DeepSeek-V3
DeepSeek-V3, the widely used open-weight MoE chat model, available across inference gateways at low cost.
Source: DeepSeek API models, DeepSeek models
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $0.2002 / M |
| Output | $0.8001 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Compare providers
The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
StreamLakeLowest | $0.2002 | $0.8001 | — | — | via OpenRouter |
DeepInfra | $0.24 | $0.9 | $0.135 | — | via OpenRouter |
SiliconFlow | $0.25 | $1 | — | — | via OpenRouter |
Novita | $0.27 | $1.12 | $0.135 | — | via OpenRouter |
GMICloud | $0.29 | $1.14 | $0.11 | — | via OpenRouter |
Fireworks AI | $0.56 | $1.68 | — | — | Direct |
Together AI | $0.6 | $1.7 | — | — | Direct |
Azure AI Foundry | $1.14 | $4.56 | — | — | Direct |
Azure AI Foundry · Data zone | $1.25 | $5 | — | — | Direct |
Azure AI Foundry · Regional | from$1.25 | $5 | — | — | Direct |
Regional deployments are priced per region; the lowest available region rate is shown.
Price history
Has this model gotten cheaper or more expensive?
| Effective | Input / Output | Status |
|---|---|---|
| July 10, 2026 – July 17, 2026 | $0.2002 / $0.8001 | past |
| July 17, 2026 – July 19, 2026 | $0.2002 / $0.8001 | past |
| July 19, 2026 | $0.2002 / $0.8001 | current |
More from DeepSeek
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every DeepSeek-V3 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.
