Question 1

How do I run Hermes in the cloud on AgentSky without managing my own server, container, or runtime environment?

Accepted Answer

Create an AgentSky account and start a Hermes agent via the API or web UI. No server setup is required: AgentSky provisions a persistent cloud computer, installs the harness, and executes your task. Pass the task and model in the same API call.

Question 2

Which AI models can I use with Hermes on AgentSky?

Accepted Answer

Hermes works with DeepSeek V4 Pro, DeepSeek V4 Flash, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, Gemini 3.8 Flash, GLM-5.3, GLM-5.3-Flash, Kimi K3, Kimi K2.7 Code, and the Claude family — Claude Opus 5, Claude Fable 5.1, Claude Sonnet 5, and Claude Haiku 4.5. Set the model as a parameter in the same call that starts the agent; switching providers is a one-word change.

Question 3

What does it cost to run Hermes on AgentSky per task, and how is it billed?

Accepted Answer

A parked Hermes agent incurs no compute charge. In the Playground, Hermes with DeepSeek V4 Pro ran 615 tasks at a median cost of $0.53 and a 90th-percentile cost of $1.79. DeepSeek V4 Flash is the lowest-cost option at a median of $0.14. Current per-model rates are on the pricing page.

Question 4

My Hermes agent keeps stopping in the middle of a long task before it finishes — what should I check first?

Accepted Answer

Long tasks can exceed the model's context window, causing the agent to stop mid-task. Check the task log for the exact step where it halted and the model limit that was reached. Breaking large tasks into scoped subtasks is the most reliable fix. Hermes on AgentSky auto-recovers from crashes, so an abrupt stop is almost always a context or model-limit issue, not a platform failure.

Question 5

If the machine running my Hermes agent is restarted or replaced by AgentSky, does it lose progress on my task?

Accepted Answer

The session workspace and supported message history persist across ordinary pauses and restarts. If the underlying machine is replaced, AgentSky restores the latest durable recovery point. This is managed recovery, not a zero-loss guarantee — work in progress at the exact moment of a hard replacement may replay from the last checkpoint rather than resume mid-step.

Question 6

How does running Hermes on AgentSky compare to running it locally on my own laptop or development machine?

Accepted Answer

Locally, Hermes stops when your laptop closes, the network drops, or the process crashes. On AgentSky, it runs in a persistent cloud computer that stays alive regardless of your laptop's state, auto-recovers from crashes, and is reachable via API or channels like Slack, Telegram, and CLI without port forwarding.

Model	Input	Output
DeepSeek V4 ProDefault	$1.32	$3.96
DeepSeek V4.1 Flash	$0.30	$1.20
GPT-5.6 Sol	$5.00	$30.00
GPT-5.6 Terra	$2.00	$12.00
GPT-5.6 Luna	$0.20	$1.20
GPT-6 Astra	$10.00	$50.00
Gemini 3.8 Flash	$1.50	$7.50
GLM-5.3	$1.40	$4.40
GLM-5.3-Flash	$0.15	$0.50
Kimi K3	$3.00	$15.00
Kimi K2.7 Code	$0.95	$4.00
Grok 4.6	$2.00	$6.00
Claude Opus 5	$5.00	$25.00
Claude Fable 5.1	$10.00	$50.00
Claude Sonnet 5	$2.00	$10.00
Claude Haiku 4.5	$1.00	$5.00

Hermes

Bring your local setup ↗

Models it runs on

What Hermes can do

Research tasks

Multi-step automation

Any model

API workflows

Up and running in minutes.

Agent + model guides

Use Hermes where your team already talks.

Give Hermes the capability a task needs.

Give Hermes access to the apps a task needs.

Questions about Hermes on AgentSky.

Run Hermes in the cloud.