Skip to main content
Astrolabe Cloud exposes stable virtual model IDs while the hosted roster can evolve behind the gateway. Use virtual models for most traffic. Request a concrete model only when you want to bypass virtual lane selection while still keeping Cloud auth, billing, stack policy, and traces.

​
Virtual models

ModelPurpose
astrolabe/autoDefault route for general AI API requests.
astrolabe/codingCode generation, patching, repo work, and agent execution traces.
astrolabe/researchLong-context synthesis, source-heavy research, and deep reasoning.
astrolabe/visionScreenshots, documents, image-grounded reasoning, and multimodal tasks.
astrolabe/strict-jsonStructured output and schema recovery.
astrolabe/cheapLow-risk, high-efficiency turns.
astrolabe/safeHigh-stakes routes with conservative premium defaults.
Short aliases such as auto, coding, and cheap normalize to their astrolabe/... model IDs.

​
Active hosted roster

Astrolabe Cloud maintains a hosted pricing catalog. The current public serving roster includes:
Model IDRole
deepseek/deepseek-v4-proWorkhorse for auto, coding, and research.
minimax/minimax-m2.7Conservative workhorse and safety fallback.
xiaomi/mimo-v2.5-proCoding and research specialist.
qwen/qwen3.6-plusLong-context research and vision candidate.
moonshotai/kimi-k2.6Multimodal and visual coding specialist.
anthropic/claude-sonnet-4.6Safe-lane default and premium escalation.
z-ai/glm-5.1Strict JSON and schema repair specialist.
deepseek/deepseek-v4-flashLow-cost coding and structured-output fallback.
mistralai/mistral-small-2603Value multimodal fallback.
x-ai/grok-4.1-fastLow-cost long-context and tool-capable model.
x-ai/grok-4.3Premium research and agentic candidate.
openai/gpt-5.4Premium verifier or executor.
anthropic/claude-opus-4.7Safe-lane escalation.
openai/gpt-5.5Frontier escalation.
google/gemma-4-31b-itCheap multimodal generalist.
openai/gpt-5.4-nanoControl-plane, router, and structured-output model.
openai/gpt-5.4-miniMid-premium structured and safe-lane option.

​
Pricing

Retail prices are returned by GET /v1/models and reflected in the Cloud app pricing views. Billing uses provider-confirmed usage where available. Routing model costs are internal to Astrolabe. Customer debits are based on serving or fallback model usage that is billable.

​
Choosing models

Use:
  • astrolabe/auto for most traffic
  • astrolabe/coding for code editing and tool loops
  • astrolabe/research for synthesis and long-context analysis
  • astrolabe/vision for visual or document-grounded requests
  • astrolabe/strict-json for schema-sensitive requests
  • astrolabe/cheap for low-risk volume
  • astrolabe/safe for sensitive or high-stakes flows
Use routing stacks to further constrain providers, models, cost mode, quality target, and verification.