← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Inkling Small Pricing
Thinking Machines · thinkingmachines-inkling-small
Input / 1M tokens
$0.450
Output / 1M tokens
$1.20
Context window
1,048,576 tokens
≈ 1,398 pages of text
Max output
262,144 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.001
1,000 requests / month$1.02/mo10,000 requests / month$10.20/mo100,000 requests / month$102.00/moEstimate your own workloadOpens the calculator with Inkling Small preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jul 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Supports extended multimodal inputs and outputs at low per-token cost with open weights for self-hosted deployment.
The business tradeoff
Small parameter count limits complex reasoning depth; performance varies with local hardware and inference stack.
Head-to-head
Vendor list rates, as of Aug 7, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.