Cloudflare Workers AI
Model prices vs the direct API
- Fee on tokens
- Not published
- Neurons: $0.011 per 1,000 Neurons, with per-model token prices published as the Neuron equivalent
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Dollar figures assume $0.011 per 1,000 Neurons (Workers Paid), from developers.cloudflare.com/workers-ai/platform/pricing
Models on Cloudflare Workers AI
17 model routes. 0 of 2 at the lab's own list price; the rest shown as a premium or discount.
GLM 5.3default region$1.4 / $4.4n/an/a
Qwen3.8 27Bdefault region · direct $0.425 / $2.55$0.45 / $3.2+19% vs direct$0.425 / $2.55+19%
Mistral Small 3.1 24Bdefault region$0.351 / $0.555n/an/a
Llama 3.3 70B Instructfp8$0.293 / $2.25n/an/a
Kimi K2.7 Codedefault region$0.95 / $4n/an/a
Gemma 4 26B A4Bdefault region$0.1 / $0.3n/an/a
DeepSeek V4 Pro 0813default region · direct $0.66 / $1.98$1.32 / $3.96+100% vs direct$0.66 / $1.98+100%
Premium: blended price (3 input to 1 output) on this platform against the lab's own API. Regions are separate routes.
Features
- Fallbacks
- Load balancing
- Caching
- Guardrails
- Observability
- Rate limits
- Budgets
- Prompts
- OpenAI-compatible
- Bring your own key
- Data residency
- Private networking
What it costs on real workloads
Claude Sonnet 5n/avs $400.00 direct
GPT-6 Soln/avs $400.00 direct
100M input and 20M output tokens a month, paying with gateway credits.
The terms, in their words
Cloudflare's serverless GPU inference for open models on its network, billed in Neurons, with AI Gateway as the companion control layer.
- Markup
- Neurons: $0.011 per 1,000 Neurons, with per-model token prices published as the Neuron equivalent
- Free tier
- 10,000 Neurons per day at no charge (Free and Paid plans)
- Providers
- Open models incl. Llama, Mistral, Gemma, Qwen, gpt-oss, DeepSeek, Kimi, GLM
- Workers AI is included in both the Free and Paid Workers plans and is priced at $0.011 per 1,000 Neurons .
- Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge .
- The Price in Tokens column is equivalent to the Price in Neurons column
Source: developers.cloudflare.com/workers-ai/platform/pricing/
Cloudflare Workers AI vs
Hugging Face Inference
NVIDIA NIM
Helicone
Kong AI Gateway
LiteLLM
Vercel AI GatewayCloudflare, Inc., is an American technology company headquartered in San Francisco, California, that provides a range of internet services, including content delivery network (CDN) services, cloud cybersecurity, DDoS mitigation, and ICANN-accredited domain registration.
Pricing as read from the gateway's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.