Step-3.7-Flash vs GPT-5.1-Codex-Mini

API pricing, benchmark indices and specs — updated 19 October 2026.

stepfun-ai · A · Open weights

Params

201.4 B

Context

—

30d

17 K

apache-2.0 · commercial OK

openai · B · API-only

Input / 1M

$0.25

Output / 1M

$2.00

AA index

20.4

proprietary · 400K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Step-3.7-Flash	GPT-5.1-Codex-Mini
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	201.4 B	n/a — API-only
Architecture	Step3p7ForConditionalGeneration	n/a — API-only
Context length	256,000	400,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	1	n/a — API-only
Downloads 30d	16,549	n/a — API-only
Downloads all time	406 K	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2026-05-23	n/a — API-only
API input price / 1M tokens	$0.20	$0.25
API output price / 1M tokens	$1.15	$2.00
Est. cost per 1M input + 1M output tokens	$1.35	$2.25
Cached input / 1M tokens	$0.04	$0.03
AA Intelligence Index	19.5	20.4
AA Coding Index	39.6	—
AA Agentic Index	—	—
Max output tokens	230,400	128,000
API providers	2	1
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

Step-3.7-Flash $1.35

GPT-5.1-Codex-Mini $2.25

Step-3.7-Flash is 1.7× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Step-3.7-Flash · fp16 473.7 GB / 24 GB

❌ Won’t fit