Allocate
Inkling Small
Open weightsNew- Price first checked
- Listed on Allocate
Inkling Small is a language model from Thinking Machines with a 512K-token context window. Provider list price is $0.50 per million input tokens and $1.20 per million output; on Allocate you pay $0.54 and $1.28. The weights are open, so you can fine-tune it and own the result.
What a real workload costs
Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.50 + 350 × $1.20 = $1,020 a month. Billed on Allocate it is $1,091.
Example usage
curl https://api.allocate.network/v1/chat/completions \
-H "Authorization: Bearer $ALLOCATE_KEY" \
-d '{
"model": "thinkingmachines/inkling-small",
"messages": [{ "role": "user", "content": "Summarise the attached contract." }]
}'Common questions
How much does Inkling Small cost per million tokens?
Provider list price is $0.50 per million input tokens and $1.20 per million output tokens. On Allocate you pay $0.54 in and $1.28 out.
What context window does Inkling Small have?
524,288 tokens (512K). At roughly 0.75 words per token, that is about 393k words of English text per request.
What does cached input cost on Inkling Small?
$0.10 per million tokens at list ($0.11 billed). Repeated prompt prefixes, such as a stable system prompt or tool definitions, bill at this rate instead of the full input price.
Can I fine-tune Inkling Small?
Yes. Inkling Small is an open-weights model; check the lab’s model card for the exact license terms. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.
Has the price of Inkling Small changed?
Allocate has checked the provider list price hourly since 12 Sep 2026. It has not changed in that time. The price history chart on this page shows every change.
How do I call Inkling Small on Allocate?
Send thinkingmachines/inkling-small in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.