Cloudflare Workers AI vs StepFun

StepFun is a Shanghai model lab whose Step 3.7 Flash ships under Apache 2.0. Workers AI is a Western serverless host for many labs' open models.

By The Subconscious Team · Updated September 30, 2026

Cloudflare Workers AI vs StepFun: key differences

StepFun makes models; Cloudflare hosts them. Step 3.7 Flash is a 198B mixture-of-experts vision-language model with 11B active parameters, 256K context, selectable reasoning levels and tool use, priced at $0.20 in and $1.15 out on StepFun's API and running near 128 tokens per second. That is cheaper than the large LLMs on Workers AI, like Kimi K2.6 at $0.95 in and $4.00 out. Workers AI's strength is choice: 50+ models from several labs, including DeepSeek V4 with 1M context, larger than StepFun's 256K.

Distribution and control differ. StepFun's first-party inference is China-hosted with thin Western support, though OpenRouter carries its models and the Apache 2.0 weights run on vLLM and SGLang, so teams can fine-tune and self-host. Workers AI runs on Cloudflare's own network with AI Gateway, prefix caching and integration with Workers, but offers no way to serve large custom weights. StepFun also trails frontier models on hard multimodal reasoning benchmarks, by its own profile's account.

What Cloudflare Workers AI and StepFun do

Cloudflare Workers AI

Workers AI is the serverless GPU inference service of Cloudflare, which was founded in 2009. It launched in September 2023 and reached general availability in April 2024. Models run on GPUs inside Cloudflare's own network and are called from a Worker through an AI binding or over REST, including OpenAI-compatible Chat Completions and Embeddings endpoints plus a Responses endpoint for gpt-oss. The catalog lists 50+ open models. Since Kimi K2.5 arrived in March 2026 it has carried frontier-scale LLMs: Kimi K2.6 and K2.7 Code, GLM 5.2 and 5.3, DeepSeek V4 Pro and Flash, gpt-oss 120B and 20B, Qwen 3.8 27B and Llama 4 Scout. DeepSeek V4, added August 14, 2026, was the first to offer the full 1,048,576 token context.

Example models: DeepSeek V4 Pro, GLM 5.3

Full Cloudflare Workers AI profile

StepFun

StepFun is a Shanghai AI lab known for efficient multimodal models, with a mix of proprietary API models and open-weight releases. Its current workhorse, Step 3.7 Flash, came out in May 2026 as a 198B mixture-of-experts vision-language model with only 11B active parameters. It has 256K context, selectable reasoning levels, tool use and structured outputs, and it ships under Apache 2.0. StepFun's own API prices it at $0.20 in and $1.15 out per million tokens, and OpenRouter carries it too.

Example models: Step 3.7 Flash, Step3

Full StepFun profile

Should you choose Cloudflare Workers AI or StepFun?

Cloudflare Workers AI

Choose Cloudflare Workers AI for

Picking across many labs' open models
Western-hosted inference inside an app platform
1M context on DeepSeek V4

StepFun

Choose StepFun for

Cheap vision and video understanding
Self-hosting a small-active-parameter model
Fine-tuning Apache 2.0 multimodal weights

Cloudflare Workers AI vs StepFun at a glance

Attribute	Cloudflare Workers AI	StepFun
Model access	Open weights	Open (Apache 2.0) and API models
Flagship models	DeepSeek V4 Pro, GLM 5.3, Kimi K2.7 Code, gpt-oss 120B	Step 3.7 Flash, Step3
Speed	Unknown	~128 tok/s on Step 3.7 Flash
Price	$0.011 per 1K Neurons; 10K free daily	$0.20 in, $1.15 out (Step 3.7 Flash)
Customization	BYO LoRA on small models (beta)	Open weights to fine-tune
Deployment	Serverless on Cloudflare network	First-party API, OpenRouter
Long context	1M on DeepSeek V4; 262K on Kimi	256K

Frequently asked questions

What is the difference between Cloudflare Workers AI and StepFun?

StepFun is a Shanghai model lab whose Step 3.7 Flash ships under Apache 2.0. Workers AI is a Western serverless host for many labs' open models.

When should I choose Cloudflare Workers AI over StepFun?

Picking across many labs' open models; Western-hosted inference inside an app platform; 1M context on DeepSeek V4.

When should I choose StepFun over Cloudflare Workers AI?

Cheap vision and video understanding; Self-hosting a small-active-parameter model; Fine-tuning Apache 2.0 multimodal weights.

Is Cloudflare Workers AI or StepFun cheaper?

Cloudflare Workers AI: $0.011 per 1K Neurons; 10K free daily. StepFun: $0.20 in, $1.15 out (Step 3.7 Flash). The cheaper choice depends on the model and workload.

Which has more context, Cloudflare Workers AI or StepFun?

Cloudflare Workers AI: 1M on DeepSeek V4; 262K on Kimi. StepFun: 256K.

Related comparisons

Running long-horizon agents?

If your agents run past 200K tokens, compare both against Subconscious. Our inference stack treats a long-horizon trace as the primary workload, so speed, cost, and accuracy hold up deep into the trace.

Subconscious vs Cloudflare Workers AI Subconscious vs StepFun