Source URL: https://simonwillison.net/2025/Aug/12/claude-sonnet-4-1m/
Source: Simon Willison’s Weblog
Title: Claude Sonnet 4 now supports 1M tokens of context
Feedly Summary: Claude Sonnet 4 now supports 1M tokens of context
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.
Tags: ai, generative-ai, llms, anthropic, claude, llm-pricing, long-context
AI Summary and Description: Yes
Summary: The text discusses Anthropic’s Claude Sonnet 4, which now supports a context length of 1 million tokens, significantly enhancing its capability compared to previous models. This development is positioned within the competitive landscape of AI models, such as those from Gemini and OpenAI. Additionally, it introduces a pricing structure based on context length, which is a new approach for Anthropic.
Detailed Description:
The information highlights significant advancements in the AI model landscape, particularly regarding context handling and pricing strategies:
– **Model Capabilities**: Anthropic’s Claude Sonnet 4 has extended its context window from 200,000 tokens to 1 million tokens. This is a substantial upgrade that allows for more extensive input and processing capabilities, crucial for tasks requiring more comprehensive data analysis and contextual understanding.
– **Competitive Context**: The shift towards 1 million tokens positions Anthropic more competitively against other major players, such as Gemini and OpenAI, which also offer million-token models. This is an important milestone in the ongoing evolution of Large Language Models (LLMs) where context length can significantly affect performance and utility.
– **Pricing Structure**: For the first time, Anthropic has introduced a tiered pricing model based on context lengths:
– For prompts up to 200,000 tokens, the cost is $3 per million input and $15 per million output.
– For prompts exceeding 200,000 tokens, the cost doubles, reflecting the increased computational requirements.
– This pricing strategy mirrors existing models from competitors like Gemini, indicating a market trend towards varied pricing depending on usage intensity.
– **Access and Beta Users**: The long context support is currently in public beta, specifically targeting “tier 4” users who have invested in API credits. This approach suggests a strategy to attract significant users in enterprise settings who may require enhanced processing power, while gradually rolling out availability.
– **Future Implications**: As support for longer contexts becomes more mainstream, enterprises and developers will need to reconsider how they design applications and workflows that utilize such enhanced capabilities. This might lead to richer, more nuanced developments in AI applications across various domains.
This text is relevant for professionals in AI and related fields, as it emphasizes evolving technologies that influence the capabilities available for machine learning and natural language processing, alongside current trends in pricing and accessibility. Understanding these advancements can help inform strategic decisions in AI implementation and procurement.