geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
thinking machines

Inkling-Small

AI model Released

Context window
1,048,576 tokens*
Maximum output
1,048,576 tokens*
Open weights
Yes*

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Inkling-Small 150.5* Inkling-Small · 95% interval 147.7–152.4

Run it locally

Inference · memory estimate

Inkling-Small

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Context window
1,048,576 tokens*
Maximum output
1,048,576 tokens*
Reasoning
Yes*
Tool calling
Yes*
Open weights
Yes*
Model license
Apache-2.0*

Input modalities

  • text*
  • image*
  • audio*

Output modalities

  • text*

System configuration

Detailed specifications

Specifications 1 · 4 fields
Access model
Open weights (unrestricted)*
Open weights
Yes*
Organization
Thinking Machines*
Organization country
United States of America*
Specifications 2 · 26 fields
File attachments
Yes*
Context window
1,048,576* tokens
Model family
ling*
Input modalities
  • text*
  • image*
  • audio*
Model licence
Apache-2.0*
Maximum output
1,048,576* tokens
Output modalities
  • text*
API service · Hugging Face · thinkingmachines/Inkling-Small
Provider
Hugging Face*
Model
thinkingmachines/Inkling-Small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
1,048,576*
Modalities
input
  • text*
  • image*
output
  • text*
Reasoning
Yes*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.5*
output
1.2*
API service · Arcee · thinkingmachines/inkling-small
Provider
Arcee*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
262,144*
output
262,144*
Modalities
input
  • text*
output
  • text*
Reasoning
Yes*
Tool calling
Yes*
Temperature control
Yes*
File attachments
No*
Availability status
deprecated*
Interleaved reasoning
field
reasoning_content*
Prices (USD per million tokens)
input
0.5*
output
1.2*
cache_read
0.1*
API service · Thinking Machines · thinkingmachines/Inkling-Small
Provider
Thinking Machines*
Model
thinkingmachines/Inkling-Small*
Snapshot
2026-10-26*
Token limits
context
65,536*
output
65,536*
Modalities
input
  • text*
  • image*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    toggle*
  • type
    effort*
    values
    • low*
    • medium*
    • high*
    • xhigh*
    • max*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.58*
output
1.44*
cache_read
0.116*
API service · Thinking Machines · thinkingmachines/Inkling-Small:peft:262144
Provider
Thinking Machines*
Model
thinkingmachines/Inkling-Small:peft:262144*
Snapshot
2026-10-26*
Token limits
context
262,144*
output
262,144*
Modalities
input
  • text*
  • image*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    toggle*
  • type
    effort*
    values
    • low*
    • medium*
    • high*
    • xhigh*
    • max*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.58*
output
1.44*
cache_read
0.116*
API service · Vercel AI Gateway · thinkingmachines/inkling-small
Provider
Vercel AI Gateway*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
1,000,000*
output
1,000,000*
Modalities
input
  • text*
  • image*
  • pdf*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • xhigh*
    • max*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · NanoGPT · thinkingmachines/Inkling-Small
Provider
NanoGPT*
Model
thinkingmachines/Inkling-Small*
Snapshot
2026-10-26*
Token limits
context
524,288*
input
524,288*
output
32,768*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
No*
Tool calling
Yes*
Structured output
No*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · AI/ML API · thinkingmachines/inkling-small
Provider
AI/ML API*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
262,144*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • low*
    • medium*
    • high*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Interleaved reasoning
field
reasoning_details*
Prices (USD per million tokens)
input
0.61364*
output
1.52352*
cache_read
0.122728*
API service · OpenRouter · thinkingmachines/inkling-small:free
Provider
OpenRouter*
Model
thinkingmachines/inkling-small:free*
Snapshot
2026-10-26*
Token limits
context
1,048,576*
output
262,144*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Structured output
No*
Temperature control
Yes*
File attachments
Yes*
API service · CommandCode · thinkingmachines/inkling-small
Provider
CommandCode*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
1,000,000*
output
1,000,000*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.5*
output
1.2*
cache_read
0.1*
API service · Kilo Gateway · thinkingmachines/inkling-small
Provider
Kilo Gateway*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
262,144*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Structured output
No*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · Deep Infra · thinkingmachines/Inkling-Small
Provider
Deep Infra*
Model
thinkingmachines/Inkling-Small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
1,048,576*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Tool calling
Yes*
Structured output
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · OpenRouter · thinkingmachines/inkling-small
Provider
OpenRouter*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
262,144*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Structured output
No*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · LLMTR · thinkingmachines/inkling-small
Provider
LLMTR*
Model
thinkingmachines/inkling-small*
Snapshot
2026-10-26*
Token limits
context
262,144*
output
262,144*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • xhigh*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.58*
output
1.44*
cache_read
0.116*
API service · Thinking Machines · thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4
Provider
Thinking Machines*
Model
thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4*
Snapshot
2026-10-26*
Token limits
context
262,144*
output
262,144*
Modalities
input
  • text*
  • image*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    toggle*
  • type
    effort*
    values
    • low*
    • medium*
    • high*
    • xhigh*
    • max*
Tool calling
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.3*
output
1.2*
cache_read
0.06*
API service · Eden AI · deepinfra/thinkingmachines/Inkling-Small
Provider
Eden AI*
Model
deepinfra/thinkingmachines/Inkling-Small*
Snapshot
2026-10-26*
Token limits
context
524,288*
output
1,048,576*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • none*
    • minimal*
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Structured output
Yes*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
API service · NanoGPT · thinkingmachines/Inkling-Small:thinking
Provider
NanoGPT*
Model
thinkingmachines/Inkling-Small:thinking*
Snapshot
2026-10-26*
Token limits
context
524,288*
input
524,288*
output
32,768*
Modalities
input
  • text*
  • image*
  • audio*
output
  • text*
Reasoning
Yes*
Reasoning controls
  • type
    effort*
    values
    • minimal*
    • low*
    • medium*
    • high*
    • max*
Tool calling
Yes*
Structured output
No*
Temperature control
Yes*
File attachments
Yes*
Prices (USD per million tokens)
input
0.45*
output
1.2*
cache_read
0.1*
Reasoning
Yes*
Temperature control
Yes*
Tool calling
Yes*

* Provisional data