Question 1

What does this Step 3.7 Flash 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: Step 3.7 Flash or Inkling Small?

Accepted Answer

Step 3.7 Flash lists $0.185 input and $1.11 output per 1M tokens. Inkling Small lists $0.50 input and $1.20 output. The cheaper workload depends on the mix of input and output. Long-context tiers, caching, batch processing and retries can change the bill.

Question 3

Which has the larger context window: Step 3.7 Flash or Inkling Small?

Accepted Answer

Step 3.7 Flash lists 256K 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: Step 3.7 Flash 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 Step 3.7 Flash and Inkling Small support?

Accepted Answer

Step 3.7 Flash records text, image, video 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 Step 3.7 Flash or Inkling Small?

Accepted Answer

Consider Step 3.7 Flash if you need a lower listed input rate or a lower listed output rate. Consider Inkling Small if you need larger context or larger maximum output. 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	Step 3.7 Flash	Inkling Small
Provider	StepFun	Thinkingmachines
Listed pricing route	StepFun	Thinkingmachines
Model family	—	ling
Accepted inputs	text, image, video	text, image, audio
Produced outputs	text	text
Context window	256K	1.05MHigher
Max output	256K	1.05MHigher
Input price / 1M	$0.185Lower	$0.50
Output price / 1M	$1.11Lower	$1.20
Reasoning mode	Documented	Documented
Tool calling	Documented	Documented
Image input	Documented	Documented
Audio input	Not documented	Documented
Structured output	Not documented	Not documented
License	Open weights	Apache-2.0

Step 3.7 Flash vs Inkling Small

Step 3.7 Flash

Inkling Small

Key differences

Pricing, limits and capabilities

Which model should you choose?

Documentation and model profiles

Questions people ask

Compare a different pair