{"slug":"api-vextorium-com-v1-llm-token-count-825fa6","title":"Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100","host":"api.vextorium.com","method":"POST","resource":"https://api.vextorium.com/v1/llm-token-count","category":"market","description":"Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token. Budget LLM calls and split contexts.","price_listed":0.003,"price_asked":0.003,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":315,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:10","eip155:5042","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"text":"Artificial intelligence agents are transforming the digital economy. AI agents pay for data with micropayments. The x402 protocol lets agents pay per call without accounts. Many companies already offer pay-per-use APIs for agents. USDC micropayments make this business model viable."},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"model":{"enum":["o200k_base","cl100k_base"],"type":"string"},"text":{"type":"string"}},"required":["text"]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"characters":{"type":["number","null"]},"characters_per_token":{"type":["number","null"]},"encoding":{"type":["string","null"]},"estimates":{"properties":{"claude_approx":{"type":["number","null"]},"gemini_approx":{"type":["number","null"]},"llama3_approx":{"type":["number","null"]}},"type":["object","null"]},"note":{"type":["string","null"]},"tokens":{"type":["number","null"]},"tokens_other_encoding":{"properties":{"cl100k_base":{"type":["number","null"]}},"type":["object","null"]},"words":{"type":["number","null"]}},"type":["object","null"]},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-04","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.003,"price_match":true,"latency_ms":315,"error":null}],"description_full":"Count the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token. Budget LLM calls and split contexts.","last_updated":"2026-10-03T20:58:28.509Z","schemes":["exact"]}