GreenPT / greenpt/metis
Metis - access through LLMTR
Metis is a decision model. It evaluates the state you send (a support ticket, a log line, a form) against up to 32 typed questions and returns a structured answer for each: the probability that a yes/no statement holds, one of the 2-255 options you define, or one of 2-10 levels on your own ordered scale; choice and score answers come with a confidence value. It generates no text and only input tokens are billed. The state, the questions and the model's fixed prompt must fit in 32,768 tokens together. The state is counted once however many questions you ask, so put the questions about one state in one request. See the Structured Decisions docs for the request format and billing.
Technical specifications
| Canonical ID | greenpt/metis |
|---|---|
| Provider | GreenPT |
| Context window | 32,768 tokens |
| Operations | SYSTEM_ONE |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| SYSTEM_ONE | INPUT_TEXT | PER_1M_TOKENS | $0.147783 |
| SYSTEM_ONE | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
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/metis","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
- DeepSeek V4 Flash greenpt/deepseek-v4-flash-0731
- GLM-5.2 greenpt/glm-5.2-eu
- DeepSeek V4.1 Flash greenpt/deepseek-v4.1-flash