Inkling API
About
Build advanced reasoning agents with Inkling, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $3.74/1M input and $9.36/1M output tokens, native tool calling support, open weights architecture. Access Inkling via the Thinking Machines API with up to 256K output tokens.
Capabilities
Input Modalities
textimageaudiopdf
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
256K
Tokens
Pricing
Standard (per 1M tokens)
Input
$3.74
Output
$9.36
Caching (per 1M tokens)
Read
$0.75
Frequently Asked Questions
Inkling by Thinking Machines costs $3.74 per 1M input tokens and $9.36 per 1M output tokens. Cached reads cost $0.75 per 1M tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
TINKER_API_KEY
API Base URL
https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1