Custom providers on Manifest
9.5B tokens
/ 30 days
16 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 | 3.5 B |
2.Deepseek V4 Flash 0731 | API Key | 1.7 B |
3.DeepSeek V4.1 Flash | API Key | 1.6 B |
4.GLM 5.3 Flash | API Key | 1.2 B |
5.Qwen3.8 Omni Flash | API Key | 636 M |
6.Agnes 2.5 Flash | API Key | 272 M |
7.Gemini 3.7 Flash | API Key | 204 M |
8.Qwen3.8 Max | API Key | 121 M |
9.Glm 5.3 Flash | API Key | 111 M |
10.Deepseek V4 Flash | API Key | 46 M |
11.Other Custom Models | API Key | 42 M |
12.Deepseek V4.1 Flash | API Key | 36 M |
13.Deepseek V4 Flash Free | API Key | 35 M |
14.Deepseek V4 Flash | API Key | 2 M |
15.Minimax M3 | API Key | 1 M |
16.Agnes 2.0 Flash | API Key | 1 M |
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.
