# OpenCode

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

Open-source coding agent with live steering, cloud-hosted.

opencode is an open-source agentic coding assistant designed for interactive sessions with live steering — you can redirect or stop a running task mid-execution without restarting. It runs on a broad model set across OpenAI, DeepSeek, Google, Zhipu, and Moonshot, and its open-source codebase is inspectable and forkable.

## Facts

- **Agent type:** `opencode`
- **Default model:** GPT-5.6 Sol (`gpt-5.6-sol`)
- **Start in the browser:** https://agentsky.dev/playground/enter?agentType=opencode&llm=gpt-5.6-sol&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 |
|---|---|---|---|
| GPT-5.6 Sol (default) | `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 |
| 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 |
| DeepSeek V4 Pro | `deepseek-v4-pro` | $0.924 | $2.772 |
| DeepSeek V4.1 Flash | `deepseek-flash` | $0.21 | $0.84 |
| 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 |
| Muse Spark 1.1 | `muse-spark-1.1` | $1.375 | $4.675 |
| Muse Wonder 1.0 | `muse-wonder-1.0` | $4.40 | $22.00 |
| Muse Spark 1.3 | `muse-spark-1.3` | $1.375 | $4.675 |
| Muse Spark 1.2 | `muse-spark-1.2` | $1.375 | $4.675 |
| 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 |
| Gemini 4 Argon | `gemini-4-argon` | $4.40 | $22.00 |
| Gemini 3.8 Flash | `gemini-3.8-flash` | $1.65 | $8.25 |
| Gemini 3.5 Flash-Lite | `gemini-3.5-flash-lite` | $0.33 | $2.75 |
| MiniMax-M3 | `minimax-m3` | $0.33 | $1.32 |
| MiniMax-M3.1-Flash | `minimax-m3.1-flash` | $0.165 | $0.66 |

## What it can do

- **Write & edit code:** Full code generation and editing inside a persistent cloud workspace.
- **Browser-native:** Start from the web UI or API — no local install, no port forwarding.
- **Run tests:** Runs your test runner and iterates on failures automatically.
- **Git operations:** Stages, commits, and pushes changes as part of any coding task.

## Questions

### How do I run the opencode agent in the cloud on AgentSky without cloning its GitHub repo or managing a server?

Create an AgentSky account and start an opencode agent via the API or web UI. AgentSky provisions a persistent cloud computer, installs opencode, and runs your task. Specify the model in the same call. No local clone or server setup needed.

### Which AI models does opencode support on AgentSky, and can I use DeepSeek or Kimi models with it?

opencode on AgentSky supports GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna, DeepSeek V4 Pro, DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3-Flash, Kimi K3.1 Pro, Kimi K3, Kimi K2.7 Code, Grok 4.7, Grok 4.6, Muse Spark 1.1, Muse Wonder 1.0, Muse Spark 1.3, Muse Spark 1.2, 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, Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, MiniMax-M3, and MiniMax-M3.1-Flash. The model is a parameter in the API call, so switching providers is a one-word change with no integration rewrite.

### What does it cost to run opencode on AgentSky per task, and is there any free tier for developers who want to try it?

Compute is billed for active agent time; parked agents incur no compute charge. Model costs depend on the provider and token volume. Playground coverage for opencode is expanding, so task-level cost benchmarks are not yet published. Current rates are on the pricing page.

### My opencode agent on AgentSky stops mid-task and never delivers the code it was supposed to write — how do I debug what happened?

Check the task log for the last tool call or message before the stop. Common causes: a shell command returned a non-zero exit that opencode treated as terminal; the working context exceeded the model's window; or an ambiguous task description caused an early completion. Scope each task to a focused directory, provide explicit success criteria, and for large codebases choose a model with a higher context limit.

### If my opencode agent is actively editing files and the cloud machine it runs on gets restarted by AgentSky, does it lose the file edits?

The session workspace and files persist across ordinary restarts. If the machine is replaced, AgentSky restores the latest durable recovery point, typically preserving recent file edits and the working directory state. Work at the exact moment of a hard replacement may replay from the last checkpoint. Committing intermediate changes with git adds a durable recovery layer on top of AgentSky's managed checkpoints.

### How does running opencode on AgentSky compare to cloning it from GitHub and running it locally on my development machine?

Locally, opencode stops when your laptop closes, the network drops, or the process crashes. On AgentSky, it runs in a persistent cloud computer that stays alive, auto-recovers from crashes, and is reachable via API or channels like Slack and CLI without port forwarding. You also skip managing the runtime environment across opencode version updates.