# Best LLM API for Hermes Agent, measured

Updated November 07, 2026. Built-in providers checked against Hermes Agent's documentation (https://hermes-agent.nousresearch.com/docs/integrations/providers) on 2026-11-07.

As of November 07, 2026, of the 15 LLM APIs built into Hermes Agent that we measure, OpenRouter answers fastest: 68 ms median time to first byte, averaged over 4 regions. By region, Fireworks AI is fastest from Europe (16 ms), US Central (29 ms) and Tokyo (19 ms), OpenRouter from São Paulo (62 ms). 4 of 15 hosts answered every probe over the 90 days since 2026-08-09; the lowest was OpenAI API (direct) at 99.1%.

Median time to first byte (24 h) per region, host uptime over 90 days since 2026-08-09, outages attributed to the provider in the last 30 days (host, and real requests to one model where we hold a key). Measured at the exact host Hermes Agent calls, directly.

| Provider | Id | Host | Europe | US Central | Tokyo | São Paulo | Host uptime 90 d | Outages 30 d |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| OpenRouter | `openrouter` | openrouter.ai | 98 ms | 59 ms | 54 ms | 62 ms | 100% | 0 |
| Fireworks AI | `fireworks` | api.fireworks.ai | 16 ms | 29 ms | 19 ms | 254 ms | 100% | 0 |
| Google / Gemini | `gemini` | generativelanguage.googleapis.com | 90 ms | 41 ms | 63 ms | 137 ms | 100% | 119 requests to gemini-flash-lite-latest |
| Anthropic | `anthropic` | api.anthropic.com | 197 ms | 95 ms | 227 ms | 194 ms | 100% | 0 |
| NovitaAI | `novita` | api.novita.ai | 231 ms | 93 ms | 147 ms | 247 ms | 99.9% | 0 |
| xAI (Grok) | `xai` | api.x.ai | 221 ms | 110 ms | 165 ms | 224 ms | 99.9% | 0 |
| OpenAI API (direct) | `openai-api` | api.openai.com | 215 ms | 139 ms | 208 ms | 244 ms | 99.1% | 0 |
| Kimi / Moonshot | `kimi-coding` | api.moonshot.ai | 309 ms | 266 ms | 130 ms | 341 ms | 99.9% | 0 |
| Nebius Token Factory | `nebius-token-factory` | api.tokenfactory.nebius.com | 33 ms | 181 ms | 466 ms | 377 ms | 99.9% | 1 host |
| z.ai / GLM | `zai` | api.z.ai | 184 ms | 252 ms | 94 ms | 541 ms | 99.9% | 1 host |
| DeepSeek | `deepseek` | api.deepseek.com | 290 ms | 317 ms | 183 ms | 432 ms | 99.9% | 0 |
| MiniMax China | `minimax-cn` | api.minimaxi.com (China endpoint; the global `minimax` provider calls api.minimax.io, not measured) | 312 ms | 343 ms | 223 ms | 478 ms | 99.9% | 0 |
| Upstage | `upstage` | api.upstage.ai | 586 ms | 355 ms | 59 ms | 616 ms | 99.9% | 0 |
| Qwen Cloud (Alibaba DashScope) | `alibaba` | dashscope-intl.aliyuncs.com | 358 ms | 415 ms | 167 ms | 706 ms | 99.9% | 0 |
| StepFun | `stepfun` | api.stepfun.com (China endpoint) | 429 ms | 392 ms | 325 ms | 673 ms | 99.7% | 2 host |

Not shown — the agent calls a host we do not measure:

- Tencent TokenHub: Hermes Agent calls tokenhub.tencentmaas.com, our probe measures api.hunyuan.cloud.tencent.com, the Tencent Hunyuan API, shut down on September 30, 2026 (https://hermes-agent.nousresearch.com/docs/reference/environment-variables)

Any other OpenAI-compatible API: the `Custom endpoint` option in `hermes model` (https://hermes-agent.nousresearch.com/docs/integrations/providers).

## What is the best LLM API for Hermes Agent?

It depends on what the agent waits for and where it runs. On measured speed, as of November 07, 2026 the fastest of the 15 built-in APIs we probe is OpenRouter at 68 ms median time to first byte across 4 regions; by region, Fireworks AI is fastest from Europe (16 ms), US Central (29 ms) and Tokyo (19 ms), OpenRouter from São Paulo (62 ms). On reliability, 4 of 15 hosts answered every probe over the last 90 days. Model quality and price are separate questions this measurement does not answer.

## Which LLM providers does Hermes Agent support out of the box?

Hermes Agent's documentation lists built-in providers; 15 of them are measured here at the exact host Hermes Agent calls: OpenRouter, Fireworks AI, Google / Gemini, Anthropic, NovitaAI, xAI (Grok), OpenAI API (direct), Kimi / Moonshot, Nebius Token Factory, z.ai / GLM, DeepSeek, MiniMax China, Upstage, Qwen Cloud (Alibaba DashScope), StepFun. Any other OpenAI-compatible API can be added as the Custom endpoint option in hermes model.

## Is there a free LLM API for Hermes Agent?

Yes, with limits. Google / Gemini: free input and output tokens on a limited set of Gemini models (rate-limited; content sent on the free tier is used to improve Google's products; apps for users in the EEA, Switzerland or the UK must use paid services (terms: https://aistudio.google.com/docs/terms)). OpenRouter: model variants whose ID ends in :free (20 requests a minute; 50 a day, or 1,000 a day once you have bought at least 10 credits). z.ai / GLM: GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash: input and output both free (rate limits not published in the docs; the other GLM models are paid). NovitaAI: one model priced at $0 for input and output: Apodex 1.1 Mini (rate limits and how long it stays free are not stated). All are built into Hermes Agent; terms checked 2026-11-07 on each provider's own page, full list at https://llmlatency.dev/free-llm-api.

## Does the VPS region matter for Hermes Agent?

For some APIs a lot. Upstage answers in 59 ms from Tokyo and 616 ms from São Paulo, and every model call waits at least that long before the model starts. Put the agent where the API you use is fastest.

Source: https://llmlatency.dev/self-hosted-agents/hermes-agent · CC BY 4.0