DeepSeek V4 Pro 0423 pricing
DeepSeek V4 Pro 0423 from DeepSeek runs on 5 providers. The lowest price is $1.044 input and $2.088 output per 1M tokens, on DigitalOcean. On Azure AI Foundry it costs 1.8× as much.
Updated
- Lab
- DeepSeek
- Context
- 1.05M
- Input
- Text
- Providers
- 5
DigitalOcean$1.31Lowest
DeepInfra$1.631.2×
Alibaba Cloud$1.771.4×
Novita AI$2.001.5×
Azure AI Foundry$2.391.8×
Every price, by provider
| Provider | Input | Output | Cached | Cache write | Batch in | Batch out | Context | Max output |
|---|---|---|---|---|---|---|---|---|
| DigitalOcean | $1.044 | $2.088 | $0.2088 | – | – | – | 1.05M | 384K |
| DeepInfrafp8 | $1.30 | $2.60 | $0.10 | – | – | – | 1.05M | 393K |
| Alibaba Cloudfp8 | $1.416 | $2.832 | $0.118 | – | – | – | 1M | 393K |
| Novita AIfp8 | $1.60 | $3.20 | $0.135 | – | – | – | 1.05M | 393K |
| Azure AI Foundry | $1.91 | $3.83 | $0.16 | – | – | – | 1.05M | 384K |
Prices in US dollars. Token prices are per 1 million tokens. abracadabra compiles them from each provider’s listing on OpenRouter, the LiteLLM price list and the providers’ own pricing pages, and refreshes them daily. The dataset is free to use: /api/ai-pricing.
See which tasks your agent finishes.
A price says what a call costs. abracadabra reads every conversation your agent has and shows the topics people bring, the tasks that get done and the turn where the rest stop.
Free to start, no card. Or open the playground (opens in a new tab).