Question 1

What does this Fugu vs Inkling Small comparison cover?

Accepted Answer

It brings together documented inputs and outputs, token limits, deployment terms and available pricing. When both models have source-linked, verified results on a shared benchmark, those results are shown with their individual sources. The comparison is a starting point for evaluating your own workload.

Question 2

Which is cheaper: Fugu or Inkling Small?

Accepted Answer

The available pricing does not establish a comparable input and output token rate for both models. Check the billing unit and selected host in each profile. Images, speech, video and local inference can have different cost structures.

Question 3

Which has the larger context window: Fugu or Inkling Small?

Accepted Answer

Fugu lists 1M tokens and Inkling Small lists 1.05M. Inkling Small therefore has the larger recorded context window, but capacity alone is not a quality score.

Question 4

Which is faster: Fugu or Inkling Small?

Accepted Answer

There is no matched speed measurement for both models with the same source, host, region and date. Test the same prompts at your expected concurrency and measure time to the first useful response as well as complete task time.

Question 5

What input and output types do Fugu and Inkling Small support?

Accepted Answer

Fugu records text, image input and text output. Inkling Small records text, image, audio input and text output. “Not documented” means the current source record is incomplete; it does not prove that a modality is unsupported.

Question 6

Should I choose Fugu or Inkling Small?

Accepted Answer

Consider Inkling Small if you need larger context. Inkling Small offers downloadable weights; Fugu is listed as a proprietary model. Compare licence terms and operating costs before choosing a deployment. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.

Specification	Fugu	Inkling Small
Provider	Sakana AI	Thinkingmachines
Listed pricing route	Sakana AI	Thinkingmachines
Model family	fugu	ling
Accepted inputs	text, image	text, image, audio
Produced outputs	text	text
Context window	1M	1.05MHigher
Max output	—	1.05M
Input price / 1M	—	$0.50
Output price / 1M	—	$1.20
Reasoning mode	Documented	Documented
Tool calling	Documented	Documented
Image input	Documented	Documented
Audio input	Not documented	Documented
Structured output	Documented	Not documented
License	Proprietary	Apache-2.0

Fugu vs Inkling Small

Fugu

Inkling Small

Key differences

Pricing, limits and capabilities

Which model should you choose?

Documentation and model profiles

Questions people ask

Compare a different pair