Enter a document size in any unit. Compare stated context capacity, a conservative working zone, and illustrative response time across the included models.
Runs entirely in your browser. No signup.
Stated context windows are technical ceilings. Real reliability degrades past ~50% of the window (Chroma “Context Rot” research). The reliable working zone is shaded.
Every number this tool shows, and where it comes from.
Context windows. Sourced from vendor documentation: Anthropic, OpenAI, Google AI for Developers, Together AI, DeepSeek API.
Reliable working zone. 50% of the stated window, based on Chroma Research’s “Context Rot” findings (2025) and the broader long-context-degradation literature. Some models hold reliability further; we err conservative.
Token conversion. ~4 chars/token, ~0.75 words/token, ~500 tokens per page of typical English prose, ~250 tokens per KB. These are averages; technical writing and code can run 30-40% denser.
Latency assumptions. TTFT and tokens-per-second are illustrative defaults derived from public benchmarks and our own measurements. Real-world latency depends on region, traffic, and prompt size. Always validate against your own region under your own load.
Cache hit reduction. Warm-cache TTFT is approximated as ~70% of cold TTFT. Anthropic and OpenAI both ship faster TTFT on cache hits, with the exact ratio depending on prompt structure.
Model set last verified 2026-05-06.
The rest of the toolkit runs in your browser too.
Open Orbit to keep model choice, cost, approvals, and run history together.
500 trial credits. Card required. $0 charged today.