Tencent's HY3 reasoning and coding model with a 262K-token context.

Modalities
IntextOuttext
Input / output
$0.14 / $0.58USD per 1M tokens
Context
262K
Providers
Live

Chat with HY3 free →

Playground

Preparing playground

Providers

fallback732ms100%

API

POST/api/v1/chat/completionsOpenAI-compatible
hy3
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy3",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingresponse_formatreasoningreasoning_effort

Pricing

Input
$0.14/M tokens
Cached input
$0.014/M tokens
Output
$0.58/M tokens

Published USD rates. Actual cost depends on input, output, cache usage and request options.