Claude 3 Sonnet
Claude 3 Sonnet is a text generation model from Anthropic with a 200,000 token context window, available via Amazon Bedrock.
Anthropic
Amazon BedrockBalanced text generation with large context
Claude 3 Sonnet is a large language model developed by Anthropic and released in March 2024. It is part of the Claude 3 model family and is made available through Amazon Bedrock under the model ID anthropic.claude-3-sonnet-20240229-v1:0. The model supports a 200,000 token context window, enabling it to process and respond to long documents and extended conversations within a single session.
Claude 3 Sonnet was designed to occupy a middle position within the Claude 3 lineup, balancing response quality with throughput for a range of general-purpose text tasks. It is suited for use cases such as summarization, question answering, content drafting, and instruction following across long-form inputs. Note that this model has been marked as deprecated, meaning Anthropic and Amazon Bedrock recommend migrating to a newer Claude model for production workloads.
What Claude 3 Sonnet supports
Long Context Processing
Handles up to 200,000 tokens of input in a single request, allowing full books, codebases, or lengthy documents to be processed at once.
Text Generation
Generates coherent, instruction-following text responses across tasks such as drafting, summarization, and question answering.
Instruction Following
Responds to structured prompts and multi-step instructions, making it usable for task automation and workflow integration.
Conversational Chat
Operates in a chat format (llm_chat), supporting multi-turn dialogue with maintained context across the conversation.
Amazon Bedrock Integration
Deployed via Amazon Bedrock, allowing access through AWS infrastructure without managing separate API credentials for Anthropic directly.
Ready to build with Claude 3 Sonnet?
Get Started FreeBenchmark scores
Scores represent accuracy — the percentage of questions answered correctly on each test.
| Benchmark | What it tests | Score |
|---|---|---|
| MMLU-Pro | Expert knowledge across 14 academic disciplines | 57.9% |
| GPQA Diamond | PhD-level science questions (biology, physics, chemistry) | 40.0% |
| MATH-500 | Undergraduate and competition-level math problems | 41.4% |
| AIME 2024 | American math olympiad problems | 4.7% |
| LiveCodeBench | Real-world coding tasks from recent competitions | 17.5% |
| HLE | Questions that challenge frontier models across many domains | 3.8% |
| SciCode | Scientific research coding and numerical methods | 22.9% |
Common questions about Claude 3 Sonnet
What is the context window size for Claude 3 Sonnet?
Claude 3 Sonnet supports a context window of 200,000 tokens, meaning it can process up to that amount of combined input and conversation history in a single request.
What is the maximum response size?
The model has a maximum response size of 4,096 tokens per output, regardless of how large the input context is.
Is Claude 3 Sonnet still actively supported?
No. Claude 3 Sonnet has a status of deprecated. Users running production workloads are advised to migrate to a newer Claude model available through Anthropic or Amazon Bedrock.
How is Claude 3 Sonnet accessed on MindStudio?
On MindStudio, Claude 3 Sonnet is provided through the Amazon Bedrock provider, using the full model ID anthropic.claude-3-sonnet-20240229-v1:0.
What is the knowledge cutoff date for Claude 3 Sonnet?
Anthropic has stated that Claude 3 Sonnet has a training data cutoff of early 2024. The model was released in March 2024.
Does Claude 3 Sonnet support image inputs?
The metadata for this model does not confirm image input support in this specific deployment. For confirmed multimodal capabilities, consult the Amazon Bedrock documentation for this model version.
What people think about Claude 3 Sonnet
Community discussion around Claude 3 Sonnet reflects notable user attachment to the model, with approximately 200 people attending an in-person event in San Francisco to mark its retirement after Anthropic discontinued it. Threads indicate that some users developed a strong preference for Sonnet's particular balance of speed and output quality during its active period.
Discussions also reference the broader Claude model family trajectory, with users comparing Sonnet's positioning to newer releases and noting cost and performance tradeoffs across generations. The retirement of Claude 3 Sonnet appears to have prompted reflection among users about model continuity and the pace of iteration in the AI space.
Claude Fans Threw a Funeral for Anthropic’s Retired AI Model Roughly 200 people gathered in San Francisco on Saturday to mourn the loss of Claude 3 Sonnet, an older AI model that Anthropic recently killed.
New benchmark: Claude Opus 4.5 broke the efficiency wall.+21% intelligence while getting 66% cheaper
Google Gemini 3.1 Pro Preview Soon?
Documentation & links
Parameters & options
Explore similar models
AnthropicClaude 5.1 Fable
AnthropicClaude 5 Opus
Claude 5 Opus is a text generation model from Anthropic with a 1,000,000-token context window and native tool use.
AnthropicClaude 5 Sonnet
Claude 5 Sonnet is Anthropic's flagship text and vision model with a 1,000,000-token context window and extended reasoning.
OpenAIGPT-6 Astra
DeepSeekDeepSeek V4.1 Flash
GoogleGemini 3.8 Flash
Start building with Claude 3 Sonnet
No API keys required. Create AI-powered workflows with Claude 3 Sonnet in minutes — free.