MODELS / TENCENT

Hy3

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…

TEXTREASONINGIMPLICIT-CACHINGREASONINGTOOL-USE
262.1K
CONTEXT WINDOW
-
MAX OUTPUT TOKENS
$0.14
INPUT PRICE / 1M TOKENS
$0.58
OUTPUT PRICE / 1M TOKENS
QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/tencent/hy3",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Hy3 supports, in one table.

MODEL ID
blackboxai/tencent/hy3
DEVELOPED BY
Tencent
MODEL TYPE
Text
RELEASED
Jul 6, 2026
CONTEXT WINDOW
262.1K
MAX OUTPUT TOKENS
-
INPUT MODALITIES
text
OUTPUT MODALITIES
text
INPUT PRICE
$0.14 / 1M tokens
OUTPUT PRICE
$0.58 / 1M tokens
CACHE READ
$0.035 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Not available (closed-weight model)
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoning