Bol.ai vs modelparams.dev

Stop retyping Bills of Lading. Upload a BOL as PDF, scan or photo and get structured data in seconds, parties, ports, containers, weights. JSON, CSV & API.

modelparams.dev is the open catalog of LLM API parameters. Compare temperature, top_p, max_tokens and every other knob across 403 models from 22 providers.

About Bol.ai

Stop retyping Bills of Lading. Upload a BOL as PDF, scan or photo and get structured data in seconds, parties, ports, containers, weights. JSON, CSV & API. The Bill of Lading is our specialty, and we read the documents that travel with it. Built for the daily reality of freight forwarders and customs brokers: stacks of carrier BOLs that someone has to key into the system. Every container number is checked against its ISO 6346 check digit, dates and weights against plausibility rules, suspect fields are flagged, never silently wrong.

About modelparams.dev

modelparams.dev is the open catalog of LLM API parameters. Compare temperature, top_p, max_tokens and every other knob across 403 models from 22 providers. Maximum number of output tokens the model may generate. Lower values make outputs more focused; higher values make them more varied. Converse carries it through additionalModelRequestFields; it is not part of inferenceConfig. Bedrock rejects the adaptive mode the first-party Anthropic API accepts, so only disabled and enabled are listed here. Maximum token budget the model may use for extended thinking before producing the final answer.