Anthropic: Claude Sonnet 4.5

Claude Sonnet 4.5 maintains coherent multi-turn conversations with 200K token context windows, enabling it to reason across long documents, codebases, and conversation histories without losing semantic coherence. The model uses transformer-based attention mechanisms optimized for long-range dependencies, allowing developers to pass entire files, API documentation, or conversation threads as context without truncation or summarization.

Claude Sonnet 4.5 generates production-ready code across 40+ programming languages using transformer-based code understanding trained on diverse repositories and coding patterns. The model is specifically optimized for software engineering benchmarks (SWE-bench Verified), meaning it can understand repository structure, generate multi-file changes, and reason about existing codebases to produce contextually appropriate implementations.

Claude Sonnet 4.5 supports streaming responses where tokens are sent to the client as they're generated, enabling real-time display of model output without waiting for the full response. This uses server-sent events (SSE) or WebSocket protocols, allowing developers to build responsive interfaces where users see text appearing in real-time, improving perceived latency and user experience.

Claude Sonnet 4.5 processes images (JPEG, PNG, GIF, WebP formats) up to 20MB and performs visual reasoning including OCR, object detection, diagram interpretation, and visual question answering. The model uses a vision transformer backbone integrated with the language model, allowing it to answer questions about image content, extract text, describe layouts, and reason about visual relationships in a single unified inference pass.

Claude Sonnet 4.5 supports constrained output generation where developers provide a JSON schema and the model generates responses guaranteed to conform to that schema. This uses a combination of token-level constraints and post-generation validation, ensuring that structured data extraction, API response formatting, and database record generation always produce valid, parseable output without requiring post-processing or retry logic.

Claude Sonnet 4.5 supports tool calling via a schema-based function registry where developers define tools as JSON schemas and the model decides when to invoke them with appropriate parameters. The model can chain multiple tool calls in a single response, handle tool results, and reason about which tools to use based on the task. This integrates with OpenRouter's multi-provider abstraction, allowing the same tool definitions to work across different Claude versions or other models.

Claude Sonnet 4.5 supports explicit chain-of-thought prompting where the model generates intermediate reasoning steps before producing final answers. This can be triggered via prompt engineering (e.g., 'Let's think step by step') or via the `thinking` parameter in extended thinking mode, allowing the model to decompose complex problems into smaller reasoning steps, improving accuracy on math, logic, and multi-step reasoning tasks.

Claude Sonnet 4.5 supports batch processing via Anthropic's Batch API, where developers submit multiple requests in a single batch file and receive results asynchronously at a 50% cost discount. The batch system queues requests, processes them during off-peak hours, and returns results via webhook or polling, making it ideal for non-time-sensitive workloads like data processing, content generation, or analysis at scale.

Claude Sonnet 4.5 supports prompt caching where frequently-used context (like system prompts, documents, or code files) is cached on Anthropic's servers and reused across multiple requests. Cached tokens are charged at 10% of standard token cost and retrieved with minimal latency, enabling efficient multi-turn conversations, document analysis workflows, and agent systems that repeatedly reference the same context.

Claude Sonnet 4.5 processes mixed inputs containing text, code, and images in a single unified inference pass, enabling the model to reason across modalities without separate preprocessing or sequential calls. The vision transformer backbone is integrated with the language model, allowing questions about images that reference code, code that references images, and text that ties both together in coherent reasoning.

Claude Sonnet 4.5 is trained using Constitutional AI (CAI) principles, where the model is fine-tuned to follow a set of principles (constitution) that guide safe, helpful, and honest responses. This includes built-in refusal of harmful requests, bias mitigation, and transparency about limitations, without requiring explicit safety prompts or external moderation layers.