Skip to content
LLMs
Thinking Machines logo

Thinking Machines: Inkling Small

by Thinking Machines

Thinking Machines: Inkling Small is a large language model from Thinking Machines. It costs $0.450 per million input tokens and $1.20 per million output tokens. Its context window is 1.0M tokens.

Free tier availableReasoningTool callingPrompt cachingBatch tierOpen weightsimage inputaudio input
Input / 1M tokens
$0.450
Output / 1M tokens
$1.20
Cached input / 1M
$0.100

On repeated prefixes

Context window
1.0M

tokens

Who serves it cheapest

3 hosts serve Inkling Small. Same weights, same API - the price difference is pure margin and routing.

Providers serving Thinking Machines: Inkling Small, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapestfp8$0.450$1.20524K-49.3%
BaseTenfp8$0.500$1.201.0M-100.0%
Together$0.500$1.20524K-99.5%

The spread between DeepInfra and Together is 1.1× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
26.1
Coding index
52.9
Agentic index
25.0

About 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...

Specifications

Thinking Machines: Inkling Small specifications
Model IDthinkingmachines/inkling-small
ProviderThinking Machines
Context window1.0M tokens
Max output262K tokens
Input modalitiestext, image, audio
Output modalitiestext
Knowledge cutoff-
Open weightsYes - thinkingmachines/Inkling-Small
ReleasedJuly 30, 2026

Cheaper alternatives

Models that cost less than Inkling Small while keeping at least half its context window and every input modality it supports.

Gemini 3.1 Flash Lite

$0.250 in · $1.50 out

1.1× cheaper

Gemini 3.1 Flash Lite Preview

$0.250 in · $1.50 out

1.1× cheaper

MiMo-V2.5

$0.140 in · $0.280 out

3.6× cheaper

Gemini 2.5 Flash Lite

$0.100 in · $0.400 out

3.6× cheaper

Muse Spark 1.3 Contributor

$0.100 in · $0.200 out

5.1× cheaper

Frequently asked

How much does Thinking Machines: Inkling Small cost?

$0.450 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.100 per million tokens.

What is the context window of Thinking Machines: Inkling Small?

1.0M tokens, with up to 262K tokens of output per request.

Which provider serves Thinking Machines: Inkling Small cheapest?

DeepInfra at $0.450 per million input tokens - 1.1× cheaper than Together, the most expensive of the 3 hosts serving it.