Use Obscurify.ai as a model provider in Hermes Agent

Hermes Agent talks to any OpenAI-compatible API, so you can add Obscurify.ai as a named provider in its config. You get 200+ models through one key and an account number instead of an email.

Tested on 2026-10-31 with Hermes Agent v0.22.5 against the live API, including an agent turn that wrote a file through a tool.

Before you start

You need:

Hermes Agent: follow its install guide.
An Obscurify.ai API key. Create an account, add credit on the account page, then click Show API Key. New accounts may get $1 of starter credit while this month’s promo budget lasts.

Save the key in Hermes’s secrets file. It starts with sk-obs1_:

echo 'OBSCURIFY_API_KEY=sk-obs1_...' >> ~/.hermes/.env

Add the provider

Put this in ~/.hermes/config.yaml. If you already have a model: or providers: section, merge it in:

model:
  provider: obscurify
  default: deepseek/deepseek-v4-flash
providers:
  obscurify:
    name: Obscurify.ai
    api: https://obscurify.ai/v1
    key_env: OBSCURIFY_API_KEY
    transport: chat_completions
    default_model: deepseek/deepseek-v4-flash

Try it

hermes -z "Reply with exactly: ok"

Then give it something that needs a tool:

hermes -z "Create a file named hello.txt in the current directory containing exactly: obscurify works. Then reply DONE." --yolo

--yolo skips the approval prompts, so use it only for a test like this one. Leave it off in normal use.

Use other models

Change default under model. The full list is at /v1/models, with prices on the model list. IDs keep their prefix, as in z-ai/glm-5.3. Good starting points are deepseek/deepseek-v4-flash, z-ai/glm-5.3, moonshotai/kimi-k2-0905 and qwen/qwen3-coder.

Hermes needs a model with at least 64K of context.

Or install the plugin

The plugin from the Hermes plugin catalog adds Obscurify.ai to hermes model, with the whole model list and each model’s context window:

hermes plugins install obscurify-provider
hermes plugins enable obscurify-provider
hermes -z "Reply with exactly: ok" --provider obscurify -m deepseek/deepseek-v4-flash

What it costs

Each request is charged from your balance at the model’s price. Agents use far more tokens than chat, because each step resends the system prompt, tools and history: small tasks in our tests averaged about 20,000 tokens. Pay As You Go stops at 1M tokens a month, Casual at 10M, and Pro has no limit. See pricing.

If something fails

402: there’s no balance on the account. Add credit on the account page.
403: your plan doesn’t include that model. Frontier models need Casual or Pro, and uncensored models need Pro.
404 model_not_found: check the ID against /v1/models, and keep its prefix.
429: you’re going too fast, or you’ve hit the plan’s monthly token limit.

What stays private

Prompts and responses aren’t stored on Obscurify.ai’s servers, and text requests only use zero-data-retention routes, which rely on providers’ published policies. Providers don’t see who sent a prompt, but they do see its text, and that includes any files your agent reads and sends. Details are in the privacy policy.

More agents: Obscurify.ai for agents.