Use this model in opencode

#28

by Jumpty - opened Mar 13

•

hi all, I would like to ask if this model can be started as a service through Ollama and called from OpenCode?
After configuring it, I encountered a timeout when inputting in OpenCoder. The output log looked something like this: "time=2026-03-12T23:40:45.629+08:00 level=INFO source=server.go:1568 msg="aborting completion request due to client closing the connection"
[GIN] 2026/03/12 - 23:40:45 | 500 | 2m17s | 127.0.0.1 | POST "/v1/chat/completions"
[GIN] 2026/03/12 - 23:40:45 | 200 | 2m17s | 127.0.0.1 | POST "/v1/chat/completions""

lek12

Mar 13

OII

JamesFlare

Mar 14

How did you config your opencode.jsonc?

lakshaysethi

Mar 16

Use llama Cpp server to serve the gguf of this and use v1 api

Jumpty

Mar 17

How did you config your opencode.jsonc?

I had only configured Claude Opus in OpenCode before, with only the baseurl and API key.

WynnD

Mar 21

•

edited Mar 21

Use @ai-sdk/anthropic and set a dummy api key

Example in "provider" block:

"llama.cpp": {
      "npm": "@ai-sdk/anthropic",
      "name": "llama.cpp",
      "options": {
        "baseURL": "http://192.168.0.101:8080/v1",
        "apiKey": "doesnotmatter",
        "structuredOutputs": false
},

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment