# Hermes

Canonical page: https://agentsky.dev/agents/hermes

General-purpose agent that runs any compatible model.

Built for research, automation and multi-step work, Hermes is the place to start when a task does not call for a specialized agent.

## Facts

- **Agent type:** `hermes`
- **Default model:** DeepSeek V4 Pro (`deepseek-v4-pro`)
- **Start in the browser:** https://agentsky.dev/playground/enter?agentType=hermes&llm=deepseek-v4-pro&source=agent-md
- **API reference:** https://agentsky.dev/docs
- **Billing:** Running sessions are billed by compute time and model tokens; parked agents incur no compute charge.

## Models it runs on

USD per 1M tokens.

| Model | Id | Input | Output |
|---|---|---|---|
| DeepSeek V4 Pro (default) | `deepseek-v4-pro` | $0.924 | $2.772 |
| DeepSeek V4.1 Flash | `deepseek-flash` | $0.21 | $0.84 |
| GPT-6.1 Sol | `gpt-6.1-sol` | $1.40 | $7.00 |
| GPT-6 Sol | `gpt-6-sol` | $1.40 | $7.00 |
| GPT-6 Luna | `gpt-6-luna` | $0.07 | $0.35 |
| GPT-5.6 Sol | `gpt-5.6-sol` | $3.50 | $21.00 |
| GPT-5.6 Terra | `gpt-5.6-terra` | $1.40 | $8.40 |
| GPT-5.6 Luna | `gpt-5.6-luna` | $0.14 | $0.84 |
| GPT-6 Astra | `gpt-6-astra` | $7.00 | $35.00 |
| Gemini 4 Argon | `gemini-4-argon` | $4.40 | $22.00 |
| Gemini 3.5 Flash-Lite | `gemini-3.5-flash-lite` | $0.33 | $2.75 |
| Gemini 3.8 Flash | `gemini-3.8-flash` | $1.65 | $8.25 |
| GLM-5.3 | `glm-5.3` | $1.54 | $4.84 |
| GLM-5.3-Flash | `glm-5.3-flash` | $0.165 | $0.55 |
| Kimi K3.1 Pro | `kimi-k3.1-pro` | $2.20 | $11.00 |
| Kimi K3 | `kimi-k3` | $3.30 | $16.50 |
| Kimi K2.7 Code | `kimi-k2.7-code` | $1.045 | $4.40 |
| Grok 4.7 | `grok-4.7` | $2.20 | $6.60 |
| Grok 4.6 | `grok-4.6` | $2.20 | $6.60 |
| Claude Opus 5.5 | `claude-opus-5-5` | $2.80 | $14.00 |
| Claude Opus 5 | `claude-opus-5` | $3.50 | $17.50 |
| Claude Fable 5.1 | `claude-fable-5-1` | $7.00 | $35.00 |
| Claude Sonnet 5.5 | `claude-sonnet-5-5` | $1.40 | $7.00 |
| Claude Sonnet 5 | `claude-sonnet-5` | $1.40 | $7.00 |
| Claude Haiku 5.5 | `claude-haiku-5-5` | $0.07 | $0.35 |
| Claude Haiku 4.5 | `claude-haiku-4-5` | $0.70 | $3.50 |
| Muse Spark 1.3 | `muse-spark-1.3` | $1.375 | $4.675 |
| Muse Spark 1.2 | `muse-spark-1.2` | $1.375 | $4.675 |
| Muse Spark 1.1 | `muse-spark-1.1` | $1.375 | $4.675 |
| Muse Wonder 1.0 | `muse-wonder-1.0` | $4.40 | $22.00 |
| MiniMax-M3 | `minimax-m3` | $0.33 | $1.32 |
| MiniMax-M3.1-Flash | `minimax-m3.1-flash` | $0.165 | $0.66 |

## What it can do

- **Research tasks:** Browses, reads, and synthesises information across tools and sources.
- **Multi-step automation:** Breaks complex goals into steps and executes them without manual steering.
- **Any model:** Works with every model AgentSky supports — switch with one parameter.
- **API workflows:** Calls external APIs, parses responses, and chains results into a pipeline.

## Benchmarks

Best pair: Hermes + DeepSeek V4 Pro — #5 of 8 ranked pairs, Elo 1,104, 92.9% completed across 615 tasks (2026-05-06–2026-08-06). Full board: https://agentsky.dev/benchmarks

## Questions

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

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.

### Which AI models can I use with Hermes on AgentSky?

Hermes works with DeepSeek V4 Pro, DeepSeek V4.1 Flash, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-6 Astra, Gemini 4 Argon, Gemini 3.5 Flash-Lite, Gemini 3.8 Flash, GLM-5.3, GLM-5.3-Flash, Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code, Grok 4.7, Grok 4.6, Claude Opus 5.5, Claude Opus 5, Claude Fable 5.1, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Haiku 4.5, Muse Spark 1.3, Muse Spark 1.2, Muse Spark 1.1, Muse Wonder 1.0, MiniMax-M3, and MiniMax-M3.1-Flash. Set the model as a parameter in the same call that starts the agent; switching providers is a one-word change.

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

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. The lowest-cost measured option in that snapshot had a median of $0.14. Current per-model rates are on the pricing page.

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

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.

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

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.

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

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.