thinkingmachines

Thinking Machines: Inkling (batch)

Inking, from Thinking Machines, is a versatile AI model capable of processing text, images, and audio data, with a context length of 524,288 tokens. It supports reasoning and tools integration but does not offer structured output. This model excels in certain areas, as indicated by its benchmark scores: it shines particularly in coding tasks (with an impressive score of 85.9) but lags in agentic tasks. Given its pricing at $0.5 per million input tokens and $2.025 per million output tokens, Inking is more suitable for users requiring a diverse input modality capability and reasoning abilities, especially those working on complex coding projects. With a blended benchmark score of 70.5 across three independent evaluations, it performs well in practical applications but may not be the best choice for all tasks; its agentic scores suggest limitations in general-purpose agency.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.50
per 1M tokens
Output Price
$2.02
per 1M tokens
Context Window
524,288
tokens

Benchmark results

Independent, published benchmarks. Blended score 70.5 across 3 benchmarks, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 69.8
AI Index Coding software engineering tasks 85.9
AI Index Agentic multi-step tool-using tasks 56.3
Model ID
thinkingmachines/inkling:batch
Vendor
thinkingmachines
Released
July 2026
Tokenizer
Other
Input Modalities
text, image, audio
Output Modalities
text
Max Output
default
Tool Calling
✓ supported
Structured Output
not supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
✓ accepts audio
Moderated
no

What it costs in practice

Computed from the current $0.50/M input and $2.02/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.35
A month of a busy support chatbot 5M in / 2M out $6.55

Category rankings

Where Thinking Machines: Inkling (batch) places across the 11 categories it ranks in. How we rank →

#CategoryScore
#6 TranscriptionVoice · of 25 ranked 123
#8 TTS ReplacementVoice · of 25 ranked 115
#9 Image CaptioningVision · of 25 ranked 121
#10 Audio SummarizationVoice · of 25 ranked 155
#11 Customer SupportBusiness · of 25 ranked 133
#14 Short-Form SummarizationWriting · of 25 ranked 130
#14 Chat CompanionPersonal · of 25 ranked 130
#15 Email DraftingWriting · of 25 ranked 126
#15 Language LearningEducation · of 25 ranked 126
#17 Trivia & General KnowledgePersonal · of 25 ranked 120
#20 Code CompletionCode · of 25 ranked 132

Similar models

Quick answers

How much does Thinking Machines: Inkling (batch) cost?
$0.50 per million input tokens and $2.02 per million output tokens.
What is Thinking Machines: Inkling (batch)'s context window?
524,288 tokens, roughly 786 pages of text in a single request.
Does Thinking Machines: Inkling (batch) support tool calling?
It supports tool calling, a reasoning mode.
Can Thinking Machines: Inkling (batch) process images?
Yes, it accepts image input.