Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | Moonlight 16B A3B Instructmoonlight-16b-a3b-instruct | Claude Fable 5.1claude-fable-5.1 | Gemini 3.8 Flashgemini-3.8-flash |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $10.00 / 1M | $0.75 / 1M |
| Output | $0 / 1M | $50.00 / 1M | $3.75 / 1M |
| Cache Write (5m) | $0.00 / 1M | $12.50 / 1M | $0.75 / 1M |
| Cache Write (1h) | $0.00 / 1M | $20.00 / 1M | $0.75 / 1M |
| Cache Read | $0.00 / 1M | $1.00 / 1M | $0.75 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 8.2K | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | No | Yes | Yes |
| Function Calling | No | Yes | Yes |
| JSON Mode | No | Yes | Yes |
| Streaming | No | Yes | Yes |
| Catalogue | |||
| Provider | Moonshot AI | Anthropic | |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | — | Claude Fable 5.1 is an upgraded version of Fable 5, delivering broad improvements with particularly strong gains in agentic coding, long-running workflows, and professional knowledge work. It excels at large code refactors, front-end and visual code generation, financial analysis, and complex analytical tasks. Compared with Fable 5, it also produces more concise plans and summaries while maintaining strong performance across extended tasks, making it a natural upgrade for existing Fable workflows and a strong option alongside Opus 5 for reasoning-intensive applications. | Gemini 3.8 Flash is Google's most intelligent Flash-class model, delivering significant improvements over Gemini 3.7 Flash across software engineering, agentic workflows, and complex multi-step reasoning. Designed to combine strong capability with Flash-tier efficiency, it is well suited for coding assistants, autonomous agents, and high-throughput production workflows that require responsive performance without sacrificing reasoning quality. |