Tencent: Hy4 preview
tencent/hy4-previewTencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
Modalities
In / out per 1M$0.83 / $2.50
Context1M
ReleasedAug 28, 2026
Providers
4 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 DeepInfraus · fp4 | $0.83 | $2.50 | $0.04 | 1.71s | 32 tps | 100% |
| $0.83 | $2.50 | $0.04 | 3.83s | 47 tps | 100% | |
 SiliconFlowfp8 | $0.83 | $2.50 | $0.04 | 1.76s | 41 tps | 100% |
| $0.83 | $2.50 | $0.04 | 2.83s | 48 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Hy4 preview in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Hy4 preview costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.83
per 1M tokens
Output
$2.50
per 1M tokens
Cache read
$0.04
per 1M cached tokens
Included in every pass
Hy4 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.
0.0s10.0s20.0s30.0s40.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Tencent Cloud NovitaAI DeepInfra (us) SiliconFlow
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Tencent Cloud NovitaAI DeepInfra (us) SiliconFlow
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.9%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.95%
100% 98% 97% 95%
Oct 18, 11:00 AMNow
Apps
Tools that most often run Hy4 preview, by tokens this week.
Activity
36192.9B tokens processed market-wide in the last month.
01000.0B2000.0B3000.0B4000.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for Hy4 preview?
tencent/hy4-preview. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Hy4 preview hold?
1,048,576 tokens per request, of which up to 64,000 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Hy4 preview cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.83 per 1M input tokens and $2.50 per 1M output tokens.
Who built Hy4 preview?
Tencent, in the Hy4 family.
Explore
Other models your pass can call.
