GreenPT
French inference API for open-weight models, hosted on Scaleway with embeddings, reranking and speech
GreenPT is a Dutch AI platform with an OpenAI-compatible API covering chat completions, embeddings, reranking, speech-to-text, and document parsing. Models are named rather than hidden: its own GreenL and GreenR tiers sit alongside proxied access to GLM, Kimi, Qwen, Mistral and gpt-oss.
Pricing is per token and published per model, starting at €0.25/1M input for GreenL. Prompt caching cuts repeated prefixes to a lower rate on the models that support it. Speech-to-text is billed per hour of audio.
The company is based in Utrecht and runs inference on European infrastructure powered by renewable energy, which is the differentiator for teams that need EU processing.
Pricing: Per token usage
GreenPT prices by model
Per 1M tokens, read off GreenPT's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | €0.22 | €0.011 | €1.10 | 1 Oct 2026 | |
| GLM 5.3 | €1.10 | €0.275 | €4.40 | 1 Oct 2026 | |
| GLM 5.3 Flash | €0.11 | €0.022 | €0.44 | 1 Oct 2026 | |
| Kimi K3 | €3.30 | €0.825 | €16.50 | 1 Oct 2026 |
GreenPT Alternatives
Explore 113 products in the Inference APIs category. View all GreenPT alternatives.
CheapestInference
Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
Runware
Unified API for image, video, audio and 3D generation running on custom inference hardware
Project Zero
CPU-only LLM inference engine in C with no runtime dependencies
Akumi
EU-hosted OpenAI-compatible inference API with data residency, PII pseudonymization and per-request audit trails
Work on GreenPT? Feature it at the top of Inference APIs.
Is your product missing?