November 19, 2026 · Together AI
tencent/Hy4 now on serverless with a 1,048,576-token context window
The following models are now available on serverless:
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).
Free. Unsubscribe any time.
Related updates
Qwen4-Max available on serverless with 1M context and image input
GLM-5.3 on serverless with 1M context, at $1.40 input / $4.40 output per 1M tokens
Tev1-4B-experimental available on serverless with 32,768 context
AI Search - New Workers AI text generation models in AI Search · Cloudflare
Gemini 4 Neon generally available, with a 1,048,576-token input and output limit · Google Cloud