[BUG] API Error: 404 404 page not found
Status Fixed / completed
Reported on v2.1.17
Maintainer reply None cached
Activity 6 comments · opened Jan 23, 2026 · closed Jan 26, 2026
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
I'm trying to use Claude Code with Ollama, but getting a 404 error.
# Ollama is running and model is pulled
ollama pull qwen2.5-coder
ollama list # shows qwen2.5-coder:latest
# Environment variables set
export ANTHROPIC_AUTH_TOKEN=ollama
export ANTHROPIC_BASE_URL=http://localhost:11434/v1
# Running Claude Code
claude --model qwen2.5-coderError:
❯ [my prompt]
⎿ API Error: 404 404 page not found`
### What Should Happen?
Working with these ANTHROPIC_AUTH_TOKEN and ANTHROPIC_BASE_URL
### Error Messages/Logs
Steps to Reproduce
ollama pull qwen2.5-coder
ollama list # Expected: qwen2.5-coder appears in the list
npm install -g @anthropic-ai/claude-code
claude /logout
export ANTHROPIC_AUTH_TOKEN=ollama
export ANTHROPIC_BASE_URL=http://localhost:11434/v1
claude --model qwen2.5-coderEnter any prompt (e.g., "Create a Hello World in Python")
**Expected behavior:**
Claude Code should connect to the local Ollama instance and generate code using the qwen2.5-coder model.
**Actual behavior:**API Error: 404 404 page not found
Claude Model
Other
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
2.1.17 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Terminal.app (macOS)
Additional Information
_No response_
6 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
@fabgrd remove the "/v1" from the end of the BASE_URL
However, the integration / api is still broken. You see it on the ollama log side. Here are the ollama logs I see where a 404 is returned on the messages endpoint but not others. Not sure yet is this an issue with ollama or claude at this point.
[GIN] 2026/01/24 - 01:38:07 | 200 | 2.637402ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2026/01/24 - 01:38:25 | 404 | 1.776928ms | ::1 | POST "/v1/messages?beta=true"
[GIN] 2026/01/24 - 01:38:25 | 404 | 1.517692ms | ::1 | POST "/v1/messages?beta=true"
Thanks a lot for the tip! Tried with another LLM and got: API Error: 400 "deepseek-coder-v2:16b does not support tools".
Is tool support something that needs to be implemented on Ollama's side, or is this an API compatibility issue? Do you think using a proxy like LiteLLM actually solve this problem ?
Upgrading Ollama to v0.14.2 fixed this for me. I'll just document some steps to help others.
I have Ollama running via Snap, so I:
1) checked for the right channel (
snap info ollama) - currently it's edge2) switched it to the latest of v0.14.2 with
sudo snap switch ollama --edge, and finally3) actually installed the new version with
sudo snap refresh ollama.On a separate machine where Ollama was installed with
curl -fsSL https://ollama.com/install.sh | sh, rerunning the command brought Ollama up to v0.15.0, which also fixed the error.If you get an error like this:
found"},"request_id":"req_72101449e6e1f9f5eeb1e98b"
Check that you're passing the model exactly as it appears at http://localhost:11434/v1/models.
I'm starting Claude Code like so:
ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 claude --model qwen2.5-coderUpgrading Ollama to v0.15.1 fixed this for me 🙂
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.