MODELS / TENCENT

Tencent Hy4 Flash

Tencent Hy4 Flash is a lower-cost model in the Hy4 family for coding, reasoning, and agentic workflows. It supports deep reasoning with preserved thinking, tool calling, structured outputs, prompt caching, and image understanding, with a 1M-token context window.

TEXTREASONINGIMPLICIT-CACHINGSTRUCTURED-OUTPUTTOOL-USEVISIONOPEN-WEIGHTS
1.0M
CONTEXT WINDOW
64K
MAX OUTPUT TOKENS
$0.035
INPUT PRICE / 1M TOKENS
$0.14
OUTPUT PRICE / 1M TOKENS
QUICKSTART
PROTOCOL:
OPENAI COMPATIBLE
STREAMING:
SUPPORTED

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/hy4-flash",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS
CONTEXT:
1.0M
PROVIDER:
TENCENT
TYPE:
TEXT

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Tencent Hy4 Flash supports, in one table.

MODEL ID
blackboxai/tencent/hy4-flash
DEVELOPED BY
Tencent
MODEL TYPE
Text
RELEASED
Nov 16, 2026
CONTEXT WINDOW
1.0M
MAX OUTPUT TOKENS
64K
INPUT MODALITIES
text, image
OUTPUT MODALITIES
text
INPUT PRICE
$0.035 / 1M tokens
OUTPUT PRICE
$0.14 / 1M tokens
CACHE READ
$0.002 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Enterprise · single-tenant
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs