Anthropic: Claude Sonnet 5 (batch)

Claude Sonnet 5 (batch) is Anthropic's batch-priced listing, accepting text, image, and file inputs. It offers a 1,000,000-token context window and can return up to 128,000 tokens per completion, which suits long documents, large codebases, or multi-file inputs processed in one request. It supports tool use and reasoning; structured output support is not specified in the available data, so confirm it before relying on schema-constrained responses. At $1 per million input tokens and $5 per million output tokens, this model belongs on the shortlist for teams running high-volume, non-interactive workloads where cost per token matters. Its blended benchmark score of 91.4 rests on only three independent benchmarks, so treat it as promising rather than settled. Within that set, it scores 100 on the AI Index coding measure and 88 on the overall index, while its 77 on the agentic measure is noticeably weaker. That profile favors coding-heavy pipelines over autonomous multi-step agent work.