Inkling Small

thinkingmachines/inkling-small

A chat model with a 1M-token context window, at $0.4725 per million input tokens and $1.26 per million output tokens.

Details

Maker: thinkingmachines
Kind: Chat
Context window: 1,000,000 tokens
Max output: 1,000,000 tokens
Input: $0.4725 per million tokens
Cached input: $0.105 per million tokens, 78% off
Cache write: Same as input
Output: $1.26 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-07-30

Description

Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling-small",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model