AI model
anthropic/claude-sonnet-4.6:fast-reasoning
Anthropic: Claude Sonnet 4.6 (fast) (Reasoning) is a 1,000,000-token model served on Composite at $3.75 per million tokens in and $18.8 per million tokens out.
Try in Playground| Model ID | anthropic/claude-sonnet-4.6:fast-reasoning |
|---|---|
| Provider | Claude Platform on AWS |
| Context window | 1,000,000 tokens |
| Accepts | text, image, file |
| Returns | text |
| Input price | $3.75 per million tokens |
| Output price | $18.8 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Web search | $0.0125 per result |
| Thinking | Optional - see "Anthropic: Claude Sonnet 4.6 (fast) (Reasoning) (Reasoning)" in the catalog to turn it on by default |
| Moderated | Yes - by the provider |
| Cost on a monthly plan | About 39 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 1 |
Make a Composite API key and type anthropic/claude-sonnet-4.6:fast-reasoning as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
$3.75 per million tokens input · $18.8 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 39 plan credits, at the provider's own price.
Claude Platform on AWS
Claude models are widely regarded for nuanced, in-character writing and for following detailed system prompts and character cards closely.
With a 1,000,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced for quality-sensitive scenes, where writing quality and instruction-following matter more than minimizing per-message cost.
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
Supplied by Claude Platform on AWS, not written by Composite.
Composite Anthropic Router · Anthropic: Claude Opus 5 (Drafted) · Anthropic: Claude Opus 4.8 (Drafted)