Claude Sonnet 4 now supports 1M tokens of context (via) Gemini and OpenAI both have million token models, so it's good to see Anthropic catching up. This is 5x the previous 200,000 context length limit of the various Claude Sonnet models.
Anthropic have previously made 1 million tokens available to select customers. From the Claude 3 announcement in March 2024:
The Claude 3 family of models will initially offer a 200K context window upon launch. However, all three models are capable of accepting inputs exceeding 1 million tokens and we may make this available to select customers who need enhanced processing power.
This is also the first time I've seen Anthropic use prices that vary depending on context length:
- Prompts ≤ 200K: $3/million input, $15/million output
- Prompts > 200K: $6/million input, $22.50/million output
Gemini have been doing this for a while: Gemini 2.5 Pro is $1.25/$10 below 200,000 tokens and $2.50/$15 above 200,000.
Here's Anthropic's full documentation on the 1m token context window. You need to send a context-1m-2025-08-07
beta header in your request to enable it.
Note that this is currently restricted to "tier 4" users who have purchased at least $400 in API credits:
Long context support for Sonnet 4 is now in public beta on the Anthropic API for customers with Tier 4 and custom rate limits, with broader availability rolling out over the coming weeks.
Recent articles
- LLM 0.27, the annotated release notes: GPT-5 and improved tool calling - 11th August 2025
- Qwen3-4B-Thinking: "This is art - pelicans don't ride bikes!" - 10th August 2025
- My Lethal Trifecta talk at the Bay Area AI Security Meetup - 9th August 2025