Hy4 Preview is Tencent's 770B-parameter mixture-of-experts model with 49B active parameters. It is designed for coding agents, complex tool-use workflows, and productivity tasks, with a 1M-token context window and configurable reasoning effort.
Added Aug 28, 2026
Context Window
1.0M
Max Output
64.0K
Avg output tokens (7d)
937 tokens
Input Price (Auto)
$0.83/1M
Output Price (Auto)
$2.50/1M
Cache Read (Auto)
$0.042/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
No benchmark data is available yet for this model.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Tencent Hy4 Preview with similar models from the same provider or model family.
Tencent Hy3
tencent/hy3Hy3 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.
DeepSeek V4 Flash Vision Exp Uncensored
deepseek/deepseek-v4-flash-vision-exp-uncensoredAn uncensored variant of the experimental vision-enabled DeepSeek V4 Flash model for chat, image understanding, reasoning, coding, and tool use, with a 524K context window.
TheDrummer/Artemis v1.1
TheDrummer/Artemis-v1.1TheDrummer's Artemis v1.1 is a Gemma 4 31B fine-tune for creative writing, expressive dialogue, and roleplay, with optional thinking and a 262K context window.
Synth 2.5 Flash Preview
synth-2.5-flashSynth 2.5 Flash Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.
Synth 2.5 Pro Preview
synth-2.5-proSynth 2.5 Pro Preview is a low-cost text model designed for role-play, character dialogue, and collaborative storytelling.
GPT 6 Astra Pro
openai/gpt-6-astra-proGPT 6 Astra in Pro reasoning mode. Uses additional model work for difficult tasks, with higher latency and token usage at the same per-token rates. Reasoning effort remains independently configurable.