98.3% 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 66K 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", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1