Measured on Composite
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
AI model
Tencent: Hy4 preview (cheapest-provider) (Reasoning)
tencent/hy4-preview:cheapest-provider-reasoning
Tencent: Hy4 preview (cheapest-provider) (Reasoning) is a 1,048,576-token model served on Composite at $0.267 per million tokens in and $2.50 per million tokens out.
Try in PlaygroundSpecifications
| Model ID | tencent/hy4-preview:cheapest-provider-reasoning |
|---|---|
| Provider | DeepInfra |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.267 per million tokens |
| Output price | $2.50 per million tokens |
| Prompt caching | Supported — cached input is 60% off the list rate on pay-as-you-go credits |
| Thinking | Optional - see "Tencent: Hy4 preview (cheapest-provider) (Reasoning) (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | 8 requests of the daily allowance per call |
| Plans that may spend on it | Basic, Plus, Pro, Ultra, Enterprise |
| Routing endpoints | 1 |
Pricing
$0.267 per million tokens input · $2.50 per million tokens output
Input and output are charged at the provider’s list price.
On a monthly plan, one call costs 8 requests of that day's allowance. That needs the Basic or Plus or Pro or Ultra or Enterprise plan; credits pay for it on any plan.
Provider
DeepInfra
Roleplay fit
This model is available on Composite alongside dozens of others from other labs, so it is easy to compare against similar options.
Context behavior
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
Cost for regular use
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
From the provider
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Supplied by DeepInfra, not written by Composite.
Related models
Composite Anthropic Router · Composite Gemini Router · Composite GPT Router