| meta | content | dates | category | productIcon | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
|
ai-data |
GenerativeApiProductIcon |
Scaleway's Generative APIs provide access to pre-configured, serverless endpoints of leading AI models, hosted in European data centers. This allows you to integrate advanced AI capabilities into your applications without managing underlying infrastructure.
Our Generative APIs support a range of popular models, including:
- Chat / Text Generation models: Refer to our dedicated documentation for a list of supported chat models.
- Vision models: Refer to our dedicated documentation for a list of supported vision models.
- Embedding models: Refer to our dedicated documentation for a list of supported embedding models.
The free tier allows you to process up to 1,000,000 tokens without incurring any costs. After reaching this limit, you will be charged per million tokens processed. Free tier usage is calculated by adding all input and output tokens consumed from all models used. For more information, refer to our pricing page or access your bills by token types and models in billing section from Scaleway Console (past and provisional bills for the current month).
Note that when your consumption exceeds the free tier, you will be billed for each additional token consumed by model and token type. The minimum billing unit is 1 million tokens. Here are two examples for low volume consumption:
Example 1: Free Tier only
| Model | Token type | Tokens consumed | Price | Bill |
|---|---|---|---|---|
llama-3.3-70b-instruct |
Input | 500k | 0.90€/million tokens | 0.00€ |
llama-3.3-70b-instruct |
Output | 200k | 0.90€/million tokens | 0.00€ |
mistral-small-3.1-24b-instruct-2503 |
Input | 100k | 0.15€/million tokens | 0.00€ |
mistral-small-3.1-24b-instruct-2503 |
Output | 100k | 0.35€/million tokens | 0.00€ |
Total tokens consumed: 900k
Total bill: 0.00€
Example 2: Exceeding Free Tier
| Model | Token type | Tokens consumed | Price | Billed consumption | Bill |
|---|---|---|---|---|---|
llama-3.3-70b-instruct |
Input | 800k | 0.90€/million tokens | 1 million tokens | 0.00€ (Free Tier application) |
llama-3.3-70b-instruct |
Output | 2 500k | 0.90€/million tokens | 3 million tokens | 2.70€ |
mistral-small-3.1-24b-instruct-2503 |
Input | 100k | 0.15€/million tokens | 1 million tokens | 0.15€ |
mistral-small-3.1-24b-instruct-2503 |
Output | 100k | 0.35€/million tokens | 1 million tokens | 0.35€ |
Total tokens consumed: 900k
Total billed consumption: 6 million tokens
Total bill: 3.20€
Note that in this example, the first line where the free tier applies will not display in your current Scaleway bills by model but will instead be listed under Generative APIs Free Tier - First 1M tokens for free.
A token is the minimum unit of content that is seen and processed by a model. Hence, token definitions depend on input types:
- For text, on average,
1token corresponds to~4characters, and thus0.75words (as words are on average five characters long) - For images,
1token corresponds to a square of pixels. For example, pixtral-12b-2409 model image tokens of16x16pixels (16-pixel height, and 16-pixel width, hence256pixels in total).
The exact token count and definition depend on tokenizers used by each model. When this difference is significant (such as for image processing), you can find detailed information in each model documentation (for instance in pixtral-12b-2409 size limit documentation). Otherwise, when the model is open, you can find this information in the model files on platforms such as Hugging Face, usually in the tokenizer_config.json file.
You can see your token consumption in Scaleway Cockpit. You can access it from the Scaleway console under the Metrics tab. Note that:
- Cockpits are isolated by Projects, hence you first need to select the right project in the Scaleway console before accessing Cockpit to see your token consumption for this Project (you can see the
project_idin the Cockpit URL:https://{project_id}.dashboard.obs.fr-par.scw.cloud/. - Cockpit graphs can take up to 1 hour to update token consumption, see Troubleshooting for further details.
If your users do not have a Scaleway account, you can still give them access to their Generative API usage consumption by either:
- Providing them an access to Grafana inside Cockpit. You can create dedicated Grafana users with read-only access (Viewer Role). Note that these users will still have access to all other Cockpit dashboards for this project.
- Collecting consumption data from the Billing API and exposing it to your users. Consumption can be detailed by Projects.
- Collecting consumption data from Cockpit data sources and exposing it to your users. As an example, you can query consumption using the following query:
curl -G 'https://{data-source-id}.metrics.cockpit.fr-par.scw.cloud/prometheus/api/v1/query_range' \
--data-urlencode 'query=generative_apis_tokens_total{resource_name=~".*",type=~"(input_tokens|output_tokens)"}' \
--data-urlencode 'start=2025-03-15T20:10:51.781Z' \
--data-urlencode 'end=2025-03-20T20:10:51.781Z' \
--data-urlencode 'step=1h' \
-H "Authorization: Bearer $COCKPIT_TOKEN" | jq
Make sure that you replace the following values:
data-source-id: ID of your Scaleway metrics data source$COCKPIT_TOKEN: your Cockpit tokenstartandendtime properties: your specific time range
You can see your token consumption in Scaleway Cockpit. You can access it from the Scaleway console under the Metrics tab. Note that:
- Cockpits are isolated by Projects. You first need to select the right Project in the Scaleway console before accessing Cockpit to see your token consumption for the desired Project (you can see the
project_idin the Cockpit URL:https://{project_id}.dashboard.obs.fr-par.scw.cloud/. - Cockpit graphs can take up to 1 hour to update token consumption, see Troubleshooting for further details.
Currently, you cannot configure a specific threshold after which your usage will blocked. However:
- You can configure billing alerts to ensure you are warned when you hit specific budget thresholds.
- Your total billing remains limited by the amount of tokens you can consume within rate limits.
- If you want to ensure fixed billing, you can use Managed Inference, which provides the same set of OpenAI-compatible APIs and a wider range of models.
Access is open to all Scaleway customers. You can start by using the Generative APIs Playground in the Scaleway console to experiment with different models. For integration into applications, you can use the OpenAI-compatible APIs provided by Scaleway. Detailed instructions are available in our Quickstart guide.
All models are currently hosted in a secure data center located in Paris, France, operated by OPCORE. This ensures low latency for European users and compliance with European data privacy regulations.
You can find the privacy policy applicable to all use of Generative APIs here.
Yes, Scaleway's Generative APIs are designed to be compatible with OpenAI libraries and SDKs, including the OpenAI Python client library and LangChain SDKs. This allows for seamless integration with existing workflows.
- Generative APIs: A serverless service providing access to pre-configured AI models via API, billed per token usage.
- Managed Inference: Allows deployment of curated or custom models with chosen quantization and instances, offering predictable throughput and enhanced security features like private network isolation and access control. Managed Inference is billed by hourly usage, whether provisioned capacity is receiving traffic or not.
To get started, explore the Generative APIs Playground in the Scaleway console. For application integration, refer to our Quickstart guide, which provides step-by-step instructions on accessing, configuring, and using a Generative APIs endpoint.
Yes, API rate limits define the maximum number of requests a user can make within a specific time frame to ensure fair access and resource allocation between users. If you require increased rate limits (by a factor from 2 to 5 times), you can request them by creating a ticket. If you require even higher rate limits, especially to absorb infrequent peak loads, we recommend using Managed Inference instead with dedicated provisioned capacity. Refer to our dedicated documentation for more information on rate limits.
Scaleway is dedicated to updating and offering the latest versions of generative AI models, ensuring improvements in capabilities, accuracy, and safety. As new versions of models are introduced, you can explore them through the Scaleway console. Learn more in our dedicated documentation.
We are currently working on defining our SLAs for Generative APIs. We will provide more information on this topic soon.
We are currently working on defining our performance guarantees for Generative APIs. We will provide more information on this topic soon.
Yes, you need to comply with model licenses when using Generative APIs. Applicable licenses are available for each model in our documentation and in Console Playground.