Uncensored StepFun Models
The best uncensored StepFun model is Step 3.7 Flash (30.3 intelligence) — served without a provider-level moderation layer. Step 3.5 Flash (26.0) is next.
Large language models served without a provider-level moderation layer, ranked by intelligence. "Uncensored" here means the API endpoint doesn't add its own filtering on top of the model — each model's own alignment training still applies, and open-weight entries can be self-hosted for full control. Relevant for fiction, roleplay, red-teaming and safety research, where an extra moderation layer causes over-refusal on legitimate prompts.
- 1
step-3.7-flashReasoningToolsJSON+130.3 intel · $0.200/M · 262K ctx30.3Intelligence - 2step-3.5-flashReasoningTools26.0 intel · $0.100/M · 262K ctx26.0Intelligence
Frequently asked
What is the best uncensored StepFun model?
The best uncensored StepFun model is Step 3.7 Flash (30.3 intelligence) — served without a provider-level moderation layer. Step 3.5 Flash (26.0) is next.
What's a good alternative to Step 3.7 Flash?
Step 3.5 Flash (26.0) is the closest alternative on this metric. See the full ranking above for the tradeoffs.
How many StepFun models are there?
modelgrep tracks 2 StepFun models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Step 3.7 Flash. 2 of them qualify for this ranking.