OVHcloud AI Endpoints

Inference layers 19 models data_array 262K max context Free tier

info Notes

Free anonymous tier (no API key, no signup): 2 RPM per IP per model. 20+ open-weight models hosted in EU. OpenAI SDK-compatible. []

key How to get API key

General steps — follow the official OVHcloud AI Endpoints page for exact details.

  1. Open the OVHcloud AI Endpoints API key page ↗
  2. Create a new account, or sign in if you already have one.
  3. Generate an API key from the dashboard or settings.

layers Available models 19

search
ModelCapabilitiesContextOutputRate limit
Qwen3.5-397B-A17B qwen3.5-397b-a17b
description
131K—2 RPM (anonymous)
gpt-oss-120b gpt-oss-120b
description
128K—2 RPM (anonymous)
gpt-oss-20b gpt-oss-20b
description
128K—2 RPM (anonymous)
Meta-Llama-3_3-70B-Instruct meta-llama-3_3-70b-instruct
description
131K—2 RPM (anonymous)
Qwen3.6-27B qwen3.6-27b
description
131K—2 RPM (anonymous)
Qwen3.5-9B qwen3.5-9b
description
131K—2 RPM (anonymous)
Qwen3-32B qwen3-32b
description
131K—2 RPM (anonymous)
Qwen3-Coder-30B-A3B-Instruct qwen3-coder-30b-a3b-instruct
Text (code)
262K—2 RPM (anonymous)
Qwen2.5-VL-72B-Instruct qwen2.5-vl-72b-instruct
description visibility
128K—2 RPM (anonymous)
Mistral-Small-3.2-24B-Instruct mistral-small-3.2-24b-instruct
description
128K—2 RPM (anonymous)
Mistral-Nemo-Instruct-2407 mistral-nemo-instruct-2407
description
128K—2 RPM (anonymous)
Mistral-7B-Instruct-v0.3 mistral-7b-instruct-v0.3
description
32K—2 RPM (anonymous)
Riva TTS English riva-tts-english
description
262K—7 models at €0
Riva TTS German riva-tts-german
description
262K—7 models at €0
Riva TTS Spanish riva-tts-spanish
description
262K—7 models at €0
Riva TTS Italian riva-tts-italian
description
262K—7 models at €0
Qwen 3Guard Gen 0.6B qwen-3guard-gen-0.6b
description
262K—7 models at €0
Qwen 3Guard Gen 8B qwen-3guard-gen-8b
description
262K—7 models at €0
Stable Diffusion XL stable-diffusion-xl
description
262K—7 models at €0

help Frequently Asked Questions

OVHcloud AI Endpoints offers 19 free models.

The largest context window is 262,000 tokens.

The free tier is limited to 2 RPM (anonymous).