Skip to content

docs: Update reasoning_effort parameter mapping for Gemini 2.5 models (v1.17.13) #677

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

Open
roh26it wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs: Update reasoning_effort parameter mapping for Gemini 2.5 models (v1.17.13) #677

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 17 additions & 2 deletions integrations/llms/gemini.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2135,17 +2135,32 @@ 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`. The value is passed directly to Gemini as the `thinkingLevel`:
You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:

```python
response = portkey.chat.completions.create(
model="gemini-2.5-flash-preview-04-17",
max_tokens=3000,
reasoning_effort="medium", # Options: "none", "minimal", "low", "medium", "high"
reasoning_effort="medium", # Options: "none", "low", "medium", "high"
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
```

#### Gemini 2.5 Models

For Gemini 2.5 models, `reasoning_effort` maps to `thinking_budget` with specific token allocations:

| reasoning_effort | thinking_budget (tokens) |
|------------------|--------------------------|
| `none` | Disabled |
| `low` | 1,024 |
| `medium` | 8,192 |
| `high` | 24,576 |

#### Gemini 3.0+ Models

For Gemini 3.0 and later models, `reasoning_effort` maps directly to `thinkingLevel`:

| reasoning_effort | Gemini thinkingLevel |
|------------------|---------------------|
| `none` | Disabled |
Expand Down
19 changes: 17 additions & 2 deletions integrations/llms/vertex-ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -723,17 +723,32 @@ 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`. The value is passed directly to Gemini as the `thinkingLevel`:
You can also control thinking using the OpenAI-compatible `reasoning_effort` parameter instead of `thinking.budget_tokens`:

```python
response = portkey.chat.completions.create(
model="@VERTEX_PROVIDER/google.gemini-2.5-flash-preview-04-17",
max_tokens=3000,
reasoning_effort="medium", # Options: "none", "minimal", "low", "medium", "high"
reasoning_effort="medium", # Options: "none", "low", "medium", "high"
messages=[{"role": "user", "content": "Explain quantum computing"}]
)
```

#### Gemini 2.5 Models

For Gemini 2.5 models, `reasoning_effort` maps to `thinking_budget` with specific token allocations:

| reasoning_effort | thinking_budget (tokens) |
|------------------|--------------------------|
| `none` | Disabled |
| `low` | 1,024 |
| `medium` | 8,192 |
| `high` | 24,576 |

#### Gemini 3.0+ Models

For Gemini 3.0 and later models, `reasoning_effort` maps directly to `thinkingLevel`:

| reasoning_effort | Vertex thinkingLevel |
|------------------|---------------------|
| `none` | Disabled |
Expand Down