GreenPT / greenpt/green-l-raw
Green L Raw - access through LLMTR
Green L Raw is the same model as Green L, served without the assistant instruction the provider injects server-side, with a 128,000-token context window. The difference was measured: a one-word request billed eight input tokens on this row against 2,489 on Green L. This is the right row when you write your own system prompt, because you are not paying for a style you will overwrite. It genuinely processes image input and described a product photo correctly in measurement. Tool/function calling was verified over a full two-turn loop. Repeated prefixes are not served from a cache, so a long fixed system prompt is billed at full price on every request.
Technical specifications
| Canonical ID | greenpt/green-l-raw |
|---|---|
| Provider | GreenPT |
| Context window | 128,000 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 | $0.305078 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.976248 |
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/green-l-raw","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