Cost-efficient small model that's smarter and cheaper than GPT-3.5 Turbo, with vision capabilities. 128K context, October 2023 knowledge cutoff.
| Type | Standard Price | Batch API Price* | Cached Price** |
|---|---|---|---|
| Input tokens | $0.150 / 1M tokens | $0.075 / 1M tokens | $0.075 / 1M tokens |
| Output tokens | $0.600 / 1M tokens | $0.300 / 1M tokens | - |
Fast, cost-efficient reasoning model tailored to coding, math, and science use cases. 128K context, October 2023 knowledge cutoff.
| Type | Standard Price | Cached Price* |
|---|---|---|
| Input tokens | $3.00 / 1M tokens | $1.50 / 1M tokens |
| Output tokens** | $12.00 / 1M tokens | - |
* Batch API: Responses returned within 24 hours for 50% discount
** Cached prompts offered at 50% discount compared to uncached prompts
*** Output tokens include internal reasoning tokens not visible in API responses
Token conversion: ~750 words = 1,000 tokens