GeniusRelay
EN中文Sign upConsole

Tencent: Tencent Hy3

hy3

CompareAPIGet an API key

Hy3 is Tencent's 295B-parameter Mixture-of-Experts model with 21B active parameters, native 256K context, and configurable reasoning modes. It is built for coding, long-context comprehension, multi-turn dialogue, and agentic task execution with a focus on high-throughput production workloads.

Modalities

Text → Text

Input / output price

$0.0858 / $0.338 per 1M

Context

262K · max output 128K

Capabilities

ReasoningTool callingLong context

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.0858
Output$0.338
Cached input$0.0377

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00053
Per day
$0.2639
Per month (30 days)
$7.92

Tencent Hy3: input $0.0858/M · output $0.338/M · cached input $0.0377/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "hy3", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to hy3.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy3",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Tencent Hy3 billed?
Input is $0.0858 and output is $0.338 per million tokens; cached input is $0.0377. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
262K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.