github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 22:52:13 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11752] Does the Ollama /api/chat endpoint support setting Reasoning Effort? #33548

New Issue
Closed
opened 2026-04-22 16:23:35 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 16:23:35 -05:00
Owner
Copy Link

Originally created by @EntropyYue on GitHub (Aug 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11752

Issue #11738 mentions that OpenAI-compatible endpoints support this parameter

Originally created by @EntropyYue on GitHub (Aug 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11752 Issue #11738 mentions that OpenAI-compatible endpoints support this parameter
GiteaMirror commented 2026-04-22 16:23:37 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (Aug 6, 2025):

yes! For the gpt-oss models think can now be "high"/"medium"/"low" in addition to true and false.

curl http://localhost:11434/api/chat -d '{
"stream": false,
  "think": "low",
  "model": "gpt-oss",
  "messages": [
    { "role": "user", "content": "Tell me an interesting fact" }
  ]
}' | jq .

we'll be adding documentation soon and updating SDKs

We also support this from the cli via e.g., --think=low and also /set think low within interactive CLI sessions

<!-- gh-comment-id:3161491187 --> @drifkin commented on GitHub (Aug 6, 2025): yes! For the `gpt-oss` models `think` can now be "high"/"medium"/"low" in addition to true and false. ``` curl http://localhost:11434/api/chat -d '{ "stream": false, "think": "low", "model": "gpt-oss", "messages": [ { "role": "user", "content": "Tell me an interesting fact" } ] }' | jq . ``` we'll be adding documentation soon and updating SDKs We also support this from the cli via e.g., `--think=low` and also `/set think low` within interactive CLI sessions
GiteaMirror commented 2026-04-22 16:23:38 -05:00
Author
Owner
Copy Link

@njbrake commented on GitHub (Aug 7, 2025):

Just a note that I think this behavior is broken in the ollama python sdk https://github.com/ollama/ollama-python/issues/552

<!-- gh-comment-id:3162151141 --> @njbrake commented on GitHub (Aug 7, 2025): Just a note that I think this behavior is broken in the ollama python sdk https://github.com/ollama/ollama-python/issues/552
GiteaMirror commented 2026-04-22 16:23:38 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (Aug 7, 2025):

thanks, yes we need to update that, will try to get to that asap

<!-- gh-comment-id:3162155878 --> @drifkin commented on GitHub (Aug 7, 2025): thanks, yes we need to update that, will try to get to that asap
GiteaMirror commented 2026-04-22 16:23:38 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (Aug 7, 2025):

python sdk updated (v0.5.3), javascript coming next. Example at https://github.com/ollama/ollama-python/blob/main/examples/thinking-levels.py

<!-- gh-comment-id:3165923125 --> @drifkin commented on GitHub (Aug 7, 2025): python sdk updated (v0.5.3), javascript coming next. Example at https://github.com/ollama/ollama-python/blob/main/examples/thinking-levels.py
GiteaMirror commented 2026-04-22 16:23:39 -05:00
Author
Owner
Copy Link

@chigkim commented on GitHub (Mar 1, 2026):

Is this possible through openai api by setting reasoning effort?
If so, can you set reasoning effort to "none" to disable entirely for other models like qwen3.5?

<!-- gh-comment-id:3978893980 --> @chigkim commented on GitHub (Mar 1, 2026): Is this possible through openai api by setting reasoning effort? If so, can you set reasoning effort to "none" to disable entirely for other models like qwen3.5?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#33548
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?