Use Hermes with the LLM gateway
Hermes is a lightweight agent for delivering AI capabilities to your stack. Point it at the gateway endpoint and every request routes through the right model. Same Hermes config, smaller bill.
172 models routed through the gateway over the last 30 days.
Why use Hermes with the gateway
Hermes exposes a clean YAML-driven config for plugging in any OpenAI-compatible endpoint. Our LLM gateway is exactly that: a single endpoint that fans your traffic out to many providers, picks the right model per request, and surfaces cost in one dashboard.
- One config.yaml change, zero workflow disruption
- Save up to 70% on a typical Hermes workload
- Switch between Claude, GPT, Gemini, and open models without rewriting prompts
- Per-agent spend limits and rate caps
- Real-time cost dashboards with token, model, and latency breakdowns
- Open source, self-hostable, OpenAI-compatible
Setup in 60 seconds
Add the gateway endpoint to your Hermes config.yaml
or run hermes model and pick "Custom endpoint".
Point Hermes at the gateway endpoint to route requests across multiple models.
Open the Hermes configuration file:
hermes config edit
Add the following model: section to
your config.yaml:
model:
provider: custom
base_url: https://api.manifest.build/v1
api_key: mnfst_YOUR_KEY
default: auto
custom
https://api.manifest.build/v1
mnfst_YOUR_KEY
auto
Run the onboarding wizard and select Custom endpoint when prompted. Then enter the following values:
hermes model
https://api.manifest.build/v1
mnfst_YOUR_KEY
auto
Hermes tokens processed by the gateway
Models in use
# Model |
Auth type | Tokens / last 30 days |
|---|---|---|
1.Openai.Gpt 5.6 Sol | API Key | 1.8 B |
2.Deepseek V4 Flash 0731 | API Key | 868 M |
3.Deepseek V4 Flash | Subscription | 669 M |
4.Anthropic.Claude Sonnet 5 | API Key | 539 M |
5.Openrouter Free | API Key | 516 M |
6.Glm 5.3 Flash | Subscription | 396 M |
7.Deepseek V4.1 Flash | Subscription | 336 M |
8.Qwen3.7 Flash | API Key | 298 M |
9.Kilo Auto Free | API Key | 294 M |
10.Openai.Gpt 5.6 Luna | API Key | 226 M |
11.Mimo V2.5 | Subscription | 167 M |
12.Minimax M3 | Subscription | 152 M |
13.Gpt 5.6 Terra | Subscription | 148 M |
14.Deepseek V4.1 Flash | Subscription | 138 M |
15.Gpt 5.6 Sol | Subscription | 134 M |
16.Grok 4.6 | Subscription | 126 M |
17.Gpt 5.6 Luna | Subscription | 122 M |
18.Gemini 3.8 Flash | API Key | 114 M |
19.Deepseek V4 Flash | API Key | 89 M |
20.Grok 4.5 | Subscription | 89 M |
21.MiniMax M3 | API Key | 88 M |
22.Kimi K2.7 Code | Subscription | 84 M |
23.Qwen3.6 Plus | Subscription | 83 M |
24.Gemini 3.5 Flash Lite | API Key | 78 M |
25.Gemini 3.7 Flash | API Key | 73 M |
26.Hy3 | API Key | 67 M |
27.Deepseek V4 Flash Latest | API Key | 60 M |
28.Deepseek V4 Flash 0731 | API Key | 49 M |
29.Deepseek V4 Pro | Subscription | 48 M |
30.Deepseek V4 Flash Free | API Key | 47 M |
31.Kimi K2.6 | Subscription | 43 M |
32.Gemini 3.1 Flash Lite | API Key | 43 M |
33.Gemini 3.5 Flash | API Key | 40 M |
34.Step 3.7 Flash | API Key | 39 M |
35.Deepseek V4 Pro | API Key | 37 M |
36.Qwen3.8 27B | API Key | 34 M |
37.Deepseek V4 Pro | Subscription | 33 M |
38.MiniMax M3 | Subscription | 32 M |
39.Deepseek V4 Pro 0813 | API Key | 30 M |
40.Gemini 3.6 Flash | API Key | 28 M |
41.Glm 5.1 | Subscription | 26 M |
42.Gemini Flash Lite Latest | API Key | 23 M |
43.Gpt 5.6 Luna | Subscription | 18 M |
44.Gpt 5.5 | Subscription | 17 M |
45.Kimi K3 | Subscription | 15 M |
46.Glm 5.3 | Subscription | 15 M |
47.Muse Spark 1.2 Contributor | Subscription | 12 M |
48.Glm 5.2 | Subscription | 12 M |
49.Nemotron 3 Ultra 550b A55b | API Key | 11 M |
50.Gpt 5.6 Terra | API Key | 11 M |
51.Kimi K3 | API Key | 11 M |
52.Muse Glimmer 30b | API Key | 11 M |
53.Hy3 | Subscription | 10 M |
54.Glm 5.3 | Subscription | 9 M |
55.Nemotron 3 Ultra Free | API Key | 9 M |
56.Deepseek V4 Flash | API Key | 9 M |
57.Mistral Vibe Cli Latest | Subscription | 7 M |
58.Ox Alpha | API Key | 6 M |
59.Openai.Gpt 5.6 Terra | API Key | 6 M |
60.Qwen3.7 Max | Subscription | 6 M |
61.Deepseek V4 Flash 0731 | Subscription | 5 M |
62.Gpt 6 Astra | Subscription | 5 M |
63.Nemotron 3 Super 120b A12b | API Key | 4 M |
64.Mistral Small 2603 | API Key | 4 M |
65.Glm 5.3 Flash | API Key | 4 M |
66.Ministral 14b Latest | API Key | 4 M |
67.Big Pickle | API Key | 3 M |
68.Ling 3.0 Flash VL | API Key | 3 M |
69.Nemotron 3 Ultra 550b A55b | API Key | 3 M |
70.Minimax M3 | API Key | 3 M |
71.O4 Mini | API Key | 2 M |
72.Moonshotai.Kimi K2.5 | API Key | 2 M |
73.Claude Sonnet 5 | Subscription | 2 M |
74.Nemotron 3 Super 120b A12b | API Key | 2 M |
75.Mimo V2.5 | API Key | 2 M |
76.Devstral 2512 | API Key | 2 M |
77.Nemotron 3.5 Lightning | API Key | 2 M |
78.Deepseek Flash | Subscription | 2 M |
79.Mimo V2.5 Free | API Key | 2 M |
80.Claude Opus 5 | Subscription | 1 M |
81.Gpt 4o | Subscription | 1 M |
82.Starcoder2 15b | API Key | 967 K |
83.Deepseek V4 Flash Vision Exp | API Key | 958 K |
84.Gemini 2.5 Flash Lite | API Key | 953 K |
85.Gpt 5.4 | Subscription | 946 K |
86.Laguna Xs 2.1 | API Key | 927 K |
87.Gemini 3.1 Flash Lite Preview | API Key | 882 K |
88.Step 3.7 Flash | API Key | 872 K |
89.Gpt 4o Mini | API Key | 846 K |
90.Gpt Oss 120b | API Key | 634 K |
91.Gemini 2.5 Flash | API Key | 622 K |
92.Gemma 4 31b It | API Key | 545 K |
93.Anthropic.Claude Opus 5 | API Key | 445 K |
94.Solar Pro4 | API Key | 337 K |
95.Deepseek Flash | API Key | 327 K |
96.Mistral Nemotron | API Key | 321 K |
97.Gemini Flash Latest | API Key | 297 K |
98.Kimi For Coding | Subscription | 235 K |
99.Inkling | API Key | 233 K |
100.Qwen.Qwen3 Coder 30b A3b Instruct | API Key | 233 K |
101.Nemotron 3 Nano Omni 30b A3b Reasoning | API Key | 225 K |
102.Mistral Medium 2508 | API Key | 216 K |
103.DeepSeek V4.1 Flash | API Key | 214 K |
104.Grok 4.3 | Subscription | 196 K |
105.Laguna S 2.1 | API Key | 194 K |
106.Glm 5 | Subscription | 194 K |
107.Gemini 3 Flash Preview | API Key | 161 K |
108.MiniMax M2 | API Key | 147 K |
109.Minimax M3 | API Key | 136 K |
110.Qwen3.8 Flash | Subscription | 120 K |
111.Glm 5.1 | Subscription | 116 K |
112.Anthropic.Claude Fable 5 | API Key | 113 K |
113.Minimax M2.5 | Subscription | 109 K |
114.Nemotron 3 Nano Omni 30b A3b Reasoning | API Key | 103 K |
115.MiniMax M2.7 | Subscription | 103 K |
116.Zai.Glm 4.7 Flash | API Key | 103 K |
117.Qwen3.8 27b | API Key | 102 K |
118.X Preview F Free | API Key | 72 K |
119.Deepseek V4.1 Flash | API Key | 69 K |
120.Qwen3.8 Flash | API Key | 63 K |
121.Claude Sonnet 4 6 | API Key | 59 K |
122.Gemini 2.5 Pro | API Key | 35 K |
123.Grok Build 0.1 | Subscription | 32 K |
124.Gemma 4 26b A4b It | API Key | 32 K |
125.Gemma 4 31b It | API Key | 20 K |
126.Nemotron 3.5 Lightning Free | API Key | 18 K |
127.Gemini 3.1 Flash Lite | Subscription | 12 K |
128.Gpt Oss Safeguard 20b | API Key | 12 K |
129.Zai.Glm 5 | API Key | 10 K |
130.Gpt 4o | API Key | 10 K |
131.Openai.Gpt Oss 20b | API Key | 7 K |
132.Qwen.Qwen3 Coder Next | API Key | 6 K |
133.Mistral.Ministral 3 14b Instruct | API Key | 6 K |
134.Nvidia.Nemotron Nano 3 30b | API Key | 6 K |
135.Nvidia.Nemotron Super 3 120b | API Key | 6 K |
136.Gpt Oss 20b | API Key | 2 K |
137.Lfm 2.5 2.6b | API Key | 2 K |
138.Dots 3 Note Preview | API Key | 2 K |
139.Nemotron 3.5 Lightning 30b A3b | API Key | 2 K |
140.North Mini Code | API Key | 1 K |
141.Llama 3.2 11b Vision Instruct | API Key | 1 K |
142.Ling 3.0 Flash Sante | API Key | 1 K |
143.Ling 3.0 Flash Fin | API Key | 1 K |
144.Nemotron 3 Nano 30b A3b | API Key | 985 |
145.Nex N2.5 Pro | API Key | 980 |
146.Qwen3.6 27b | API Key | 942 |
147.Efficient | API Key | 856 |
148.Ling 3.0 Flash Fin Free | API Key | 761 |
149.Laguna Xs 2.1 | API Key | 578 |
150.Llama 3.2 90b Vision Instruct | API Key | 525 |
151.Diffusiongemma 26b A4b It | API Key | 263 |
152.Gemma 4 31b It | API Key | 252 |
153.Gpt 5 Mini | API Key | 184 |
154.Mistral Nemo Minitron 8b 8k Instruct | API Key | 128 |
155.Deepseek V4 Pro 0813 | API Key | 89 |
156.Glm 5.2 | Subscription | 57 |
157.Gpt 4.1 Mini | API Key | 53 |
158.Deepseek V4 Flash Vision Exp | Subscription | 36 |
159.Ling 3.0 Flash Vl | API Key | 27 |
160.Deepseek V3.2 | API Key | 16 |
161.Nex N2.5 Mini | API Key | 16 |
162.Claude Haiku Latest | API Key | 13 |
163.Deepseek V4 Pro | API Key | 11 |
164.Deepseek R1 0528 | API Key | 11 |
165.Deepseek Chat | API Key | 10 |
166.Deepseek Chat V3.1 | API Key | 10 |
167.Deepseek V3.1 Terminus | API Key | 10 |
168.Deepseek V3.2 Exp | API Key | 10 |
169.Deepseek Chat V3 0324 | API Key | 9 |
170.Deepseek R1 | API Key | 9 |
171.Gemini 3.8 Flash | API Key | 3 |
172.Gemini 3.7 Flash | API Key | 2 |