Inkling Small API Pricing
thinkingmachines · Budget · released 2026-07. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.
- Input: $0.45 per 1M tokens
- Output: $1.20 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.10
- Context window: 524K
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads — only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0013 | $0.000960 | $96 |
| Knowledge Q&A | 2,000 / 800 | $0.0019 | $0.0014 | $137 |
| Meeting Summary | 10,000 / 1,200 | $0.0059 | $0.0056 | $559 |
| Marketing Content | 2,500 / 1,800 | $0.0033 | $0.0031 | $311 |
| Coding Task | 3,000 / 2,000 | $0.0037 | $0.0032 | $323 |
| Invoice Processing | 1,500 / 600 | $0.0014 | $0.0012 | $124 |
| Call Summary | 2,000 / 700 | $0.0017 | $0.0017 | $167 |
| Agent Workflow | 6,000 / 3,000 | $0.0063 | $0.0048 | $483 |
These are list prices — real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.