fix(ovhcloud): Edit models capabilities in model_prices_and_context_window.json #22905
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -27224,208 +27224,6 @@ | |
| "max_tokens": 128000, | ||
| "mode": "chat" | ||
| }, | ||
| "palm/chat-bison": { | ||
| "input_cost_per_token": 1.25e-07, | ||
| "litellm_provider": "palm", | ||
|
|
@@ -39203,5 +39001,170 @@ | |
| "supports_reasoning": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true | ||
| }, | ||
| "ovhcloud/Qwen3Guard-Gen-8B": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 32768, | ||
| "max_input_tokens": 32768, | ||
| "max_output_tokens": 32768 | ||
| }, | ||
| "ovhcloud/Qwen3Guard-Gen-0.6B": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 32768, | ||
| "max_input_tokens": 32768, | ||
| "max_output_tokens": 32768 | ||
| }, | ||
eliasto marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "ovhcloud/Meta-Llama-3_3-70B-Instruct": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 7.4e-07, | ||
| "output_cost_per_token": 7.4e-07, | ||
| "supports_function_calling": true, | ||
|
Comment on lines
+39016
to
+39027
Contributor
There was a problem hiding this comment.
Every previously-existing OVHcloud entry had a Please restore the "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct"This pattern applies to all twelve re-declared models (
Contributor
Author
There was a problem hiding this comment. No it's not necessary |
||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true | ||
| }, | ||
| "ovhcloud/Llama-3.1-8B-Instruct": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 1.1e-07, | ||
| "output_cost_per_token": 1.1e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true | ||
| }, | ||
| "ovhcloud/Qwen2.5-VL-72B-Instruct": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 32768, | ||
| "max_input_tokens": 32768, | ||
| "max_output_tokens": 32768, | ||
| "input_cost_per_token": 1.01e-06, | ||
| "output_cost_per_token": 1.01e-06, | ||
| "supports_function_calling": false, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": false, | ||
| "supports_vision": true | ||
| }, | ||
| "ovhcloud/Qwen3-Coder-30B-A3B-Instruct": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 262144, | ||
| "max_input_tokens": 262144, | ||
| "max_output_tokens": 262144, | ||
| "input_cost_per_token": 7e-08, | ||
| "output_cost_per_token": 2.6e-07, | ||
| "supports_function_calling": true, | ||
eliasto marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_reasoning": false | ||
| }, | ||
| "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 1e-07, | ||
| "output_cost_per_token": 3.1e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_vision": true | ||
| }, | ||
| "ovhcloud/Mistral-Nemo-Instruct-2407": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
|
Comment on lines
+39082
to
+39084
Contributor
There was a problem hiding this comment. Context window reduced for Two models have had their context windows significantly reduced compared to the previous entries:
Users who currently pass prompts between 65 K and 118 K / 127 K tokens to these models will start receiving context-limit errors after this change is deployed. Per the repo's guideline against backwards-incompatible changes without user-controlled flags, this should be documented in the PR description if it reflects a real OVHcloud endpoint limit change, or reverted if it does not. Context Used: Rule from Why: This breaks current ... (source) |
||
| "max_tokens": 65536, | ||
| "max_input_tokens": 65536, | ||
| "max_output_tokens": 65536, | ||
| "input_cost_per_token": 1.4e-07, | ||
| "output_cost_per_token": 1.4e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true | ||
| }, | ||
| "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 32768, | ||
| "max_input_tokens": 32768, | ||
| "max_output_tokens": 32768, | ||
| "input_cost_per_token": 7e-07, | ||
| "output_cost_per_token": 7e-07, | ||
| "supports_function_calling": false, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": false | ||
| }, | ||
| "ovhcloud/Qwen3-32B": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 32768, | ||
| "max_input_tokens": 32768, | ||
| "max_output_tokens": 32768, | ||
| "input_cost_per_token": 9e-08, | ||
| "output_cost_per_token": 2.5e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_reasoning": true | ||
| }, | ||
| "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 7.4e-07, | ||
| "output_cost_per_token": 7.4e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_reasoning": true | ||
| }, | ||
| "ovhcloud/gpt-oss-20b": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 5e-08, | ||
| "output_cost_per_token": 1.8e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
eliasto marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "supports_reasoning": true | ||
| }, | ||
| "ovhcloud/Mistral-7B-Instruct-v0.3": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 65536, | ||
| "max_input_tokens": 65536, | ||
| "max_output_tokens": 65536, | ||
| "input_cost_per_token": 1.1e-07, | ||
| "output_cost_per_token": 1.1e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true | ||
| }, | ||
| "ovhcloud/gpt-oss-120b": { | ||
| "litellm_provider": "ovhcloud", | ||
| "mode": "chat", | ||
| "max_tokens": 131072, | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 131072, | ||
| "input_cost_per_token": 9e-08, | ||
| "output_cost_per_token": 4.7e-07, | ||
| "supports_function_calling": true, | ||
| "supports_response_schema": true, | ||
| "supports_tool_choice": true, | ||
| "supports_reasoning": true | ||
| } | ||
eliasto marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| } | ||
eliasto marked this conversation as resolved.
Show resolved
Hide resolved
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.