Step 3.5 Flash 2603

Step 3.5 Flash

StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.

Step 3.7 Flash Thinking

Step 3.7 Flash Thinking is StepFun's high-efficiency multimodal MoE model with visible reasoning enabled for deeper agentic coding, long-context reasoning, tool use, and native image/video understanding. ⚠️ Note: This model routes through StepFun, so privacy and logging guarantees may be limited.

Step R1 V Mini

Step-R1-V-Mini, which supports image and text input, text output, has good instruction following and general capabilities, can perceive images with high precision and complete complex reasoning tasks.

GLM 5.3 Flash TEE

GLM-5.3 Flash is Z.AI's natively multimodal 320B MoE reasoning model with 18B active parameters, served by Phala inside a Trusted Execution Environment with Redpill attestation and signed completion receipts.

GLM 5.3 Flash Uncensored

GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.

Qwen3.8 Flash

Qwen3.8 Flash is Alibaba's latest fast multimodal model, with a million-token context window for coding, agentic workflows, visual understanding, long documents, codebases, and videos.