GreenPT / greenpt/gemma4
Gemma 4 - access through LLMTR
Gemma 4 is an open-weight model with a 256,000-token context window. It genuinely processes image input and counts an image at a flat 256 tokens: in measurement a text request cost 21 input tokens and the same request with an image cost 292, and the model described the photo correctly. One warning: this row reasons by default, and at 64- and 400-token budgets it spent the whole budget reasoning and returned an empty reply; at 900 tokens it answered correctly. Set `max_tokens` well above the answer you expect. Tool/function calling was verified over a full two-turn loop. Repeated prefixes are not served from a cache.
Technical specifications
| Canonical ID | greenpt/gemma4 |
|---|---|
| Provider | GreenPT |
| Context window | 256,000 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 | $0.610155 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $1.830465 |
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/gemma4","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