Skip to content

Commit ce03b77

Browse files
fpagnyRoRoJldecarvalho-doc
authored
feat(genapi): update deprecated models (#5831)
* feat(genapi): update deprecated models Updated deprecation notices for mistral small 3.1, devstral and qwen2.5 coder models and added recommendations for alternatives. * feat(genapi): update deprecated models * fix(genapi): supported model wording Apply suggestions from nerda-codes * Apply suggestions from code review Co-authored-by: ldecarvalho-doc <82805470+ldecarvalho-doc@users.noreply.github.com> --------- Co-authored-by: Rowena Jones <36301604+RoRoJ@users.noreply.github.com> Co-authored-by: ldecarvalho-doc <82805470+ldecarvalho-doc@users.noreply.github.com>
1 parent cc8ef2b commit ce03b77

File tree

1 file changed

+5
-8
lines changed

1 file changed

+5
-8
lines changed

pages/generative-apis/reference-content/supported-models.mdx

Lines changed: 5 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -74,15 +74,9 @@ Our [Embeddings API](/generative-apis/how-to/query-embedding-models) provides bu
7474
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/).
7575
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.
7676

77-
| Provider | Model string | End of Life (EOL) date
78-
|-----------------|-----------------|-----------------|
79-
| Mistral | `devstral-small-2505` | 14th November, 2025 |
80-
| Mistral | `mistral-small-3.1-24b-instruct-2503` | 14th November, 2025 |
81-
| Qwen | `qwen2.5-coder-32b-instruct` | 14th November, 2025 |
82-
8377
<Message type="note">
84-
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`.
8680
</Message>
8781

8882
## End of Life (EOL) models
@@ -92,4 +86,7 @@ These models are not accessible anymore from Generative APIs. They can still how
9286
| Provider | Model string | EOL date
9387
|-----------------|-----------------|-----------------|
9488
| Meta | `llama-3.1-70b-instruct` | 25th May, 2025 |
89+
| Mistral | `devstral-small-2505` | 14th November, 2025 |
90+
| Mistral | `mistral-small-3.1-24b-instruct-2503` | 14th November, 2025 |
91+
| Qwen | `qwen2.5-coder-32b-instruct` | 14th November, 2025 |
9592
| SBERT | `sentence-t5-xxl` | 26 February, 2025 |

0 commit comments

Comments
 (0)