# Cloudflare Workers AI vs General Compute

> Workers AI runs 50+ open models on Cloudflare's network next to your Workers. General Compute serves four models with decode on ASICs.

Canonical: https://www.subconscious.dev/compare/cloudflare-workers-ai-vs-general-compute · By The Subconscious Team · Updated October 27, 2026

## How they compare

Workers AI bills in Neurons with 10,000 free a day and carries frontier-scale open models like DeepSeek V4 Pro, GLM 5.3 and Kimi K3, with 1M context on DeepSeek V4 and Kimi K3. Its gpt-oss 120B costs $0.35 in and $0.75 out per million tokens. General Compute serves GPT-OSS 120B at $0.21 in and $0.79 out and reports over 1,000 tokens per second on it in its own benchmark, using GPU prefill and ASIC decode. Its other models are MiniMax M2.7, DeepSeek V3.2 and DeepSeek V3.1, with context up to 192K.

Workers AI is the pick for apps already built on Workers, where inference, code, storage and the Agents SDK share one platform, and for long-context loops on newer models. General Compute fits teams that want decode speed or need to serve a fully fine-tuned checkpoint, which Workers AI does not support for large LLMs. It also sells dedicated racks under a tokens-per-second SLA.

## 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.

### General Compute

General Compute is a San Francisco inference cloud built on alternative chips. It splits each request across hardware, with NVIDIA GPUs handling prefill and ASICs from Cerebras, SambaNova, Positron AI and d-Matrix handling decode. In its own open benchmark on GPT-OSS 120B it measured 1,025 to 1,234 output tokens per second against 100 to 121 on an unnamed GPU cloud, and up to 16.2x faster end to end. Founders Finn Puklowski and Jason Goodison raised a $15M seed led by FUSE, an up to $400M debt facility from Upper90 and, on October 27, 2026, a $100M Series A co-led by Blackbird and Abstract.

## Which is best, and when

### Choose Cloudflare Workers AI for

- Apps built on Cloudflare Workers
- Daily free inference allocation
- 1M context on DeepSeek V4 and Kimi K3

### Choose General Compute for

- Decode speed on GPT-OSS 120B
- Serving full fine-tuned checkpoints
- Dedicated capacity contracts

## At a glance

| Attribute | Cloudflare Workers AI | General Compute |
|---|---|---|
| Model access | Open weights | Open weights |
| Flagship models | DeepSeek V4 Pro, GLM 5.3, Kimi K3, Kimi K2.7 Code, gpt-oss 120B | MiniMax M2.7, DeepSeek V3.2, GPT-OSS 120B |
| Speed | - | 1,000+ tok/s on GPT-OSS 120B (vendor) |
| Price | $0.011 per 1K Neurons; 10K free daily | $0.21–$0.28 in, $0.38–$1.20 out per 1M |
| Customization | BYO LoRA on small models (beta) | Custom LoRA and fine-tuned checkpoints |
| Deployment | Serverless on Cloudflare network | Serverless API, dedicated racks, bare metal |
| Long context | 1M on DeepSeek V4 and Kimi K3; 262K on Kimi K2.6 and K2.7 Code | 192K (MiniMax M2.7) |

## FAQ

### What is the difference between Cloudflare Workers AI and General Compute?

Workers AI runs 50+ open models on Cloudflare's network next to your Workers. General Compute serves four models with decode on ASICs.

### When should I choose Cloudflare Workers AI over General Compute?

Apps built on Cloudflare Workers; Daily free inference allocation; 1M context on DeepSeek V4 and Kimi K3.

### When should I choose General Compute over Cloudflare Workers AI?

Decode speed on GPT-OSS 120B; Serving full fine-tuned checkpoints; Dedicated capacity contracts.

### Is Cloudflare Workers AI or General Compute cheaper?

Cloudflare Workers AI: $0.011 per 1K Neurons; 10K free daily. General Compute: $0.21–$0.28 in, $0.38–$1.20 out per 1M. The cheaper choice depends on the model and workload.

### Which has more context, Cloudflare Workers AI or General Compute?

Cloudflare Workers AI: 1M on DeepSeek V4 and Kimi K3; 262K on Kimi K2.6 and K2.7 Code. General Compute: 192K (MiniMax M2.7).

## 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 General Compute](https://www.subconscious.dev/compare/subconscious-vs-general-compute.md).

Full profiles: [Cloudflare Workers AI](https://www.subconscious.dev/providers/cloudflare-workers-ai.md), [General Compute](https://www.subconscious.dev/providers/general-compute.md).