Skip to content
All releases
Added

Hy4 flash

Tencent's everyday productivity model joins the catalog through your own AIHubMix key.

Hy4 flash accepts text and images and produces text, with a 1M-token context window. Tencent designed it for document understanding, coding assistance and routine agent workflows. Bring your own AIHubMix key. AIHubMix lists $0.081 per million input tokens, $0.324 per million output tokens and $0.00324 per million cached input tokens. AnyRouter does not charge for BYOK inference.

AI SDK
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({ model: anyrouter("tencent/hy4-flash"), prompt: "Summarize this document." })
Coding agent
curl -fsSL https://anyrouter.dev/cli.sh | bash
anyr login
anyr claude --model "tencent/hy4-flash"

Try it in the playground. Playbooks: AI SDK, coding agents, OpenAI SDK. Tencent's launch describes its intended uses and limitations.

Tencent table comparing Hy4 flash with other models on productivity and agent benchmarks
Tencent-reported Hy4 flash benchmark results. Source: Tencent.
Tencent launch graphic introducing Hy4 flash for everyday productivity
Tencent Hy4 flash launch graphic. Source: Tencent.

Looking for the full catalog? Browse all models.