Host Cloudflare repriced DeepSeek V4 Pro: output down 36%, cache read up 355%
Published 15 September 2026
Price move, per 1M tokens
- Cloudflare · input↓ 13%$1.32 → $1.15
- Cloudflare · output↓ 36%$3.96 → $2.55
- Cloudflare · cache read↑ 355%$0.044 → $0.200
| host | rate | was | now | change |
|---|---|---|---|---|
| Cloudflare | input | $1.32 | $1.15 | ↓ 13% |
| Cloudflare | output | $3.96 | $2.55 | ↓ 36% |
| Cloudflare | cache read | $0.044 | $0.200 | ↑ 355% |
output: ↓ 36%cache read: ↑ 355%
If you buy
Chatty workloads that rarely reuse context now cost less to run here, while prompt-caching setups should re-check their spend before the next top-up.
The model
DeepSeek V4 Proopen the model →
Open weights1598.8B parameters1049K context28 hosts
intelligence36th of 168 writing32nd of 168 coding43rd of 168 agents31st of 55
DeepSeek V4 Pro is a large downloadable text model with a one-million-token request limit and strong mathematics scores. Its mixture-of-experts design keeps only 37 billion parameters active per token, making it more efficient to run than its total size suggests.
Source
Read on openrouter.ai · we published this on 15 September 2026.
read the original at openrouter.ai ↗