LLM Context Window Comparison
Compare context window and maximum output sizes across the latest Claude, GPT, and Gemini models. Enter your document size to see which models can handle it.
≈ 66,500 tokens
| Model | Context window | Fits your doc? |
|---|---|---|
Claude Fable 5 Anthropic | 1M | Yes |
Claude Opus 4.8 Anthropic | 1M | Yes |
Claude Opus 4.7 Anthropic | 1M | Yes |
Claude Sonnet 4.6 Anthropic | 1M | Yes |
Gemini 2.5 Pro Google | 1M | Yes |
Gemini 2.5 Flash Google | 1M | Yes |
Claude Haiku 4.5 Anthropic | 200K | Yes |
o3-mini OpenAI | 200K | Yes |
GPT-4o OpenAI | 128K | Yes |
GPT-4o mini OpenAI | 128K | Yes |
Token estimates assume ~1.33 tokens per English word. Context windows are total input + output. Confirm current limits with each provider.
Choosing a model is step one
Context windows are easy; building the retrieval, prompts, and guardrails around them is the hard part. Yiriba builds the whole system — book a free call.
Book a free call