Use OpenCode with Manifest
OpenCode can use OpenAI-compatible providers from
~/.config/opencode/opencode.json.
Add Manifest as a provider and keep using OpenCode while Manifest chooses the right model for each coding request.
52 models routed through Manifest over the last 30 days.
Why use OpenCode with Manifest
Coding assistants mix simple edits, long-context search, and hard reasoning. Manifest lets OpenCode keep one stable model name while routing those requests across your providers, subscription plans, local models, and fallbacks.
- Use one manifest/auto model in OpenCode
- Route easy edits to cheaper models and hard changes to stronger ones
- Fallback across providers when quota or rate limits hit
- Track token usage, cost, model choice, and failures in one dashboard
- Keep the OpenCode workflow unchanged
- Self-host Manifest or use Manifest Cloud
Setup in 60 seconds
Add Manifest as an OpenAI-compatible provider in your global
opencode.json config and set the default
model to manifest/auto.
Add this block to ~/.config/opencode/opencode.json.
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"manifest": {
"npm": "@ai-sdk/openai-compatible",
"name": "Manifest",
"options": {
"baseURL": "https://api.manifest.build/v1",
"apiKey": "mnfst_YOUR_KEY"
},
"models": {
"auto": {
"name": "Manifest Auto"
}
}
}
},
"model": "manifest/auto"
}
https://api.manifest.build/v1
mnfst_YOUR_KEY
manifest/auto
OpenCode tokens processed on Manifest
Models in use
# Model |
Auth type | Tokens / last 30 days |
|---|---|---|
1.Big Pickle | API Key | 975 M |
2.Deepseek V4 Pro | API Key | 439 M |
3.X Preview F Free | API Key | 198 M |
4.Gpt 5.6 Sol | Subscription | 165 M |
5.Deepseek V4 Flash Free | API Key | 135 M |
6.Deepseek V4 Flash | API Key | 114 M |
7.Mimo V2.5 Free | API Key | 98 M |
8.Gpt 5.6 Luna | Subscription | 94 M |
9.Openrouter Free | API Key | 86 M |
10.Gpt 5.5 | Subscription | 80 M |
11.MiniMax M3 | Subscription | 76 M |
12.Step 3.7 Flash | API Key | 28 M |
13.Glm 5.1 | Subscription | 27 M |
14.Kimi K3 | API Key | 26 M |
15.Deepseek V4 Flash | Subscription | 26 M |
16.Laguna Xs 2.1 | API Key | 21 M |
17.Ling 3.0 Flash | API Key | 19 M |
18.Nemotron 3 Ultra 550b A55b | API Key | 18 M |
19.Gpt 5.4 | Subscription | 14 M |
20.Glm 5.2 | Subscription | 13 M |
21.Minimax M3 | Subscription | 10 M |
22.Step 3.7 Flash | API Key | 10 M |
23.Mistral Vibe Cli Latest | Subscription | 8 M |
24.Kilo Auto Free | API Key | 8 M |
25.Inkling | API Key | 8 M |
26.Minimax M3 | Subscription | 7 M |
27.Deepseek V4 Pro | Subscription | 6 M |
28.Gpt Oss:120b | Subscription | 5 M |
29.Kimi K3 | Subscription | 5 M |
30.Glm 5.2 | API Key | 3 M |
31.Minimax M3 | API Key | 3 M |
32.Qwen3.6 Plus | Subscription | 3 M |
33.Nemotron 3 Ultra 550b A55b | API Key | 3 M |
34.Longcat 2.0 Free | API Key | 2 M |
35.Nemotron 3 Nano Omni 30b A3b Reasoning | API Key | 2 M |
36.Qwen3.7 Plus | Subscription | 2 M |
37.Gemma4:31b | Subscription | 2 M |
38.Glm 5.2 | API Key | 965 K |
39.Lfm 2.5 2.6b | API Key | 918 K |
40.Gpt 5.6 Terra | Subscription | 670 K |
41.Gemini Flash Lite Latest | API Key | 619 K |
42.Nemotron 3 Ultra | Subscription | 606 K |
43.GLM 5.2 FP8 | API Key | 203 K |
44.Gemini 3.5 Flash | API Key | 137 K |
45.Codestral 2508 | API Key | 134 K |
46.Deepseek V4 Flash | Subscription | 86 K |
47.Glm 5.2 | Subscription | 43 K |
48.Gemma 4 26b A4b It | API Key | 34 K |
49.Mimo V2.5 | Subscription | 15 K |
50.Hy3 Free | API Key | 9 K |
51.Claude Opus 5 | Subscription | 4 K |
52.Gpt Oss 120b | API Key | 871 |