Comparisons

Cerver vs. OpenRouter

A router for requests. A runtime for agents.

"So… OpenRouter?" is the most common reply to the cerver pitch. Same sentence on the surface — one API, any model. Opposite economics underneath.

OpenRouter — routes requests

your app
▼  sends an API request
router · their proxy
▼  picks one model, answers
Harnessnone — bring your own
Model300+ models
Toolstext in, text out
Transcriptnot kept
Computetheir proxy
Billingper-token
$0.0000 every token
metered

Cerver — runs agents

your app
▼  opens a session
runtime · your compute
▼  runs the agent, end to end
Harnessclaude codecodexgrok
Modelanyswap mid-session
Toolsweb searchshellfilesmcp
Transcriptyoursresumable
Computelocalvercelcloudflareaws
Billingsubscriptionapi
$0.00 on plans you already pay
— or bring your API key
the same ask — as a request
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_KEY" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [
      { "role": "user", "content": "Fix the failing test" }
    ]
  }'

# → text describing a fix.
#   applying it, running the tests, retrying — your job.
the same ask — as a session
curl -X POST https://gateway.cerver.ai/v2/sessions \
  -H "Authorization: Bearer $CERVER_API_TOKEN" \
  -d '{
    "session_name": "fix-tests",
    "harness": "claude",
    "compute": { "provider": "local" }
  }'

curl -X POST .../v2/sessions/SESSION_ID/run-llm \
  -H "Authorization: Bearer $CERVER_API_TOKEN" \
  -d '{ "input": "Fix the failing test" }'

# → the agent edits the files, runs the tests,
#   and replies when they pass.

A router picks which model answers a request.
A runtime runs the whole agent — on the compute you choose, billed the way you choose.

✕ can't be done with a router✓ what a session does
claude code codex

Stuck mid-task? The agent asks another agent for a second opinion — full context, like a doctor referring a patient.

edit · test · retry

The loop runs on your machine until the tests actually pass — not a text suggestion you apply yourself.

move machines live

Start on the laptop, finish on the server. The session and its transcript move; the work doesn't restart.

kill · take over

A runaway overnight agent is one API call away from stopped — or from your keyboard.

resume tomorrow

The transcript persists. Pick up Friday's session on Monday with everything it knew.

stay on your network

Private repos, internal APIs, VPN-only services — the agent reaches them because it runs where you run.

Not rivals — different layers that compose. A cerver session can even use OpenRouter as its model backend. The router picks the model; the runtime runs the agent. And if you're paying for Claude Max or Codex today, the cheapest agent fleet you can run is the one that finally uses them.

See a session run on your own machine.

Start an agent, watch the transcript live, move it to another computer mid-task — and pay nothing per token beyond the subscription you already have. Cerver's fee is a flat $2 per 1M tokens.

← All posts