GreenPT / greenpt/qwen3-coder-30b-a3b-instruct-eu
Qwen3 Coder 30B A3B - access through LLMTR
Qwen3 Coder 30B A3B is a sparse mixture-of-experts model tuned for coding, with a 256,000-token context window, sitting at the cheap end of this provider. It does not reason by default: in measurement it answered a short question in two tokens, so output cost is predictable. 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 `not a multimodal model` error. Since file contents take up most of the context in code work, the combination of a 256K window with a low input price is this row's real advantage. Repeated prefixes are not served from a cache.
Technical specifications
| Canonical ID | greenpt/qwen3-coder-30b-a3b-instruct-eu |
|---|---|
| Provider | GreenPT |
| Context window | 256,000 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 | $0.305078 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $1.159295 |
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-coder-30b-a3b-instruct-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