GPU Server
OpenAI-compatible inference for Qwen3.6-35B-A3B.
Model
qwen/qwen3.6-35b-a3b
Context
262,144 tokens
Max output
235,929 tokens
Input
Text, image, video
Output
Text, streaming
Quantization
NVFP4
Location
Germany
Prompt logging
Disabled
Pricing
| Input | $0.049 / 1M tokens |
|---|---|
| Cached input | $0.0049 / 1M tokens |
| Output | $0.69 / 1M tokens |
API
- Base URL:
https://gpu-server.tailbd22dc.ts.net/v1 - Model feed: https://gpu-server.tailbd22dc.ts.net/models
- Health: https://gpu-server.tailbd22dc.ts.net/health
- Status: https://gpu-server.tailbd22dc.ts.net/status
Authentication uses a bearer token. The endpoint supports chat completions, streaming, tool calls, structured outputs, reasoning, logprobs and multimodal input.
Provider
Operated by David Alexander Joachim Peter Thelen, Homburger Hohl 53, 60437 Frankfurt am Main. Contact: david.thelen@web.de.
Model license: Apache 2.0. This service is not affiliated with Alibaba Cloud or the Qwen team.