← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Inkling (batch) Pricing
Thinking Machines · thinkingmachines-inkling-batch
Input / 1M tokens
$1.00
Output / 1M tokens
$4.05
Context window
524,288 tokens
≈ 699 pages of text
Max output
471,859 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0028
1,000 requests / month$2.82/mo10,000 requests / month$28.20/mo100,000 requests / month$282.00/moEstimate your own workloadOpens the calculator with Inkling (batch) preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Large 512k context supports batch processing of long multimodal inputs at low per-token cost.
The business tradeoff
Unknown provider and open_weights hosting introduce ecosystem and reliability variance with no established track record.
Cheaper from Thinking Machines
Head-to-head
Vendor list rates, as of Aug 18, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.