From ef6c01f86e36c69c90a9d21b005c252888045b87 Mon Sep 17 00:00:00 2001 From: fpagny Date: Tue, 3 Jun 2025 13:49:05 +0200 Subject: [PATCH 1/3] feat(genapi): update supported models status --- pages/generative-apis/reference-content/supported-models.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pages/generative-apis/reference-content/supported-models.mdx b/pages/generative-apis/reference-content/supported-models.mdx index 51fd2d971f..e47d0ab996 100644 --- a/pages/generative-apis/reference-content/supported-models.mdx +++ b/pages/generative-apis/reference-content/supported-models.mdx @@ -18,7 +18,7 @@ Our API supports the most popular models for [Chat](/generative-apis/how-to/quer | Provider | Model string | Context window (Tokens) | Maximum output (Tokens)| License | Model card | |-----------------|-----------------|-----------------|-----------------|-----------------|-----------------| | Google (Preview) | `gemma-3-27b-it` | 40k | 8192 | [Gemma](https://ai.google.dev/gemma/terms) | [HF](https://huggingface.co/google/gemma-3-27b-it) | -| Mistral (Preview) | `mistral-small-3.1-24b-instruct-2503` | 128k | 8192 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | [HF](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503) | +| Mistral | `mistral-small-3.1-24b-instruct-2503` | 128k | 8192 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | [HF](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503) | ## Chat models @@ -29,7 +29,7 @@ Our API supports the most popular models for [Chat](/generative-apis/how-to/quer | Mistral | `mistral-nemo-instruct-2407` | 128k | 8192 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | [HF](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) | | Qwen | `qwen2.5-coder-32b-instruct` | 32k | 8192 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | [HF](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) | | DeepSeek (Preview) | `deepseek-r1` | 20k | 4096 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | [HF](https://huggingface.co/deepseek-ai/DeepSeek-R1) | -| DeepSeek (Preview) | `deepseek-r1-distill-llama-70b` | 32k | 4096 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | [HF](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | +| DeepSeek | `deepseek-r1-distill-llama-70b` | 32k | 4096 | [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) | [HF](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) | DeepSeek-R1 is currently under maintenance and therefore not available on Generative APIs anymore. From 71de209ea759e18fd211cb590d79d55c1b29b63a Mon Sep 17 00:00:00 2001 From: fpagny Date: Tue, 3 Jun 2025 14:03:30 +0200 Subject: [PATCH 2/3] feat(genapi): update end of life models --- .../reference-content/supported-models.mdx | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/pages/generative-apis/reference-content/supported-models.mdx b/pages/generative-apis/reference-content/supported-models.mdx index e47d0ab996..3a7e46387a 100644 --- a/pages/generative-apis/reference-content/supported-models.mdx +++ b/pages/generative-apis/reference-content/supported-models.mdx @@ -63,18 +63,24 @@ Our [Embeddings API](/generative-apis/how-to/query-embedding-models) provides bu ## Deprecated models -Scaleway's model lifecyle is introduced on our [dedicated documentation page](/generative-apis/reference-content/model-lifecycle/). +These models can still be accessed in Generative APIs, but their End of Life (EOL) is planned according to our [model lifecyle](/generative-apis/reference-content/model-lifecycle/). +Deprecated models should not be queried anymore. We recommend to use newer models available in Generative APIs or to deploy these models in dedicated [Managed Inference](https://console.scaleway.com/inference/deployments) deployments. -| Provider | Model string | EOL date +| Provider | Model string | End of Life (EOL) date |-----------------|-----------------|-----------------| | Meta | `llama-3.1-70b-instruct` | 25th May, 2025 | -| SBERT | `sentence-t5-xxl` | 26 February, 2025 | Llama 3.1 70B is now deprecated. The new Llama 3.3 70B is available with similar or better performance in most use cases. After May 25th 2025, your requests to Llama 3.1 70B will be redirected automatically to Llama 3.3 70B. Llama 3.1 8B is not affected by this change and remains supported. -## EOL models +## End of Life (EOL) models + +These models are not accessible anymore from Generative APIs. They can still however be deployed on dedicated [Managed Inference](https://console.scaleway.com/inference/deployments) deployments. + +| Provider | Model string | EOL date +|-----------------|-----------------|-----------------| +| SBERT | `sentence-t5-xxl` | 26 February, 2025 | This section will list models that are retired and no longer accessible for use. From 453cf63f13cda203519fd8aff7ffa413dd9599e0 Mon Sep 17 00:00:00 2001 From: fpagny Date: Tue, 3 Jun 2025 14:05:21 +0200 Subject: [PATCH 3/3] fix(genapi): update typos --- pages/generative-apis/reference-content/supported-models.mdx | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/pages/generative-apis/reference-content/supported-models.mdx b/pages/generative-apis/reference-content/supported-models.mdx index 3a7e46387a..e63c0f7b49 100644 --- a/pages/generative-apis/reference-content/supported-models.mdx +++ b/pages/generative-apis/reference-content/supported-models.mdx @@ -63,7 +63,7 @@ Our [Embeddings API](/generative-apis/how-to/query-embedding-models) provides bu ## Deprecated models -These models can still be accessed in Generative APIs, but their End of Life (EOL) is planned according to our [model lifecyle](/generative-apis/reference-content/model-lifecycle/). +These models can still be accessed in Generative APIs, but their End of Life (EOL) is planned according to our [model lifecyle policy](/generative-apis/reference-content/model-lifecycle/). Deprecated models should not be queried anymore. We recommend to use newer models available in Generative APIs or to deploy these models in dedicated [Managed Inference](https://console.scaleway.com/inference/deployments) deployments. | Provider | Model string | End of Life (EOL) date @@ -82,5 +82,3 @@ These models are not accessible anymore from Generative APIs. They can still how | Provider | Model string | EOL date |-----------------|-----------------|-----------------| | SBERT | `sentence-t5-xxl` | 26 February, 2025 | - -This section will list models that are retired and no longer accessible for use.