输入价格$2.50/百万 tokens
输出价格$10.00/百万 tokens
上下文128Ktokens
P50 延迟—s首字延迟
吞吐量—tok/s
Aging but battle-tested. GPT-4o has the most mature function-calling implementation on the market, the largest pool of cookbook examples, and integration support across every framework. Cost runs below GPT-5 with quality that's still competitive on everyday tasks; reasoning depth is the gap. A safe production choice when team familiarity and ecosystem support matter more than absolute frontier performance.
完整定价详情
全部价格按美元 / 百万 token 计 · 所有隐性成本已揭示| Pricing tier | Input | Output | Notes |
|---|---|---|---|
Standard Pay-as-you-go API rate card | $2.50 | $10.00 | Default if no headers set |
With prompt caching Cached read · cache write | $0.25−90% | $10.00 | Cache writes priced at standard input ($2.50); cached reads 90% off. Requires cache_control header. |
Batch API (50% off) 24h SLA, async | $1.25−50% | $5.00−50% | Send up to 50K requests in one batch; results within 24h |
Image input (vision) Per image, low/high detail differ | $2.50 + image fee | $10.00 | $0.50 per 1024×1024 image at high detail; low detail ~$0.10 |
Reasoning tokens Hidden chain-of-thought tokens | $2.50 | $10.00 × ~3-8 | When using reasoning.effort: high, output tokens include hidden reasoning. Real cost can be 3-8× headline output. |
Structured output JSON mode + schema | $2.50 | $10.00 | No extra cost; first call may be slower (~2x latency) due to schema compilation |
能力
Vision (image understanding)Function callingStructured output (JSON schema)Reasoning modeMultilingual (32+ langs)Batch APIAudio I/OFine-tuning