Logo SVG copied to clipboard
New Introducing paid plans for Manifest Cloud Learn more

Custom providers on Manifest

17.0B tokens / 30 days

46 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 Key4.9 B
2.MiniMax M3
API Key1.8 B
3.Claude Opus 4 8
API Key1.3 B
4.Claude Sonnet 4 6
API Key1.2 B
5.Deepseek V4 Flash Free
API Key945 M
6.Mimo V2.5 Pro Free
API Key761 M
7.Claude Sonnet 4 6
API Key658 M
8.Minimax M3
API Key557 M
9.Glm 5.2
API Key530 M
10.Agnes 2.0 Flash
API Key507 M
11.Minimax M2.7
API Key485 M
12.Mimo V2.5
API Key407 M
13.Deepseek V4 Flash
API Key371 M
14.Mimo V2.5 Free
API Key248 M
15.Claude Sonnet 5
API Key230 M
16.Deepseek V4 Pro
API Key228 M
17.Nemotron 3 Ultra Free
API Key200 M
18.Nemotron 3 Super 120b A12b
API Key194 M
19.Auto
API Key166 M
20.Openrouter Free
API Key165 M
21.Claude Opus 4 6
API Key140 M
22.Mistral Large
API Key137 M
23.Kimi K2.6
API Key131 M
24.Mistral Medium 3 5
API Key110 M
25.Mimo V2.5 Pro
API Key98 M
26.Claude Fable 5
API Key76 M
27.Gpt 5.5
API Key69 M
28.Glm 5.2 Free
API Key53 M
29.Claude Opus 4 7
API Key45 M
30.Gpt 5.4 Mini
API Key31 M
31.Kimi K2.6
API Key31 M
32.Gpt 5.4
API Key29 M
33.Glm 5.1
API Key28 M
34.Claude Sonnet 4.5
API Key22 M
35.Claude Haiku 4 5 20251001
API Key21 M
36.Claude Haiku 4.5
API Key19 M
37.Kimi K2.6
API Key19 M
38.Gpt 5.3 Codex
API Key17 M
39.Gpt Oss 120b
API Key8 M
40.Glm 5.2
API Key8 M
41.Kimi K2.7 Code
API Key6 M
42.Kimi K2.7 Code Free
API Key2 M
43.Gpt 5.4
API Key2 M
44.Deepseek V3.2
API Key2 M
45.Zai Glm 4.7
API Key1 M
46.Nemotron 3 Nano Omni 30b A3b Reasoning
API Key818 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.