Scaleway Generative APIs

Trial verified 2026-07-30 · 0d ago OpenAI-compatible

EU-hosted open models with 1M free tokens

What's free

1,000,000 tokens free + 60 min Whisper transcription; billing starts at token 1,000,001

Rate limits

Gemma, Llama, Mistral, Qwen

The catch

European provider (France). Free allowance is a one-time token bucket, not time-limited

TypeTrial credit
Free typetrial-credit
Expiresno expiry
Modalitiestext, audio
OpenAI base URLhttps://api.scaleway.ai/v1

Free models · sample

llama-3.3-70b-instructqwen3-235b-a22b-instruct-2507mistral-small-3.2-24b-instruct-2506deepseek-r1-distill-llama-70bgemma-3-27b-itqwen2.5-coder-32b-instruct

A sample of models reachable on the free tier — the live catalog changes. Pull the current set with GET https://api.scaleway.ai/v1/models.

Quickstart — chat completions

from openai import OpenAI

client = OpenAI(base_url="https://api.scaleway.ai/v1", api_key="<YOUR_FREE_API_KEY>")
resp = client.chat.completions.create(
    model="llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

…or with curl:

curl https://api.scaleway.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"llama-3.3-70b-instruct","messages":[{"role":"user","content":"Hello!"}]}'

Appears in

← All providers