github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7125] openai: support max_completion_tokens due to deprecation of max_tokens #51037

New Issue
Open
opened 2026-04-28 17:58:03 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 17:58:03 -05:00
Owner
Copy Link

Originally created by @codefromthecrypt on GitHub (Oct 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7125

max_tokens is now deprecated for max_completion_tokens. I suspect we should support both. One way is to define another field in our request object and then default if one or the other isn't set defbf9425a/openai/openai.go (L77)

See https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens
See 10053bef25/openapi.yaml (L9854-L9866)

Originally created by @codefromthecrypt on GitHub (Oct 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7125 max_tokens is now deprecated for max_completion_tokens. I suspect we should support both. One way is to define another field in our request object and then default if one or the other isn't set https://github.com/ollama/ollama/blob/defbf9425af8228f3420d567e9eeaa29d8ac87e3/openai/openai.go#L77 See https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens See https://github.com/openai/openai-openapi/blob/10053bef25cd50a7424f5265ba51a7a63ba95b48/openapi.yaml#L9854-L9866
GiteaMirror added the feature requestapi labels 2026-04-28 17:58:06 -05:00
GiteaMirror commented 2026-04-28 17:58:11 -05:00
Author
Owner
Copy Link

@starpit commented on GitHub (Aug 19, 2025):

Could we add a MaxCompletionsToken field, and mark the existing MaxTokens as deprecated?

Fwiw, vLLM accepts both max_tokens and max_completion_tokens without complaint. Gemini's OpenAI compatibility endpoint refuses to accept both, responding with "max_tokens and max_completion_tokens cannot both be set". Oof.

<!-- gh-comment-id:3201413923 --> @starpit commented on GitHub (Aug 19, 2025): Could we add a MaxCompletionsToken field, and mark the existing MaxTokens as deprecated? Fwiw, vLLM accepts both `max_tokens` and `max_completion_tokens` without complaint. Gemini's OpenAI compatibility endpoint refuses to accept both, responding with "max_tokens and max_completion_tokens cannot both be set". Oof.
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 api feature request
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#51037
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?