← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Inkling (batch) Pricing
Thinking Machines · thinkingmachines-inkling-batch
Input / 1M tokens
$0.500
Output / 1M tokens
$2.02
Context window
524,288 tokens
≈ 699 pages of text
Max output
—
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0014
1,000 requests / month$1.41/mo10,000 requests / month$14.10/mo100,000 requests / month$141.00/moEstimate your own workloadOpens the calculator with Inkling (batch) preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
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 6, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.