Thinkingmachines model
Inkling API cost calculator
Inkling costs $1 per 1M input tokens and $4.05 per 1M output tokens on the Thinkingmachines API, with a 1.0M-token context window. A typical request (2K input, 500 output tokens) costs $0.0040 — about $121/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Inkling
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0017 | $1.71 |
| RAG query with context | 4,000 / 500 | $0.0060 | $6.03 |
| Document summarization | 20,000 / 1,000 | $0.02 | $24.05 |
| Agent coding session | 100,000 / 5,000 | $0.12 | $120 |
Inkling vs other Thinkingmachines models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Inkling | $1 | $4.05 | 1.0M |
| Inkling Small | $0.45 | $1.20 | 1.0M |
Frequently asked questions
How much does Inkling cost per 1M tokens?
According to current pricing data, Inkling costs $1 per 1M input tokens and $4.05 per 1M output tokens. Processing 1M tokens each way costs $5.05.
What does a typical API request to Inkling cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0040. At 1,000 requests per day that is $4.03 daily, or about $121 per month.
What is Inkling's context window?
Inkling supports a 1.0M-token context window (1,048,576 tokens).
Does Inkling support prompt caching?
Yes. Cached input tokens cost $0.17 per 1M — a 83% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Inkling?
Granite 4.0 Micro from Ibm-granite is currently the cheapest comparable option at $0.02 per 1M input tokens versus $1 for Inkling — roughly 59x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Inkling vs Granite 4.0 Micro pricing, or run Inkling head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.