Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Update OpenAI Compatibility Docs with /v1/models (#5151)
royjhanf561eecfb864
diff --git a/docs/openai.md b/docs/openai.mdindex fee30f71d..701fbcdd6 100644--- a/docs/openai.md+++ b/docs/openai.md@@ -27,6 +27,8 @@ chat_completion = client.chat.completions.create(],model='llama3',)++list_completion = client.models.list()```### OpenAI JavaScript library@@ -45,6 +47,8 @@ const chatCompletion = await openai.chat.completions.create({messages: [{ role: 'user', content: 'Say this is a test' }],model: 'llama3',})++const listCompletion = await openai.models.list()```### `curl`@@ -66,6 +70,7 @@ curl http://localhost:11434/v1/chat/completions \]}'+curl http://localhost:11434/v1/models```## Endpoints@@ -103,6 +108,13 @@ curl http://localhost:11434/v1/chat/completions \- [ ] `user`- [ ] `n`+### `/v1/models`++#### Notes++- `created` corresponds to when the model was last modified+- `owned_by` corresponds to the ollama username, defaulting to `"library"`+## ModelsBefore using a model, pull it locally `ollama pull`: