thinkingmachines logo
thinkingmachines

Thinking Machines: Inkling 2 Small

Source description (English)

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

Overview

Model specifications

Context
1,048,576 tokens
Maximum output
943,718 tokens
Architecture
text+image->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.3
per 1M tokens
Output
$1
per 1M tokens
Cache read
$0.03
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
Yes
Default parameters
high
Capabilities
max, high, medium, low, minimal
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"thinkingmachines/inkling-2-small","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes · max · high · medium · low · minimal

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

4 providers

Checked: November 13, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

PrimeIntellect

fp4
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$0.5
Cache read
$0.03
Cache write
Not provided

Nebius

fp4
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1
Cache read
$0.06
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1
Cache read
$0.03
Cache write
Not provided

Cloudflare

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1
Cache read
$0.1
Cache write
Not provided
thinkingmachines

4 models

All models
thinkingmachines logothinkingmachines

Thinking Machines: Inkling 2 Small (free)

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...

Context
1.0M
Input
text · image
Output
text
Input: FreeOutput: Freeper 1M tokens
View model details →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Context
524K
Input
text · image · audio
Output
text
Input: $0.45Output: $1.2per 1M tokens
View model details →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling Small (batch)

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Context
524K
Input
text · image · audio
Output
text
Input: $0.36Output: $0.96per 1M tokens
View model details →
thinkingmachines logothinkingmachines

Thinking Machines: Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Context
524K
Input
text · image · audio
Output
text
Input: $1Output: $4.05per 1M tokens
View model details →