Scaleway Generative APIs free tier

What Scaleway Generative APIs's free tier allows

Every model served through Generative APIs - Serverless is limited by tokens per minute, queries per minute and concurrent requests. Scaleway states that base limits apply only if you have registered a valid payment method, and that they increase automatically if you also verify your identity. The exact numbers live in the Organization quotas page rather than in the rate-limits documentation.

Published limits

Enforced but not published

Free access type

Metered access

Credit card

Required

Protocol

OpenAI-compatible at https://api.scaleway.ai/v1

Lifecycle

Active

Sources reviewed

2026-07-25

Requests sent through the Batches API are not rate limited and are billed at a 50% discount, which is the documented escape hatch for non-real-time work.

Where Scaleway Generative APIs sits in this catalog

Scaleway Generative APIs is one of 6 metered access entries among the 25 providers detailed here. It asks for a credit card, as 2 of the 25 do. It publishes no fixed request count, as 16 of the 25 do not.

Models Scaleway Generative APIs lists as free

• llama-3.3-70b-instruct — Llama, also free at 8 other providers here
• gpt-oss-120b — gpt-oss, also free at 9 other providers here
• qwen3-coder-30b-a3b-instruct — Qwen, also free at 8 other providers here

9 other providers here also host the gpt-oss family on free terms, and the terms are not the same: GroqCloud, SambaNova Cloud, Cloudflare Workers AI, Hugging Face Inference Providers, Fireworks AI, Ollama Cloud, Cerebras Inference, Vercel AI Gateway, Together AI. 8 other providers here also host the Llama family on free terms, and the terms are not the same: GroqCloud, SambaNova Cloud, Cloudflare Workers AI, Fireworks AI, IBM watsonx.ai, Together AI, Nebius Token Factory, DeepInfra. 8 other providers here also host the Qwen family on free terms, and the terms are not the same: Cloudflare Workers AI, SiliconFlow, Alibaba Cloud Model Studio, Ollama Cloud, Together AI, Nebius Token Factory, DeepInfra, Chutes.

Checking a Scaleway Generative APIs key

The CORS preflight echoes the requesting origin and allows an Authorization header, so a browser can call this endpoint directly. That was measured against https://api.scaleway.ai on 2026-07-25.

So a key can be checked in the browser checker without installing anything. If you would rather not paste a key into a web page, this does the same thing:

#!/usr/bin/env sh
set -eu

: "${SCALEWAY_API_KEY:?Set SCALEWAY_API_KEY to a key you created yourself at the provider console}"

# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
  --write-out '\nHTTP %{http_code}\n' \
  --header "Authorization: Bearer $SCALEWAY_API_KEY" \
  'https://api.scaleway.ai/v1/models'

Using a Scaleway Generative APIs key

Scaleway Generative APIs serves the OpenAI chat completions protocol at https://api.scaleway.ai/v1. Point any client that accepts a custom base URL at it, and let the client read the key from SCALEWAY_API_KEY so the value never lands in a config file:

# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "llama-3.3-70b-instruct"
model_provider = "scaleway"

[model_providers.scaleway]
name = "Scaleway Generative APIs OpenAI-compatible gateway"
base_url = "https://api.scaleway.ai/v1"
env_key = "SCALEWAY_API_KEY"
wire_api = "responses"

Questions about the Scaleway Generative APIs free tier

Does Scaleway Generative APIs ask for a credit card?

Yes. Scaleway Generative APIs requires a card on file before the free allowance is usable, which 2 of the 25 providers with a page here also do.

What are Scaleway Generative APIs's free-tier rate limits?

Scaleway Generative APIs publishes no single free-tier number: its limits are enforced but not published. This catalog leaves that blank rather than guessing a figure.

What happens when a Scaleway Generative APIs key hits the limit?

The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.

Is the Scaleway Generative APIs free tier going away?

Nothing in Scaleway Generative APIs's own documentation says so as of 2026-07-25. Requests sent through the Batches API are not rate limited and are billed at a 50% discount, which is the documented escape hatch for non-real-time work.

Can Scaleway Generative APIs be used with Codex, Cline, or Continue?

Yes. Scaleway Generative APIs serves the OpenAI chat completions protocol at https://api.scaleway.ai/v1, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.

Official sources

• Scaleway Generative APIs rate limitshttps://www.scaleway.com/en/docs/generative-apis/reference-content/rate-limits/
• Scaleway Generative APIs quickstarthttps://www.scaleway.com/en/docs/generative-apis/quickstart/
• Scaleway Generative APIs pricinghttps://www.scaleway.com/en/docs/generative-apis/faq/

Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.