Custom providers on Manifest
4.9B tokens
/ 30 days
22 models routed through Manifest over the last 30 days.
Bring any OpenAI-compatible endpoint — vLLM, Ollama, LiteLLM, LM Studio, or a private gateway — and Manifest routes it like any other provider, with a spending cap per agent and automatic fallback. Every custom endpoint connected to Manifest is grouped on this page as one provider.
Custom provider tokens processed on Manifest
Models in use
# Model |
Auth type | Tokens / last 30 days |
|---|---|---|
1.Other Custom Models | API Key | 2.4 B |
2.Agnes 2.5 Flash | API Key | 691 M |
3.Qwen3.8 Omni Flash | API Key | 666 M |
4.Gemini 3.7 Flash | API Key | 312 M |
5.Glm 5.3 Flash | API Key | 224 M |
6.Minimax M3 | API Key | 114 M |
7.Deepseek V4 Flash | API Key | 81 M |
8.Deepseek V4 Flash Free | API Key | 75 M |
9.Deepseek V4 Flash | API Key | 69 M |
10.Glm 5.3 Flash | API Key | 63 M |
11.Qwen3.8 Max | API Key | 60 M |
12.Deepseek V4.1 Flash | API Key | 30 M |
13.Deepseek V4 Flash 0731 | API Key | 29 M |
14.Deepseek V4 Flash | API Key | 25 M |
15.Glm 5.2 | API Key | 18 M |
16.Deepseek V4 Pro | API Key | 13 M |
17.Claude Sonnet 4 6 | API Key | 10 M |
18.Other Custom Models | API Key | 6 M |
19.Kimi K3 | API Key | 6 M |
20.Agnes 2.0 Flash | API Key | 3 M |
21.Space Bunny Free | API Key | 1 M |
22.Claude Sonnet 5 | API Key | 77 K |
Model names are aggregated across every connected custom endpoint. Models used by only a handful of workspaces are grouped under “Other Custom Models” to keep individual configurations private.
