GreenPT / greenpt/minimax-m2.5-eu
MiniMax M2.5 - access through LLMTR
MiniMax M2.5 is a reasoning model with a 192,000-token context window, sitting at the cheap end of this provider. Tool/function calling was verified over a full two-turn loop. It does not accept image input and says so honestly: an image request is refused with a 404 rather than silently billed. One caching detail is worth knowing: the model does report cache hits on repeated prefixes and you will see them in the response usage, but the provider publishes no discounted cache rate for this row — cached tokens are billed at the full input price. Do not plan savings around caching here. The model reasons by default and those tokens bill as output.
Technical specifications
| Canonical ID | greenpt/minimax-m2.5-eu |
|---|---|
| Provider | GreenPT |
| Context window | 192,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text |
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 | $0.402702 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.402702 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $1.610809 |
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/minimax-m2.5-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
- DeepSeek V4 Flash greenpt/deepseek-v4-flash-0731
- GLM-5.2 greenpt/glm-5.2-eu
- Devstral 2 123B greenpt/devstral-2-123b-instruct-2512