Hy3

tencent/hy3

A chat model with a 262K-token context window, at $0.147 per million input tokens and $0.609 per million output tokens.

Details

Maker: tencent
Kind: Chat
Context window: 262,144 tokens
Max output: 262,144 tokens
Input: $0.147 per million tokens
Cached input: $0.03675 per million tokens, 75% off
Cache write: Same as input
Output: $0.609 per million tokens
Capabilities: Reasoning, tool use
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-07-06

Description

Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes. It enhances coding, long-form comprehension, multi-turn dialogue, and agentic task execution, balancing reliability, efficiency, and cost across both high-frequency interactions and complex workflows.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy3",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model