You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: pages/generative-apis/reference-content/supported-models.mdx
+5-8Lines changed: 5 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -74,15 +74,9 @@ Our [Embeddings API](/generative-apis/how-to/query-embedding-models) provides bu
74
74
These models can still be accessed in Generative APIs, but their End of Life (EOL) is planned according to our [model lifecycle policy](/generative-apis/reference-content/model-lifecycle/).
75
75
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.
76
76
77
-
| Provider | Model string | End of Life (EOL) date
Llama 3.1 70B is now deprecated. The new Llama 3.3 70B is available with similar or better performance in most use cases.
85
-
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.
78
+
`mistral-small-3.1-24b-instruct-2503` has been deprecated as of November 14th, 2025. Requests to this model are now redirected to a more recent version of this model: `mistral-small-3.2-24b-instruct-2506`.
79
+
`qwen2.5-coder-32b-instruct and `devstral-small-2505` have been deprecated as of November 14th, 2025. Requests to these models are now redirected to a version offering similar or improved performance in most use cases: `qwen3-coder-30b-a3b-instruct`.
86
80
</Message>
87
81
88
82
## End of Life (EOL) models
@@ -92,4 +86,7 @@ These models are not accessible anymore from Generative APIs. They can still how
0 commit comments