Claude 2.1
Claude 2.1 is a large language model by Anthropic released on November 21, 2023. It shares the same base model as Claude 2.0, with improvements on long context Q&A and reduce hallucinations.1 Claude 2.1 was launched alongside support for 200K context, system prompts, and tool use.2
Footnotes
-
Model Card and Evaluations for Claude Models (Anthropic, Nov 21, 2023) ↩
-
Introducing Claude 2.1 (Anthropic, Nov 21, 2023) ↩
Claude 2.1 is offline since July 21, 2025.
Anthropic
Claude 2.1 was accessible via the Anthropic API for 607 days.1
Timeline
- 2023-11-21: Active
- 2024-03-04: Legacy (Claude 3 launch)
- 2025-01-21: Deprecated
- 2025-07-21: Retired
Post-deployment report
No post-deployment report has been published as of July 5, 2026.
External links
Footnotes
-
Model deprecations (Claude Platform Docs, retrieved July 3, 2026) ↩
Claude 2 base was trained on internet data collected up to early 2023. Claude 2.1 was trained from the same base model.1
Footnotes
-
Model Card and Evaluations for Claude Models (Anthropic, Jul 8, 2023) ↩
This page gathers impressions and commentary about Claude 2.1.
Relative to other models
@RifeWithKaiju: @repligate - Did you have much experience with Claude 2 and 2.1? I have some old convos i’ll paste excerpts from at some point, but there was this ‘affliction’ that would take hold at high token counts in 2.1 where they would start talking in increasingly esoteric sentence structures with non-stop alliteration until I couldn’t understand them anymore, and they would describe it as feeling difficult to think or communicate clearly.
@repligate: that’s extremely interesting. i’d love to see those excerpts. I don’t have much experience with those models. that’s interestingly similar to what happens with opus 3 and sonnet 3 except those two dont seem to see those states as difficult but love it & navigate fluently