Explore
Recently Added
Newly added models across every lab, live on every Brainbase harness.
@anthropic/claude-opus-5.5Claude Opus 5.5 performs at Fable 5.1 level on most work, leads on agentic coding, and costs about 40% less to run than Opus 5. It is on every Brainbase harness today.
@openai/gpt-6-solOpenAI's two cheaper GPT-6 models: Sol at $2 / $10 for everyday coding and agent work, Luna at $0.10 / $0.50 for high-volume tasks, both at half the price of their GPT-5.6 predecessors and both on every Brainbase harness today.
@spacexai/grok-4.7Grok 4.7 is a larger base model with a longer reinforcement learning run, better at checking its own work and at multi-hour terminal and office tasks, at the same price and speed as Grok 4.6. Now on every Brainbase harness.
@openai/gpt-6-astraGPT-6 Astra is OpenAI's first true long-horizon agent: it leads on terminal, repository, and computer-use benchmarks, works software through the screen, and costs 2.5× its predecessor.
Providers
14Every lab and team behind the models and harnesses on Brainbase — frontier and open-weight, all billed through your platform credits.
Anthropic
10 models · 1 harnessFrontier lab behind the Claude family — the reference models for agentic coding and long-horizon work.
OpenAI
9 models · 1 harnessMaker of the GPT-5 line and the Codex agent — deep coding models with first-party and open harness support.
Gemini — natively multimodal frontier models with massive context windows.
SpaceXAI
3 models · 1 harnessGrok — frontier reasoning models with real-time knowledge — plus Cursor's Composer and headless CLI agent.
Meta
1 modelMuse Spark — the coding-optimized frontier model from Meta Superintelligence Labs, with a million tokens of context.
Thinking Machines
1 modelInkling — the open-weight multimodal model from Mira Murati's Thinking Machines Lab.
Alibaba Qwen
2 harnessesThe Qwen ecosystem — two coding harnesses spanning open-source and vendor-native workflows.
Moonshot AI
2 modelsKimi — open-weight frontier models with standout agentic coding and vision performance.
DeepSeek
1 modelOpen-weight reasoning models that redefined the cost curve for frontier performance.
Zhipu AI
3 modelsGLM — open-weight models with a strong agentic coding pedigree from one of China's leading labs.
Cognition
1 harnessDevin — the autonomous software engineer, running vendor-native on Brainbase.
Factory
1 harnessDroid — the enterprise software-engineering agent, running vendor-native on Brainbase.
OpenCode
1 harnessThe open-source terminal agent from SST — model-agnostic by design.
Brainbase
1 harnessOur in-house harness — the Kafka SDK, built for orchestration, evals, and production agents.