Anthropic: Claude Sonnet 5

Claude Sonnet 5 is a text model from Anthropic, listed on api14 as anthropic/claude-sonnet-5. Anthropic describes it as its most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It sits in the text category and was released by the provider on 2026-06-30.

The model accepts text, images, and files as input, and it returns text. Its context window is 1,000,000 tokens, and the maximum output is 128,000 tokens. That combination of a very large context and a large output budget means you can feed in long documents or whole repositories of material and still leave room for a substantial generated response. Anthropic also describes adaptive thinking with selectable reasoning effort levels, including low, medium, high, and max, which lets you trade speed against depth of reasoning per request.

Those capabilities point to a few practical uses. Coding work fits naturally: reading large files or whole projects, explaining code, drafting changes, and driving agent loops that call tools. Because images and files are accepted as input, document-heavy tasks such as summarising reports, extracting structured data from PDFs, or answering questions over a mixed set of attachments are also reasonable. The reasoning effort controls suit agentic and multi-step workflows where you want more deliberate thinking on hard steps and cheaper, faster responses on routine ones. Structured outputs and tool calling make it usable as the reasoning core behind an application rather than only as a chat endpoint.

You call it through api14's OpenAI-compatible API using the model id anthropic/claude-sonnet-5, so existing OpenAI-style clients and SDKs work with a change of base URL and model name. The supported request parameters are include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools, and verbosity. In practice, tools and tool_choice cover function calling, response_format and structured_outputs cover constrained output shapes, and reasoning, reasoning_effort, and include_reasoning control the thinking behaviour. Use max_tokens or max_completion_tokens to cap generation, and stop to end output on given sequences.

Two limits are worth noting when you plan an integration. Output is text only, so if you need generated images or audio, this model is not the right fit. Inputs are text, images, and files, so other modalities on the input side are also out of scope. If your workload is small and simple, the reasoning effort settings let you dial the model down rather than switching away, but for tasks outside text generation you will need a different model.