GreenPT / greenpt/qwen3.5-397b-a17b-eu
Qwen3.5 397B A17B - access through LLMTR
Qwen3.5 397B A17B is a large sparse mixture-of-experts model with a 250,000-token context window. It costs roughly 2.3x the 35B row in the same family on input and 2.4x on output, and we ran no quality comparison between the two. It genuinely processes image input: in measurement it described a two-photo product image correctly and its input token count rose by the image's own tokens. Tool/function calling was verified over a full two-turn loop. The model reasons by default; on a short question it was observed spending its entire output budget on reasoning, so keep `max_tokens` high. Output costs six times input, which is where to plan the bill from. Repeated prefixes are not served from a cache.
Technical specifications
| Canonical ID | greenpt/qwen3.5-397b-a17b-eu |
|---|---|
| Provider | GreenPT |
| Context window | 250,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.854217 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $5.308348 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"greenpt/qwen3.5-397b-a17b-eu","messages":[{"role":"user","content":"Hello"}]}'Related models
- Kimi K3 greenpt/kimi-k3-eu
- GLM-5.3 greenpt/glm-5.3-eu
- GLM-5.3 Flash greenpt/glm-5.3-flash-eu
- Kimi K2.7 Code greenpt/kimi-k2.7-code-eu
- Kimi K2.6 greenpt/kimi-k2.6-eu
- MiniMax M2.5 greenpt/minimax-m2.5-eu
- DeepSeek V4 Flash greenpt/deepseek-v4-flash-0731
- GLM-5.2 greenpt/glm-5.2-eu