Inkling API Pricing
thinkingmachines · Mid-tier · released 2026-07. Prices in USD per 1 million tokens. Data snapshot: 2026-09-06.
- Input: $1.00 per 1M tokens
- Output: $4.05 per 1M tokens
- Batch API (input/output): $1.00 / $4.05
- Prompt-cache read: $0.17
- Context window: 1M
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 | $0.0035 | $0.0028 | $278 |
| Knowledge Q&A | 2,000 / 800 | $0.0052 | $0.0041 | $408 |
| Meeting Summary | 10,000 / 1,200 | $0.015 | $0.014 | $1.4K |
| Marketing Content | 2,500 / 1,800 | $0.0098 | $0.0094 | $938 |
| Coding Task | 3,000 / 2,000 | $0.011 | $0.0099 | $985 |
| Invoice Processing | 1,500 / 600 | $0.0039 | $0.0036 | $356 |
| Call Summary | 2,000 / 700 | $0.0048 | $0.0047 | $467 |
| Agent Workflow | 6,000 / 3,000 | $0.018 | $0.015 | $1.5K |
Inkling pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 3 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-06 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| DeepInfra — fp8 | $0.95 | $4.05 |
| BaseTen (the price shown above) — fp8 | $1.00 | $4.05 |
| Together (the price shown above) | $1.00 | $4.05 |
Common questions about Inkling pricing
- How much does Inkling cost?
- Inkling costs $1.00 per million input tokens and $4.05 per million output tokens on the API.
- Does Inkling offer batch or cached pricing?
- Yes. Batch API pricing is $1.00/M input and $4.05/M output. Prompt-cache reads cost $0.17/M.
- What would Inkling cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Inkling costs about $353 at list prices.
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.
Build the business case for Inkling in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server