Model
Claude 2.1
Claude 2.1, released on 21 November 2023, doubled the context window to 200,000 tokens and cut false statements by half compared with Claude 2.0. It added tool use and system prompts.
Status DeprecatedModality TextContext (K tokens) 200 Era Generative AI for everyone
- License
- Proprietary
- Access
- API, App
- Release date
- Developer
- Anthropic
What it is
Claude 2.1 was released on 21 November 2023. It was available through Anthropic's API, in the developer console, and as the model behind claude.ai for both free and Pro users.[1]
Longer context
Claude 2.1 doubled the context window to 200,000 tokens. That is about 150,000 words, or more than 500 pages. In claude.ai, the full 200K window was reserved for Claude Pro users.[1]
The context window is the amount of text the model can consider at once, in a single conversation or request. A longer window means a user can paste in a whole report or a long contract and ask questions about it.
Fewer errors
Anthropic reported a 2x decrease in false statements compared with Claude 2.0. The model was more likely to admit uncertainty than to give a wrong answer.[1]
On document comprehension, Anthropic reported a 30% reduction in incorrect answers. It also reported that the model was 3 to 4 times less likely to wrongly conclude that a document supports a claim.[1]
New developer features
Claude 2.1 introduced tool use as an early beta API feature. Tool use lets Claude call functions that developers define, along with web search and private knowledge bases.[1]
It also added system prompts. A system prompt is a set of instructions given before the conversation begins, and users could use it to set Claude's role, personality and response structure.[1]
Anthropic launched the Workbench alongside the model. Workbench is a console playground for trying out and refining prompts, and it can generate SDK code snippets. Anthropic also updated its API pricing at the same time to improve cost efficiency across models.[1]
Place in the story
The Claude 3 family succeeded Claude 2.1 on 4 March 2024.[3] Anthropic announced the deprecation of claude-2.1 on 21 January 2025, and it was retired on 21 July 2025.[2]
Version history
20-
2023
-
Mar 14, 2023
Claude (March 2023)
Claude is the AI assistant Anthropic announced on 14 March 2023, its first publicly available assistant. It was built around training AI to be helpful, honest and harmless, and it started the Claude model line.
-
Jul 11, 2023
Claude 2
Claude 2 is the second major version of Anthropic's assistant model, released on 11 July 2023 with better performance and longer responses. It was the first Claude model open to the general public.
-
Nov 21, 2023
Claude 2.1 · This page
Claude 2.1, released on 21 November 2023, doubled the context window to 200,000 tokens and cut false statements by half compared with Claude 2.0. It added tool use and system prompts.
-
Mar 14, 2023
Claude (March 2023)
-
2024
-
Mar 4, 2024
Claude 3 Opus
Claude 3 Opus, announced on 4 March 2024, was the most capable model in the Claude 3 family. It added vision and launched with a 200K-token context window and a Needle In A Haystack recall above 99%.
-
Mar 4, 2024
Claude 3 Sonnet
Claude 3 Sonnet was the middle model of Anthropic's Claude 3 family, announced on 4 March 2024. It powered the free tier of claude.ai, offered a 200K-token context window, and was retired on 21 July 2025.
-
Jun 20, 2024
Claude 3.5 Sonnet
Claude 3.5 Sonnet, released on 20 June 2024, was the first model of the Claude 3.5 family. It ran twice as fast as Claude 3 Opus at the mid-tier price and powered the new Artifacts and Projects features.
-
Oct 22, 2024
Claude 3.5 Sonnet (October 2024 upgrade)
The upgraded Claude 3.5 Sonnet, announced on 22 October 2024, raised coding and agentic scores and introduced computer use in public beta, the first such offer from a frontier AI model.
-
Mar 4, 2024
Claude 3 Opus
-
2025
-
Feb 24, 2025
Claude 3.7 Sonnet
Claude 3.7 Sonnet, released on 24 February 2025, was described by Anthropic as the first hybrid reasoning model on the market, able to answer quickly or think step by step at length. It launched with Claude Code.
-
May 22, 2025
Claude 4 (Claude Opus 4 and Claude Sonnet 4)
Claude Opus 4 and Claude Sonnet 4, announced on 22 May 2025, were hybrid models with extended thinking. Anthropic called Opus 4 the best coding model in the world, and Claude Code became generally available the same day.
-
Aug 5, 2025
Claude Opus 4.1
Claude Opus 4.1, released on 5 August 2025, upgraded Claude Opus 4 for agentic tasks, real-world coding and reasoning, at the same price. Anthropic later succeeded it with Claude Opus 4.5.
-
Sep 29, 2025
Claude Sonnet 4.5
Claude Sonnet 4.5, released on 29 September 2025, was a drop-in replacement for Sonnet 4 at the same price. Anthropic reported that it could stay focused on complex tasks for more than 30 hours.
-
Nov 24, 2025
Claude Opus 4.5
Claude Opus 4.5, released on 24 November 2025, cost a third as much as Opus 4.1 per token and introduced an effort parameter that lets developers trade capability for time and cost. Claude Opus 4.6 succeeded it.
-
Feb 24, 2025
Claude 3.7 Sonnet
-
2026
-
Feb 5, 2026
Claude Opus 4.6
Released on 5 February 2026, Claude Opus 4.6 was an upgrade to Anthropic's smartest model. It was the first Opus-class model with a 1M-token context window, in beta at launch, and it introduced agent teams in Claude Code.
-
Feb 17, 2026
Claude Sonnet 4.6
Released on 17 February 2026 with a 1M-token context window in beta, Claude Sonnet 4.6 kept the price of Sonnet 4.5 and became the default model for Free and Pro users on claude.ai.
-
Apr 16, 2026
Claude Opus 4.7
Released on 16 April 2026 at the same price as Opus 4.6, Claude Opus 4.7 added an xhigh effort level and accepted much larger images. It was the first model to test automatic blocking of high-risk cybersecurity requests.
-
May 28, 2026
Claude Opus 4.8
Released on 28 May 2026 at the same price as Opus 4.7, Claude Opus 4.8 added a fast mode at 2.5 times the speed, with fewer unnoticed flaws in its own code. Anthropic called it a modest but tangible improvement.
-
Jun 30, 2026
Claude Sonnet 5
Claude Sonnet 5, released on 30 June 2026, is Anthropic's most agentic Sonnet model. It can make plans, use browsers and terminals, and run autonomously, at an introductory price of $2 and $10 per million tokens.
-
Jul 24, 2026
Claude Opus 5
Claude Opus 5, released on 24 July 2026 at $5 and $25 per million tokens, is Anthropic's most aligned model to date and its most capable generally available model for scientific research.
-
Sep 22, 2026
Claude Opus 5.5
Claude Opus 5.5, released on 22 September 2026, is the first model in Anthropic's Claude 5.5 family. Anthropic said it performs at the level of Fable 5.1 on most work, at about 40% lower cost than Opus 5.
-
Sep 28, 2026
Claude Sonnet 5.5
Claude Sonnet 5.5, released on 28 September 2026, is the second model in the Claude 5.5 family and Anthropic's fastest Sonnet to date. It costs $2 and $10 per million tokens, with cache reads halved in October 2026.
-
Feb 5, 2026
Claude Opus 4.6
20231
-
ReleaseAnthropic releases Claude 2.1 with a 200K context window
On 21 November 2023 Anthropic released Claude 2.1, doubling the context window to 200,000 tokens. It also added a beta tool use feature and system prompts for setting Claude's role and style.
Developed by1
Succeeded by2
Successor of1
Powers1
Notes and sources
- Introducing Claude 2.1https://www.anthropic.com/news/claude-2-1
- Model deprecationshttps://platform.claude.com/docs/en/about-claude/model-deprecations
- Claude (language model)https://en.wikipedia.org/wiki/Claude_(language_model)
Cite this page: Claude 2.1. TellWorld, https://www.tellworld.net/models/claude-2-1. Updated 2026-11-08