Hy4 flash

tencent/hy4-flash

Hy4 flash is the cost-efficient tier of Tencent Hunyuan's Hy4 family, with roughly a quarter of the flagship's parameters for lower latency and cost. It accepts text and image input, has a context window of about 1M tokens, and supports reasoning, tool calling and structured output. It targets code assistance, agent workflows and high-volume tasks where Hy4's full depth is not needed.

Input price
$0.07USD / 1M tokens
Output price
$0.28USD / 1M tokens
Cache read
$0.003USD / 1M tokens
Context window
1M
Max output
64K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call Tencent Hy4 flash through SandBase?

Create a SandBase API key, then send requests with the model ID "tencent/hy4-flash" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does Tencent Hy4 flash cost?

$0.07 per 1M input tokens and $0.28 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of Tencent Hy4 flash?

1M tokens of context, with up to 64K output tokens per response.

Which features does Tencent Hy4 flash support?

Tencent Hy4 flash supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate Tencent account?

No. One SandBase API key and balance gives you access to Tencent Hy4 flash and the other models in the catalog; you do not need to sign up with Tencent separately.