Skip to content

Update Gemini thinking level mapping documentation #641

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sambharia merged 2 commits into from
Dec 26, 2025
Merged

Update Gemini thinking level mapping documentation #641

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d75ece2
Update integrations/llms/gemini.mdx
mintlify[bot] Dec 24, 2025
8ce4a46
Update integrations/llms/vertex-ai.mdx
mintlify[bot] Dec 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions integrations/llms/gemini.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2135,7 +2135,7 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g

### Using reasoning_effort Parameter

You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`. The value is passed directly to Gemini as the `thinkingLevel`:

```python
response = portkey.chat.completions.create(
Expand All @@ -2149,8 +2149,10 @@ response = portkey.chat.completions.create(
| reasoning_effort | Gemini thinkingLevel |
|------------------|---------------------|
| `none` | Disabled |
| `minimal`, `low` | `low` |
| `medium`, `high` | `high` |
| `minimal` | `minimal` |
| `low` | `low` |
| `medium` | `medium` |
| `high` | `high` |

<Info>
Gemini grounding mode may not work via Portkey SDK. Contact support@portkey.ai for assistance.
Expand Down
8 changes: 5 additions & 3 deletions integrations/llms/vertex-ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -723,7 +723,7 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g

### Using reasoning_effort Parameter

You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:
You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`. The value is passed directly to Gemini as the `thinkingLevel`:

```python
response = portkey.chat.completions.create(
Expand All @@ -737,8 +737,10 @@ response = portkey.chat.completions.create(
| reasoning_effort | Vertex thinkingLevel |
|------------------|---------------------|
| `none` | Disabled |
| `minimal`, `low` | `low` |
| `medium`, `high` | `high` |
| `minimal` | `minimal` |
| `low` | `low` |
| `medium` | `medium` |
| `high` | `high` |

### Multi turn conversation

Expand Down