Calculate the cost of using deepseek-v3 from Replicate for your AI applications
Pricing data last updated:
Mode: Chat
Max: 65,536 tokens
Max: 8,192 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
deepseek-v3 is a chat model from Replicate, one of 40 chat models they offer. It is priced at $1.45 per 1M input tokens and $1.45 per 1M output tokens, ranking 1676 out of 2292 chat models by cost and cheaper than 27% of models in this category. deepseek-v3 supports function calling. It accepts up to 66K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 65,536 input tokens. The maximum output length is 8,192 tokens.
At $1.45 per 1M input tokens and $1.45 per 1M output tokens, deepseek-v3 ranks 1676 out of 2292 chat models by input cost. It is more expensive compared to the median of $0.55 for chat models, and is cheaper than 27% of models in this category.
deepseek-v3 is one of 40 Replicate chat models, with support for function calling.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs deepseek-v3 |
|---|---|---|---|---|
| gpt-5-2025-08-07 | Azure | $1.38 | $11.00 | -5% |
| gpt-5.1 | Azure | $1.38 | $11.00 | -5% |
| gpt-5.1-chat | Azure | $1.38 | $11.00 | -5% |
Similar chat models from other providers
No. deepseek-v3 costs $1.45 per 1M input tokens while gpt-5-2025-08-07 costs $1.38 per 1M input tokens, making gpt-5-2025-08-07 5% more affordable for input. However, deepseek-v3 may offer different capabilities or performance characteristics that justify the price difference.
deepseek-v3 input pricing is $1.45 per 1M tokens, which is 164% above the median of $0.55 for chat models. It ranks 1676 out of 2292 chat models by input cost, making it cheaper than 27% of models in this category. For output, it costs $1.45 per 1M tokens compared to the median of $1.50.
Among Replicate's 40 chat models, deepseek-v3 ranks 29 by input cost.
The most comparable chat models to deepseek-v3 are: gpt-5-2025-08-07 from Azure ($1.38/1M input tokens); gpt-5.1 from Azure ($1.38/1M input tokens); gpt-5.1-chat from Azure ($1.38/1M input tokens); o1-mini-2024-09-12 from Azure ($1.21/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
You can monitor Replicate service health in real time on the Bifrost Replicate Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
deepseek-v3 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $1.45 and generating 1M output tokens costs $1.45.
