Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Tencent

Tencent Hy4 Preview

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.

  • Reasoning
  • Tool Calling
  • Structured Output

Added Aug 28, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.751
Output
$2.25
Cache read
$0.0378
Compare provider prices

Specifications

Context window
1M
Max output
64K
Parameters
770B / 49B
Total / active

Benchmarks

No public benchmark scores for this model yet.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.751$2.25$0.0378N/AN/A
Auto
Auto (Anonymized)
$0.751$2.25$0.0378N/AN/A
DeepInfra
DeepInfra
FP4
US
$0.876$2.63$0.0441N/AN/A
GMICloud
GMICloud
BF16
US
$0.876$2.63$0.0441N/AN/A
Novita
Novita
FP8
US
$0.876$2.63$0.0441N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.876$2.63$0.0441N/AN/A
Tencent Cloud
Tencent Cloud
10% off
FP8
UNK
$0.876$2.63$2.63$0.0441N/AN/A
Uomi
Uomi
3% off
GLB
$0.919$0.889$2.76$2.67N/AN/AN/A
AtlasCloud
AtlasCloud
FP8
US
$0.90$2.70$0.045N/AN/A
Venice
Venice
FP4
US
$1.09$3.28$0.0551N/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
ProviderInputOutputCached input
Auto
Autotencent/hy4-preview
$0.751/M$2.25/M$0.0378/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Tencent Hy4 Preview with similar models from the same provider or model family.

Tencent Hy4

tencent/hy4

Tencent Hy4 accepts text and images and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. It supports coding, long-document analysis, automatic tool calling and structured output. Reasoning is enabled by default at high effort; choose low effort or turn reasoning off.

Tencent Hy3

tencent/hy3

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.

DeepSeek V4.1 Flash 1017 Abliterated

deepseek/deepseek-v4.1-flash-1017-abliterated

An abliterated (refusal-removed) version of DeepSeek V4.1 Flash 1017. Text only, with tool calling, optional reasoning and a 1M-token context window. Its behavior may differ from DeepSeek V4.1 Flash 1017. Served by a single host; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017 Abliterated Thinking

deepseek/deepseek-v4.1-flash-1017-abliterated:thinking

An abliterated (refusal-removed) version of DeepSeek V4.1 Flash 1017. Text only, with tool calling, optional reasoning and a 1M-token context window. Its behavior may differ from DeepSeek V4.1 Flash 1017. Served by a single host; it may be unavailable while that host is down.

DeepSeek V4.1 Flash 1017 Abliterated (Lyber)

lyber/deepseek-v4.1-flash-1017-abliterated

DeepSeek V4.1 Flash 1017 Abliterated served by Lyber.ai.

Kimi K3.1 Pro Abliterated (Lyber)

lyber/kimi-k3.1-pro-abliterated

Kimi K3.1 Pro Abliterated served by Lyber.ai.