MODELS / THINKINGMACHINES

Inkling

Inkling is a multimodal MoE model (975B total, 41B active, 256k context) reasoning over text, image, and audio inputs.

TEXTREASONINGREASONINGTOOL-USEVISIONFILE-INPUT
256K
CONTEXT WINDOW
-
MAX OUTPUT TOKENS
$1
INPUT PRICE / 1M TOKENS
$4.05
OUTPUT PRICE / 1M TOKENS
QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/thinkingmachines/inkling",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Inkling supports, in one table.

MODEL ID
blackboxai/thinkingmachines/inkling
DEVELOPED BY
Thinkingmachines
MODEL TYPE
Text
RELEASED
Jul 15, 2026
CONTEXT WINDOW
256K
MAX OUTPUT TOKENS
-
INPUT MODALITIES
text, image, pdf
OUTPUT MODALITIES
text
INPUT PRICE
$1 / 1M tokens
OUTPUT PRICE
$4.05 / 1M tokens
CACHE READ
$0.17 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Not available (closed-weight model)
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoning