Hy4 Preview
5% offHy4 preview is a 770B-parameter Mixture-of-Experts flagship from the Tencent Hy Team (49B active per token) with a 1M-token context window, post-trained for software engineering, office and data analysis, game development, and scientific research.
Launch offer · 5% off on every provider
Applied automatically; prices return to list when each offer ends.
Price schedule by provider
DiscountedList price
Providers
FastRouter routes your requests to this provider. You can also bring your own key.
deepinfraOffers without an end date apply until further notice.
Supported parameters
Request parameters you can send with this model.
Core (Sampling & basic generation)
- max_tokens
- Maximum tokens to generate.
- seed
- Seed for deterministic sampling.
- stop
- Sequences where generation stops.
- temperature
- Controls randomness of output.
- top_k
- Limits sampling to top K tokens.
- top_p
- Nucleus sampling threshold.
Penalties (Token Penalties)
- frequency_penalty
- Penalizes frequent tokens.
- presence_penalty
- Penalizes tokens already present.
- repetition_penalty
- Penalizes repeated tokens.
Reasoning (Reasoning Controls)
- include_reasoning
- Include reasoning trace in the response.
- reasoning
- Provider-specific reasoning configuration.
Tool Use (Function Calls & Tools)
- tool_choice
- How the model should use tools.
- tools
- Tool/function definitions available to the model.
Output & Format (Response Formatting)
- logprobs
- Return log probabilities of output tokens.
- response_format
- Structured output format configuration.
Performance
Median throughput and time to first token per provider over the last week.
Throughput
Latency
Make your first API call
OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.
<FASTROUTER_API_KEY> with your key · Get your key →InstallFrequently asked questions
Model scores sourced from ArtificialAnalysis