Cloudflare Workers AI vs DeepSeek. Compare a Workers AI hosted quote with DeepSeek's direct peak-hour default quote; identities and billing scopes stay separate.
USD token-only estimates using each offering’s published default tier. 1M tokens are an aggregate workload, not a single request. Cache savings, batch discounts, long-context surcharges, tools, taxes and negotiated rates are excluded. Tokenizers and capabilities may differ; lower price does not establish equivalent quality.
Current cost comparison is paused because one or both quotes are not verified. The rates below are historical references, not current offers.
| Metric | DeepSeek V4 Flash 0731 · Workers AICloudflare Workers AI | DeepSeek V4 FlashDeepSeek |
|---|---|---|
| Input / 1M tokens | $0.44 | $0.44 |
| Output / 1M tokens | $1.32 | $1.32 |
| Cached input / 1M | $0.014 | $0.014 |
| Context window | Not published | 1,000,000 |
| Maximum output | Not published | 384,000 |
| 1M input + 1M output | Paused | Paused |
| Default pricing basis | standard | peak |
| Last verified (UTC) | 2026-09-09T01:36:53.690Z | 2026-09-08T10:18:11.171Z |
Cloudflare Workers AI hosted-model dollar token rates, not the upstream model developer's direct API price. The official token and Neuron columns are equivalent. Free daily allocation, non-token models and optional features are excluded.
Official pricing sourceLast verified:
All tiers and model details →DeepSeek V4 Flash
Official pricing sourceLast verified:
All tiers and model details →