From b2c9f0bbaa8647a61b0bc8eeb2b332d7971ed9cf Mon Sep 17 00:00:00 2001 From: villyes Date: Mon, 11 May 2026 11:16:24 +0200 Subject: [PATCH 01/12] feat(genapi): add info about cost estimator MTA-7130 --- pages/generative-apis/menu.ts | 4 ++ .../reference-content/cost-estimator.mdx | 39 +++++++++++++++++++ 2 files changed, 43 insertions(+) create mode 100644 pages/generative-apis/reference-content/cost-estimator.mdx diff --git a/pages/generative-apis/menu.ts b/pages/generative-apis/menu.ts index 2edb20b386..f20c875a76 100644 --- a/pages/generative-apis/menu.ts +++ b/pages/generative-apis/menu.ts @@ -147,6 +147,10 @@ export const generativeApisMenu = { label: 'Security and reliability in Generative APIs', slug: 'security-and-reliability', }, + { + label: 'Understanding Generative APIs costs', + slug: 'cost-estimator', + }, { label: 'Adding AI to VS Code using Continue', slug: 'adding-ai-to-vscode-using-continue', diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx new file mode 100644 index 0000000000..63e28c3fd9 --- /dev/null +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -0,0 +1,39 @@ +--- +title: Understanding Generative APIs costs +description: Discover how Scaleway Generative APIs pricing works, including hourly rates, billing, and tips to manage costs effectively. +tags: generative-apis how-much cost charge +dates: + validation: 2026-05-11 + posted: 2026-05-11 +--- +import Requirements from '@macros/iam/requirements.mdx' + +Understanding the financial impact of your AI workloads is essential for making informed decisions. The Cost estimator (available via the [Scaleway Console](https://console.scaleway.com/generative-api/cost-estimator)) gives you a clear, side‑by‑side view of how the same generative workload behaves under the different deployment options offered by Scaleway: [Generative APIs - Serverless versus Generative APIs Dedicated Deployment](/generative-apis/faq/#what-is-the-difference-between-serverless-and-dedicated-deployment). + + + - The Cost estimator provides an estimate based on standard benchmarks (with significant concurrency and a low cache hit rate). Only performance tests in production, based on customer workload can provide a fully accurate estimate. + - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10), because processing will be bottlenecked by either input or output processing in these cases. + - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt, a common prefix across requests, long conversations). + + + + + - A Scaleway account logged into the [console](https://console.scaleway.com) + - [Owner](/iam/concepts/#owner) status or [IAM permissions](/iam/concepts/#permission) allowing you to perform actions in the intended Organization + +## Use the Cost estimator + +1. Click **Generative APIs** in the **AI** section of the side menu in the [Scaleway console](https://console.scaleway.com/). + +2. Select the **Cost estimator** tab. + +3. Model your workload by setting the following: + - **Number of users** + - **Queries per user per day** + - **Hours of usage/day** + - **Load** + +4. Set your chosen **Model** and **GPU**. + The tool instantly calculates the total monthly cost for both Serverless and Dedicated modes. + +5. Compare cost differences side‑by‑side. \ No newline at end of file From c65994db757452e83748efb5510c6e4fefd07630 Mon Sep 17 00:00:00 2001 From: villyes Date: Mon, 11 May 2026 15:12:13 +0200 Subject: [PATCH 02/12] feat(genapi): add info about cost estimator MTA-7130 --- pages/generative-apis/reference-content/cost-estimator.mdx | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 63e28c3fd9..858087db88 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -1,6 +1,6 @@ --- title: Understanding Generative APIs costs -description: Discover how Scaleway Generative APIs pricing works, including hourly rates, billing, and tips to manage costs effectively. +description: Compare costs for the different deployment options of Scaleway Generative API - Serverless versus Dedicated Deployment. tags: generative-apis how-much cost charge dates: validation: 2026-05-11 @@ -13,7 +13,7 @@ Understanding the financial impact of your AI workloads is essential for making - The Cost estimator provides an estimate based on standard benchmarks (with significant concurrency and a low cache hit rate). Only performance tests in production, based on customer workload can provide a fully accurate estimate. - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10), because processing will be bottlenecked by either input or output processing in these cases. - - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt, a common prefix across requests, long conversations). + - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, long conversations). @@ -34,6 +34,6 @@ Understanding the financial impact of your AI workloads is essential for making - **Load** 4. Set your chosen **Model** and **GPU**. - The tool instantly calculates the total monthly cost for both Serverless and Dedicated modes. + The estimator instantly calculates the total monthly cost for both Serverless and Dedicated modes. 5. Compare cost differences side‑by‑side. \ No newline at end of file From d1acbd919eb568d8870982f315feb77f301cb93c Mon Sep 17 00:00:00 2001 From: villyes Date: Mon, 11 May 2026 16:45:54 +0200 Subject: [PATCH 03/12] feat(genapi): add info about cost estimator MTA-7130 --- .../reference-content/cost-estimator.mdx | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 858087db88..7e5e098e84 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -6,24 +6,20 @@ dates: validation: 2026-05-11 posted: 2026-05-11 --- -import Requirements from '@macros/iam/requirements.mdx' -Understanding the financial impact of your AI workloads is essential for making informed decisions. The Cost estimator (available via the [Scaleway Console](https://console.scaleway.com/generative-api/cost-estimator)) gives you a clear, side‑by‑side view of how the same generative workload behaves under the different deployment options offered by Scaleway: [Generative APIs - Serverless versus Generative APIs Dedicated Deployment](/generative-apis/faq/#what-is-the-difference-between-serverless-and-dedicated-deployment). +Understanding the financial impact of AI workloads is essential for making informed decisions. The Cost estimator (available via the [Scaleway console](https://console.scaleway.com/generative-api/cost-estimator)) provides a clear, side‑by‑side view of how the same generative workload behaves under the different deployment options offered by Scaleway: [Generative APIs - Serverless versus Generative APIs Dedicated Deployment](/generative-apis/faq/#what-is-the-difference-between-serverless-and-dedicated-deployment). - - The Cost estimator provides an estimate based on standard benchmarks (with significant concurrency and a low cache hit rate). Only performance tests in production, based on customer workload can provide a fully accurate estimate. + - The Cost estimator provides an estimate based on standard benchmarks (with significant concurrency and a low cache hit rate). Only performance tests in production, based on the customer's workload, can provide a fully accurate estimate. - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10), because processing will be bottlenecked by either input or output processing in these cases. - - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, long conversations). + - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, typical of long conversations). - +## Compare costs - - A Scaleway account logged into the [console](https://console.scaleway.com) - - [Owner](/iam/concepts/#owner) status or [IAM permissions](/iam/concepts/#permission) allowing you to perform actions in the intended Organization +1. Log in to the [Scaleway console](https://console.scaleway.com/). -## Use the Cost estimator - -1. Click **Generative APIs** in the **AI** section of the side menu in the [Scaleway console](https://console.scaleway.com/). +1. Click **Generative APIs** in the **AI** section of the side menu. 2. Select the **Cost estimator** tab. From c224392508eecff54817ddaa2cbf4457c245931f Mon Sep 17 00:00:00 2001 From: villyes Date: Mon, 11 May 2026 16:47:30 +0200 Subject: [PATCH 04/12] feat(genapi): add info about cost estimator MTA-7130 --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 7e5e098e84..601eeb20ae 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -1,6 +1,6 @@ --- title: Understanding Generative APIs costs -description: Compare costs for the different deployment options of Scaleway Generative API - Serverless versus Dedicated Deployment. +description: Compare costs for the different deployment options of Scaleway Generative APIs - Serverless versus Dedicated Deployment. tags: generative-apis how-much cost charge dates: validation: 2026-05-11 From a3dd4947e725f919826aa3392e4e84be9df1b3c1 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:22:28 +0200 Subject: [PATCH 05/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 601eeb20ae..993166c12a 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -10,7 +10,7 @@ dates: Understanding the financial impact of AI workloads is essential for making informed decisions. The Cost estimator (available via the [Scaleway console](https://console.scaleway.com/generative-api/cost-estimator)) provides a clear, side‑by‑side view of how the same generative workload behaves under the different deployment options offered by Scaleway: [Generative APIs - Serverless versus Generative APIs Dedicated Deployment](/generative-apis/faq/#what-is-the-difference-between-serverless-and-dedicated-deployment). - - The Cost estimator provides an estimate based on standard benchmarks (with significant concurrency and a low cache hit rate). Only performance tests in production, based on the customer's workload, can provide a fully accurate estimate. + - The Cost estimator provides an estimate based on standard benchmarks, assuming significant concurrency and a low cache hit rate. Only performance tests in production, based on your actual workload, can provide a fully accurate estimate. - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10), because processing will be bottlenecked by either input or output processing in these cases. - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, typical of long conversations). From cfb3e881b984a791392571c791dca659b2be7550 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:22:40 +0200 Subject: [PATCH 06/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 993166c12a..2ac969ecbb 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -11,7 +11,7 @@ Understanding the financial impact of AI workloads is essential for making infor - The Cost estimator provides an estimate based on standard benchmarks, assuming significant concurrency and a low cache hit rate. Only performance tests in production, based on your actual workload, can provide a fully accurate estimate. - - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10), because processing will be bottlenecked by either input or output processing in these cases. + - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10). In these cases, processing is bottlenecked by either input-heavy or output-heavy workloads. - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, typical of long conversations). From 419c0229dda6d3fdef0761522aa44a0d04c5635d Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:10 +0200 Subject: [PATCH 07/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 2ac969ecbb..f5ecfca3c1 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -12,7 +12,7 @@ Understanding the financial impact of AI workloads is essential for making infor - The Cost estimator provides an estimate based on standard benchmarks, assuming significant concurrency and a low cache hit rate. Only performance tests in production, based on your actual workload, can provide a fully accurate estimate. - Performance may vary significantly for extreme input/output ratios (e.g., 100:1 or 1:10). In these cases, processing is bottlenecked by either input-heavy or output-heavy workloads. - - In the case of dedicated deployments, caching is implicit and dedicated to a user, which can significantly improve performance for use cases with many similar input tokens (e.g., a long system prompt with a common prefix across requests, typical of long conversations). + - For dedicated deployments, caching is implicit and exclusive to each user. This can significantly improve performance for use cases with many similar input tokens, such as a long system prompt with a common prefix shared across requests, typical of extended conversations. ## Compare costs From ea0bf0cd54a9ea51a66e4cab73758bc21bb9ec34 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:20 +0200 Subject: [PATCH 08/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index f5ecfca3c1..840259ba96 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -19,7 +19,7 @@ Understanding the financial impact of AI workloads is essential for making infor 1. Log in to the [Scaleway console](https://console.scaleway.com/). -1. Click **Generative APIs** in the **AI** section of the side menu. +2. Click **Generative APIs** in the **AI** section of the side menu. 2. Select the **Cost estimator** tab. From 3a8ea2feff1a33217ae29e0fc7c20b16729e01a1 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:30 +0200 Subject: [PATCH 09/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 840259ba96..d26a36519f 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -21,7 +21,7 @@ Understanding the financial impact of AI workloads is essential for making infor 2. Click **Generative APIs** in the **AI** section of the side menu. -2. Select the **Cost estimator** tab. +3. Select the **Cost estimator** tab. 3. Model your workload by setting the following: - **Number of users** From 41b3d3e28d1ee0c1fd200aef81dec84e8f9bdfa7 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:39 +0200 Subject: [PATCH 10/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index d26a36519f..c0ebdb7066 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -23,7 +23,7 @@ Understanding the financial impact of AI workloads is essential for making infor 3. Select the **Cost estimator** tab. -3. Model your workload by setting the following: +4. Model your workload by setting the following: - **Number of users** - **Queries per user per day** - **Hours of usage/day** From 0ba00eff90f37ee3363102d0ff1f92eaa5eafdd7 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:47 +0200 Subject: [PATCH 11/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index c0ebdb7066..33e3a57a0b 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -29,7 +29,7 @@ Understanding the financial impact of AI workloads is essential for making infor - **Hours of usage/day** - **Load** -4. Set your chosen **Model** and **GPU**. +5. Set your chosen **Model** and **GPU**. The estimator instantly calculates the total monthly cost for both Serverless and Dedicated modes. 5. Compare cost differences side‑by‑side. \ No newline at end of file From 8db8a2840618a41b19884333d0edf8d593eb7900 Mon Sep 17 00:00:00 2001 From: vanda-scw Date: Mon, 11 May 2026 17:23:59 +0200 Subject: [PATCH 12/12] Update pages/generative-apis/reference-content/cost-estimator.mdx Co-authored-by: Firdevs Arslan --- pages/generative-apis/reference-content/cost-estimator.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/cost-estimator.mdx b/pages/generative-apis/reference-content/cost-estimator.mdx index 33e3a57a0b..b72af3d49b 100644 --- a/pages/generative-apis/reference-content/cost-estimator.mdx +++ b/pages/generative-apis/reference-content/cost-estimator.mdx @@ -32,4 +32,4 @@ Understanding the financial impact of AI workloads is essential for making infor 5. Set your chosen **Model** and **GPU**. The estimator instantly calculates the total monthly cost for both Serverless and Dedicated modes. -5. Compare cost differences side‑by‑side. \ No newline at end of file +6. Compare cost differences side‑by‑side. \ No newline at end of file