Signup credit
Free
Initial $10; not recurring
- Included scope
- Metered sandbox evaluation
Epho
● Identity checkedCloud coding agents over HTTP · Official-source review 2026-10-09
Epho runs Claude Code, Codex or OpenCode in cloud sandboxes from an HTTP request. Repositories, input files and MCP tools provide context, with streamed events, asynchronous turns and resumable conversation state.
- Category
- Cloud coding agents over HTTP
- Free access
- Signup includes $10 starting credit. Selected OpenCode free models need no provider key, but sandbox compute is still metered.
- API access
- POST /api/v1/chat and /chat/async, event subscriptions and credits endpoints are documented on the homepage.
Is Epho right for you?
A good fit for
Relevant to developers running reviewed coding-agent tasks from scripts or CI.
Before you choose
CPU $0.0000164/vCPU-second, memory $0.0000053/GiB-second and disk $0.000000036/GiB-second meter boot to teardown. Default 2CPU/2GiB/10GiB is about $0.0026/minute; model fees are separate BYOK. Teams start with five active turns, extra queued, one live turn per chat. Up to 32 repos and twenty input files are advertised. Persistent events/session snapshots qualify the claim nothing is stored: retention and deletion require clarification. Secret handling, fallback recovery and isolation were not independently tested.
Workflow and handoff
Send a public fixture repository without secrets, inspect streamed edits and reported cost and confirm snapshot/event retention before using private source or credentials.
Pricing and practical limits
CPU $0.0000164/vCPU-second, memory $0.0000053/GiB-second and disk $0.000000036/GiB-second meter boot to teardown. Default 2CPU/2GiB/10GiB is about $0.0026/minute; model fees are separate BYOK. Teams start with five active turns, extra queued, one live turn per chat. Up to 32 repos and twenty input files are advertised. Persistent events/session snapshots qualify the claim nothing is stored: retention and deletion require clarification. Secret handling, fallback recovery and isolation were not independently tested.
Review method
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Epho runs Claude Code, Codex or OpenCode in cloud sandboxes from an HTTP request. Repositories, input files and MCP tools provide context, with streamed events, asynchronous turns and resumable conversation state. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | CPU $0.0000164/vCPU-second, memory $0.0000053/GiB-second and disk $0.000000036/GiB-second meter boot to teardown. Default 2CPU/2GiB/10GiB is about $0.0026/minute; model fees are separate BYOK. Teams start with five active turns, extra queued, one live turn per chat. Up to 32 repos and twenty input files are advertised. Persistent events/session snapshots qualify the claim nothing is stored: retention and deletion require clarification. Secret handling, fallback recovery and isolation were not independently tested. | Facts sourced | 2026-10-09 |
Understand the total cost
Epho pricing & plans
Usage-based
Usage-based
Per-second resource billing; model tokens separate
- Included scope
- HTTP agents; streams; async and resumable chats
Alternatives to Epho
View all ↗
Trigger.devTrigger.dev runs TypeScript tasks and durable AI agents with retries, queues, streaming and observability. Its chat-agent workflow supports paused tool approvals and continued execution, while deployments version task code and Realtime exposes run status.
Explore tool
OqoqoOqoqo runs repeated agent experiments on sandboxed cloud machines with chosen tasks, treatments and rubrics. It compares agents, models and tool packages, retaining trajectories, errors, files and pass/fail results for iterative interface improvements.
Explore tool
Pre.devpre.dev is a long-horizon coding agent that plans, builds, and verifies software over extended runs in the browser or terminal. It connects to many SaaS tools, publishes previews, and sells separate RL coding tasks to AI labs through pre.dev Labs.
Explore toolThe practical questions
Frequently asked questions
Was the application hands-on tested?
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
What is Epho used for?
Epho runs Claude Code, Codex or OpenCode in cloud sandboxes from an HTTP request. Repositories, input files and MCP tools provide context, with streamed events, asynchronous turns and resumable conversation state.
Does Epho have a free plan?
Signup includes $10 starting credit. Selected OpenCode free models need no provider key, but sandbox compute is still metered.. This record does not confirm an ongoing free plan.
How much does Epho cost?
Usage-based. See the billing terms below. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Epho through an API?
POST /api/v1/chat and /chat/async, event subscriptions and credits endpoints are documented on the homepage.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
CPU $0.0000164/vCPU-second, memory $0.0000053/GiB-second and disk $0.000000036/GiB-second meter boot to teardown. Default 2CPU/2GiB/10GiB is about $0.0026/minute; model fees are separate BYOK. Teams start with five active turns, extra queued, one live turn per chat. Up to 32 repos and twenty input files are advertised. Persistent events/session snapshots qualify the claim nothing is stored: retention and deletion require clarification. Secret handling, fallback recovery and isolation were not independently tested.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Official product information
Current official product source read individually; product artwork inspected visually.
Read original source ↗Pricing review
Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.