Tencent: Hy3 preview
tencent/hy3-previewHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use.
Modalities
In / out per 1M$0.18 / $0.60
Context256K
ReleasedApr 22, 2026
Providers
1 provider serves this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.18 | $0.60 | $0.06 | 4.91s | 81 tps | 98.82% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Hy3 preview in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Hy3 preview costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.18
per 1M tokens
Output
$0.60
per 1M tokens
Cache read
$0.06
per 1M cached tokens
Included in every pass
Hy3 preview is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Median 90th percentile 99th percentile
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Median 90th percentile 99th percentile
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 98.34%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 98.82%
100% 95% 90% 85%
Oct 31, 6:10 PMNow
Apps
Tools that most often run Hy3 preview, by tokens this week.
Activity
19.1B tokens processed market-wide in the last month.
0250.0M500.0M750.0M1.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for Hy3 preview?
tencent/hy3-preview. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Hy3 preview hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Hy3 preview cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.18 per 1M input tokens and $0.60 per 1M output tokens.
Who built Hy3 preview?
Tencent, in the Hy3 family.
Explore
Other models your pass can call.
