Introducing the Universal Managed Agents API.Read the announcement
OpenAI

Providers/OpenAI

OpenAI

Maker of the GPT-5 line and the Codex agent — deep coding models with first-party and open harness support.

Operational
Model LabHarness BuilderFrontier

Models on Brainbase

GPT-5.6

3 variants available3 new

gpt-5.6-solNew
gpt-5.6-terraNew
gpt-5.6-lunaNew

GPT-5

6 variants available

gpt-5.5
gpt-5.4
gpt-5.2
gpt-5
gpt-5-mini
gpt-5-nano

Harnesses by OpenAI

Agent runtimes built by this vendor, managed end-to-end on Brainbase.

Codex
Platform-billed

Codex

codex

OpenAI's Codex CLI in headless mode — structured JSON events and sandboxed execution. Serves GPT models and open-weight models like GLM, DeepSeek, and Kimi with tuned context windows.

Model delivery · Any platform model, per task

About

OpenAI builds the GPT model family and Codex, its agentic coding harness. The Codex-tuned GPT-5 variants are optimized for long tool-use loops, patch-style editing, and repository-scale reasoning.

On Brainbase, GPT models run in OpenAI's own harnesses — the Codex CLI cloud runtime and the portable Codex Agent — and in any open harness. Codex Agent also carries tuned context-window profiles for open-weight models, making it a strong general-purpose harness beyond OpenAI's own models.

Available on Brainbase:

  • GPT-5.6: OpenAI's tri-model generation — Sol, Terra, and Luna — with a million tokens of context, including GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna
  • GPT-5: The GPT-5 line, from the frontier flagships down to mini and nano, including GPT-5.5, GPT-5.4, GPT-5.2, GPT-5, GPT-5 Mini, GPT-5 Nano

Run these models in Codex, OpenCode, or Qwen Code — selected per task like any other platform model.

Try it on Brainbase

One API call boots a managed sandbox on the codex harness pointed at gpt-5.6-sol. Hosting, scaling, and billing are handled for you.

curl -X POST https://api.brainbaselabs.com/v2/agents \
  -H "Authorization: Bearer $BRAINBASE_API_KEY" \
  -d '{
    "title": "my-agent",
    "runtime_kind": "codex",
    "default_model": "gpt-5.6-sol"
  }'
runtime_kind/codexmodel/gpt-5.6-sol