thinkingmachines/Inkling-2-Small
Inkling 2 Small is Thinking Machines' open-weight multimodal model, a mixture-of-experts design with 17B active of 594B parameters. It takes text and images, returns text, and suits developers building agentic and coding tools.
- Price per 1M tokens
- $0.16 / $0.53input / output
- Cached input
- $0.032per 1M tokens
- Context
- 1M tokens943K max output
Providers
7 providers ·
1M context · 943K max output
1M context · 943K max output
1M context
1M context · 943K max output
1M context · 131K max output
1M context · 943K max output
1M context · 943K max output
* No cache discount from this provider: cached tokens cost the input price.
A request picks by price (:floor) or by speed (provider.sort, :nitro), or sets a floor on tokens per second. How routing works
Price history
No provider selected
Loading…
API
curl https://api.opencheap.si/v1/chat/completions \
-H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "opencheap/inkling-2-small", "messages": [{ "role": "user", "content": "Hi" }] }'