Hy3 preview
tencent-tokenhub/hy3-preview · family Hy · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
free
Cache read $/1M
#236 of 7,708
Cheapest rank
- Provider
- Tencent TokenHub (
tencent-tokenhub) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 64,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Hy3 preview” is offered by 5 providers — cheapest-effective first. This one (Tencent TokenHub) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Tencent TokenHub (this) | free | free | $0.00 | 256k |
| AIHubMix | $0.17 | $0.5667 | $0.27 | 256k |
| ZenMux | $0.172 | $0.572 | $0.27 | 256k |
| Kilo Gateway | $0.18 | $0.6 | $0.29 | 262k |
| OpenRouter | $0.18 | $0.6 | $0.29 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Tencent TokenHub and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"hy3-preview","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):