Claude 3.5 Sonnet: The Model That Rewrote Price-Quality Balance

Updated: 2026-09-02

Claude 3.5 Sonnet (Anthropic, June 2024) proved that first-class quality and competitive pricing are not incompatible in a language model. It delivered performance equivalent to Claude 3 Opus (the flagship of the previous family) at Sonnet pricing and with greater speed. Its clearest strength was coding: HumanEval 92%, real-world code generation better than that of its predecessors, and first-class tool calling. The launch also brought the Artifacts feature to Claude.ai, turning every creative conversation into an independent, editable document.

Note, 2 September 2026: this article describes the launch of Claude 3.5 Sonnet in 2024 and is kept as a historical piece. Anthropic retired both snapshots of the model from the API on 28 October 2025^[1]. The current generation is Claude Fable 5.1, Claude Opus 5, Claude Sonnet 5 and Claude Haiku 4.5 (Anthropic’s model table^[2]). Our most recent Claude coverage: everything that changed in Claude Code over the summer of 2026 and, on the model family, Claude Opus 4.7 and long-horizon tasks.

Key takeaways

• Claude 3.5 Sonnet matched Opus quality at Sonnet prices, reshuffling the third-party LLM market.

• Coding and complex instruction-following are its clearest advantages over GPT-4o.

• The 200 k token context window lets you analyse medium-sized codebases whole in one call.

• Artifacts turns Claude.ai into an iterative workspace for document generation and HTML prototyping.

• Availability on AWS Bedrock and Google Vertex AI eases multi-cloud enterprise integration.

Why it changed the market

Before Claude 3.5 Sonnet, quality state-of-the-art meant Claude 3 Opus: excellent but expensive at $15/$75 per million input/output tokens. GPT-4o competed on price ($5/$15) and won on multimodal features. With 3.5 Sonnet, Anthropic broke that dynamic: Opus-level quality at Sonnet pricing ($3/$15). GPT-4o responded by expanding real-time voice and video; competition intensified for users’ benefit.

The clearest symptom was the immediate adoption by tools like Cursor and Aider, which chose Claude 3.5 Sonnet as the default model before the launch month ended.

Specs and benchmarks

The numbers that matter in practice:

• MMLU: 88.7 (technical tie with GPT-4o).

• HumanEval (coding): 92.0 vs GPT-4o’s 90.2.

• SWE-bench (real GitHub issue fixes): notable advantage.

• GSM8K (mathematical reasoning): 95.0.

• Context window: 200 k tokens.

• Speed: twice as fast as Claude 3 Opus.

• Vision: strong on OCR and diagram analysis.

The honest comparison with GPT-4o: Claude 3.5 Sonnet wins on coding, input cost, and long context; GPT-4o wins on real-time voice, image generation, and plugin ecosystem.

Coding: where the difference is most visible

HumanEval benchmarks measure correct code on standard exercises. SWE-bench measures something harder: resolving real issues in open GitHub repositories, with all the friction of a real codebase. There, Claude 3.5 Sonnet opened a gap that developers noticed before the official numbers arrived.

Three concrete reasons:

• 200 k token window: pass an entire module, its tests, and dependencies in a single prompt without fragmentation.

• Precise tool calls: function calling is deterministic with well-defined schemas, reducing fragile application parsers.

• Complex instructions: follows multi-paragraph specifications without losing the thread or simplifying intermediate requirements.

If your team uses LLM proxies like LiteLLM to manage more than one model in parallel, Claude 3.5 Sonnet was the natural candidate for coding and reasoning routes. Today that role belongs to Claude Sonnet 5 and Claude Opus 5.

Artifacts: Claude.ai as a workspace

Artifacts is a Claude.ai-exclusive feature (not available via the API) that generates code, documents or prototypes in an editable side panel. The typical use cycle:

• Ask for a React component or a Markdown document.

• Claude generates it in the Artifact panel.

• Request refinements ("add unit tests", "trim the CSS").

• For simple HTML/SVG, Claude renders the result directly in the browser.

The difference from ordinary chat is that the artefact persists and can be iterated without losing conversation history. In 2024 it was Anthropic’s closest step yet to an integrated workspace, and pairs well with the Projects feature (which saves reference documents between conversations) for longer tasks.

Availability and access models

• Anthropic API: direct access with the official SDK.

• AWS Bedrock: available, relevant for enterprise stacks.

• Google Vertex AI: available.

• Azure: not available in 2024 (today Claude is offered on Microsoft Foundry).

In October 2024 an updated version arrived, "Claude 3.5 Sonnet (new)", with the experimental Computer Use capability and additional coding improvements. Pricing remained identical, reinforcing the value argument for the Sonnet family.

Usage tips

Four patterns that work well with Claude 3.5 Sonnet:

• XML tags in prompts (<context>, <task>, <constraints>): Claude interprets these precisely and reduces ambiguity.

• Few-shot before the main prompt: two or three examples of the expected format improve output consistency.

• Explicit step-by-step instructions: "first analyse, then propose, finally write the code" works better than asking for everything at once.

• Detailed system prompt: unlike more permissive models, Claude responds well to specific technical roles and respects defined constraints.

For LLM observability tasks (tracing prompts, costs, and quality in production), Claude 3.5 Sonnet integrated well with Langfuse and LangSmith thanks to its OpenAI-compatible API.

Conclusion

Claude 3.5 Sonnet proved that lower pricing does not mean lower quality, and that was enough to force a response across the entire industry. For teams working primarily with text, code, and reasoning, without needing real-time voice or image generation, it was the most balanced model available at launch. The 200 k token window and SWE-bench performance were, through 2024, the hardest arguments to replicate at an equivalent price.

Frequently asked questions

Can I still use Claude 3.5 Sonnet through the API today?

No. Anthropic retired both snapshots of the model from the API on 28 October 2025, so this article stands as a historical account of the June 2024 launch. The current generation is Claude Fable 5.1, Claude Opus 5, Claude Sonnet 5 and Claude Haiku 4.5. The role Claude 3.5 Sonnet used to play in coding and reasoning routes behind an LLM proxy such as LiteLLM now belongs to Claude Sonnet 5 and Claude Opus 5.

How did Claude 3.5 Sonnet compare with GPT-4o on price and coding?

It delivered Opus-level quality at Sonnet pricing, $3 per million input tokens and $15 per million output tokens, against $5/$15 for GPT-4o and $15/$75 for Claude 3 Opus. On MMLU the two were tied at 88.7, but on HumanEval Claude 3.5 Sonnet scored 92.0 versus 90.2 for GPT-4o and it held a notable advantage on SWE-bench. GPT-4o kept the edge on real-time voice, image generation and its plugin ecosystem.

Were Artifacts available through the Claude API?

No: Artifacts was a Claude.ai-exclusive feature that generated code, documents or prototypes in an editable side panel. You asked for a React component or a Markdown document and refined it with follow-up requests. For simple HTML or SVG, the result rendered directly in the browser. The artefact persisted across the conversation without losing history, and it paired well with the Projects feature, which stores reference documents between conversations for longer tasks.

Sources

1. retired both snapshots of the model from the API on 28 October 2025
2. Anthropic’s model table