# Cloudflare Workers AI vs Dolphin

> Workers AI serves 50+ open models on Cloudflare's own GPUs. Dolphin serves one open model on a network of idle consumer GPUs.

Canonical: https://www.subconscious.dev/compare/cloudflare-workers-ai-vs-dolphin · By The Subconscious Team · Updated October 11, 2026

## How they compare

Workers AI includes DeepSeek V4 Pro and Flash, GLM 5.3, Kimi K2.6 and gpt-oss 120B behind OpenAI-compatible endpoints, with 10,000 free Neurons a day, prefix caching and AI Gateway for fallbacks and spend tracking. Dolphin's API launched in October 2026 with one model, DeepSeek V4.1 Flash, at $0.01 in and $0.07 out per million, served on idle consumer GPUs. Nodes are checked against a trusted copy of the model and cannot log requests, but Dolphin publishes no speed, context or SLA.

Workers AI suits teams on Cloudflare who want many models, long context and an established vendor. Dolphin suits cost-first background jobs and products that need uncensored models, if wallet and Telegram signup and variable uptime are acceptable.

## What each one does

### 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 K3, K2.6 and K2.7 Code, GLM 5.2, 5.3 and 5.3 Flash, 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, and Kimi K3 now matches it.

### Dolphin

Dolphin began in 2023 as Eric Hartford's series of open-source, uncensored fine-tunes, trained to drop the refusals and baked-in guidelines of their base models so that the developer sets the rules through the system prompt. Current releases include Dolphin Llama 3.1 8B and Dolphin Mistral 24B Venice Edition, built with Venice, and the project publishes nearly 100 models on Hugging Face. It also runs a chat app, a Telegram bot and a synthetic data service that generates answers to commonly refused prompts.

## Which is best, and when

### Choose Cloudflare Workers AI for

- Apps already built on Workers
- Many open models with long context
- Caching and fallbacks via AI Gateway

### Choose Dolphin for

- Very cheap DeepSeek V4.1 Flash calls
- Background jobs with loose latency needs
- Models without vendor-imposed refusals

## At a glance

| Attribute | Cloudflare Workers AI | Dolphin |
|---|---|---|
| Model access | Open weights | Open weights, uncensored fine-tunes |
| Flagship models | DeepSeek V4 Pro, GLM 5.3, Kimi K3, Kimi K2.7 Code, gpt-oss 120B | DeepSeek V4.1 Flash, Dolphin Mistral 24B |
| Speed | - | - |
| Price | $0.011 per 1K Neurons; 10K free daily | $0.01 in, $0.07 out (DeepSeek V4.1 Flash) |
| Customization | BYO LoRA on small models (beta) | Own uncensored fine-tunes |
| Deployment | Serverless on Cloudflare network | Decentralized serverless API |
| Long context | 1M on DeepSeek V4 and Kimi K3; 262K on Kimi K2.6 and K2.7 Code | - |

## FAQ

### What is the difference between Cloudflare Workers AI and Dolphin?

Workers AI serves 50+ open models on Cloudflare's own GPUs. Dolphin serves one open model on a network of idle consumer GPUs.

### When should I choose Cloudflare Workers AI over Dolphin?

Apps already built on Workers; Many open models with long context; Caching and fallbacks via AI Gateway.

### When should I choose Dolphin over Cloudflare Workers AI?

Very cheap DeepSeek V4.1 Flash calls; Background jobs with loose latency needs; Models without vendor-imposed refusals.

### Is Cloudflare Workers AI or Dolphin cheaper?

Cloudflare Workers AI: $0.011 per 1K Neurons; 10K free daily. Dolphin: $0.01 in, $0.07 out (DeepSeek V4.1 Flash). The cheaper choice depends on the model and workload.

## Running long-horizon agents?

If your agents run past 200K tokens, compare both against Subconscious: [Subconscious vs Cloudflare Workers AI](https://www.subconscious.dev/compare/subconscious-vs-cloudflare-workers-ai.md), [Subconscious vs Dolphin](https://www.subconscious.dev/compare/subconscious-vs-dolphin.md).

Full profiles: [Cloudflare Workers AI](https://www.subconscious.dev/providers/cloudflare-workers-ai.md), [Dolphin](https://www.subconscious.dev/providers/dolphin.md).