Model Specifications
2 Active Catalog Models
Model Catalog & Specifications
Flexlora provides curated model aliases that abstract away upstream revision churn. Target stable canonical IDs with predictable context windows, capabilities, and token pricing.
Model Matrix & Token Rates
Interactive Catalog →| Model Identifier | Category | Context Size | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|---|
flexlora:fast | fast | 128k | $0.50 | $1.50 | chat, streaming, vision, code, reasoning, toolCalling |
flexlora:smart | reasoning | 200k | $2.50 | $10.00 | chat, streaming, vision, code, reasoning, toolCalling |
Detailed Model Profiles
fast
fastflexlora:fastCore auto-routed model for conversational interactions, streaming completions, and tool execution.
Input Token Rate:$0.50
Output Token Rate:$1.50
Context Window:128k tokens (128,000)
Max Output:8k tokens
Recommended For:
- Production API Backends
- Cursor & Claude Code
- Live Chatbot UI
- Coding Agents
reasoning
standardflexlora:smartAdvanced reasoning engine with 200k context window for complex logic and repository analysis.
Input Token Rate:$2.50
Output Token Rate:$10.00
Context Window:200k tokens (200,000)
Max Output:16k tokens
Recommended For:
- Complex Refactoring
- Legal & Financial Analysis
- Multi-file diffs