Session. Super simple. Super flexible.

You do what the hell you want with it.

Careful.

See what this means ↓
Now, let's nerd out.

Session Infrastructure.

At its simplest, cerver gives every user in your AI app a session — persistent, queryable, theirs. The model writing it and the compute running it are config; switch either one anytime, or run several in parallel on the same intent and curate the winner. One API.

$ curl -X POST https://gateway.cerver.ai/v2/sessions \
    -H "Authorization: Bearer $CERVER_API_TOKEN"
→ { "session_id": "sess_a4f7c9...", "status": "ready" }
$ ▌

Free at hobby scale. Free for the agents you build on it.

sess_a4f7c9… stays
refactor this auth flow
reading auth.py · 240 lines
✓ split into middleware.py + routes.py
now add tests
all of these can drive the session
model + CLI
Opus · Claude Code Sonnet · Claude Code Haiku · Claude Code GPT-5 · Codex CLI GPT-5 · OpenAI SDK Grok · xAI CLI Gemini · Google CLI Llama · open SDK
compute
E2B sandbox Vercel sandbox Cloudflare Workers local relay Modal Replicate Beam Cloud Daytona
— same id, same transcript, swappable underneath
Inside a session

Every layer. Yours to swap.

A session isn't just the chat. It's the chat plus the model writing it plus the compute running it plus the row in your database. Cerver gives you all four as one object — and each one is config you can change without breaking the others.

chat
user ↔ agent transcript, persisted
↓ runs on
model + tools
Claude Opus · Claude Code
↓ executes on
compute
E2B sandbox · Vercel · your Mac
↓ persists to
database
one row · queryable forever
The API surface

One API.

Cerver gives you one interface for creating, running, switching, measuring, and closing AI sessions. But a good session layer should not only be reliable.

session apione interface
POST /v2/sessions
POST /v2/sessions/:id/run-llm
POST /v2/sessions/:id/compute
GET  /v2/sessions/:id/metrics
POST /v2/sessions/:id/close
Powerful sessions

Reliable is the baseline. Powerful is the point.

Cerver sessions are stable, transparent, and hard to accidentally break. They keep memory, tools, compute, billing, recovery, and user state together while your AI stack changes underneath. And they do more than hold state: they can switch models, move compute, track cost, recover runs, and spawn other sessions.

Start free → Explore Cerver sessions
powerful session reliable core
switchmodels and compute
spawnparallel sessions
measurecost and latency
Create five versions with five intelligence layers.
Compare the outputs. Keep the best one. Same session record, clear cost trail.