github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15853] docs: add guide for using third-party OpenAI-compatible providers as remote backends #72162

New Issue
Open
opened 2026-05-05 03:34:28 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 03:34:28 -05:00
Owner
Copy Link

Originally created by @FuturMix on GitHub (Apr 28, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15853

Problem

Ollama supports OpenAI-compatible APIs, but the documentation doesn't cover how to use third-party API gateways as remote backends. Users who want to access cloud models (GPT, Claude, Gemini) alongside local Ollama models have to figure this out themselves.

Proposed Solution

Add a documentation page (e.g., docs/openai-providers.md) that explains how to configure Ollama tools and SDKs to work with OpenAI-compatible API gateways. The guide would cover:

  1. Setting OPENAI_API_BASE / base_url to point to a third-party provider
  2. Code examples in Python and JavaScript using the OpenAI SDK
  3. A pattern for switching between local Ollama and remote providers

This would complement the existing docs/cloud.mdx and docs/api/openai-compatibility.mdx pages.

Why This Is Important

Many Ollama users want a hybrid setup: local models for privacy/cost, cloud models for capability. A clear guide would reduce friction and help users get the most out of Ollama's OpenAI compatibility.

I'm happy to submit a PR with the documentation if you think this would be useful.

Originally created by @FuturMix on GitHub (Apr 28, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15853 ## Problem Ollama supports OpenAI-compatible APIs, but the documentation doesn't cover how to use third-party API gateways as remote backends. Users who want to access cloud models (GPT, Claude, Gemini) alongside local Ollama models have to figure this out themselves. ## Proposed Solution Add a documentation page (e.g., `docs/openai-providers.md`) that explains how to configure Ollama tools and SDKs to work with OpenAI-compatible API gateways. The guide would cover: 1. Setting `OPENAI_API_BASE` / `base_url` to point to a third-party provider 2. Code examples in Python and JavaScript using the OpenAI SDK 3. A pattern for switching between local Ollama and remote providers This would complement the existing `docs/cloud.mdx` and `docs/api/openai-compatibility.mdx` pages. ## Why This Is Important Many Ollama users want a hybrid setup: local models for privacy/cost, cloud models for capability. A clear guide would reduce friction and help users get the most out of Ollama's OpenAI compatibility. I'm happy to submit a PR with the documentation if you think this would be useful.
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#72162
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?