Open beta Zabio is in open beta: anyone can sign up and use it in production. Models, prices and features can still change while we learn from the first customers. Tell us what breaks at hello@zabio.ai.
All news
togetherModelBrief

Together AI adds tencent/Hy4 serverless model with 1,048,576 context

Together AI added tencent/Hy4 to its serverless models, with a 1,048,576 context length and per-token pricing.

Models:tencent/Hy4

What changed

Together AI added the serverless model tencent/Hy4. It has a 1,048,576 context length, NVFP4 quantization, text and image input, reasoning, function calling, and structured outputs. Pricing is $0.834 input, $2.501 output, and $0.042 cached input per 1M tokens.

Source

tencent/Hy4: 1,048,576 context length, NVFP4 quantization, text and image input, reasoning, function calling, and structured outputs. Pricing: $0.834 input / $2.501 output / $0.042 cached input (per 1M tokens).

Original announcement: Together AI changelog

Source: Together AI changelog (2026-11-19)