Hy3
tencent/hy3Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports configurable reasoning effort.
- Input price
- $0.13
- Output price
- $0.53
- Context window
- N/A
- Max output
- 128K
Try the model
Playground
Input⌘ / Ctrl + Enter
Try a prompt
OutputReady
Your response will appear here
Choose an example or write a prompt, then click Run.
Specifications
Pricing
- Input
- $0.13 / 1M tokens
- Output
- $0.53 / 1M tokens
- Billing formula
- usage.prompt_tokens * 0.132 / 1000000 + usage.completion_tokens * 0.528 / 1000000
Context & modalities
- Max output
- 128,000 tokens
- Input
- Text
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Not supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Not supported
Access
- Provider
- Tencent
- Model ID
- tencent/hy3
- Execution
- sync
- API
- Chat Completions
- Endpoint
- /v1/chat/completions
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJ0ZW5jZW50L2h5MyIsCiAgIm1lc3NhZ2VzIjogWwogICAgewogICAgICAicm9sZSI6ICJ1c2VyIiwKICAgICAgImNvbnRlbnQiOiAiSGVsbG8iCiAgICB9CiAgXSwKICAibWF4X3Rva2VucyI6IDIwNDgKfQ==' \
| base64 --decode \
| curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @-)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Tencent: Hy3This model Tencent | — | $0.13 | $0.53 | Jul 6, 2026 |
Tencent | 128K | — | — | Jul 8, 2025 |
Tencent | 256K | — | — | Apr 22, 2026 |
Tencent | 1M | — | — | Aug 28, 2026 |