Calculate the cost of using deepseek-reasoner from DeepSeek for your AI applications
Pricing data last updated:
Mode: Chat
Max: 131,072 tokens
Max: 65,536 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
deepseek-reasoner is a chat model from DeepSeek, one of 8 chat models they offer. It is priced at $0.14 per 1M input tokens and $0.28 per 1M output tokens, ranking 409 out of 2292 chat models by cost and cheaper than 81% of models in this category. deepseek-reasoner supports reasoning, prompt caching, structured output — one of only 3 chat models with this combination. It accepts up to 131K 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 131,072 input tokens. The maximum output length is 65,536 tokens.
At $0.14 per 1M input tokens and $0.28 per 1M output tokens, deepseek-reasoner ranks 409 out of 2292 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 81% of models in this category.
deepseek-reasoner is one of 8 DeepSeek chat models, one of only 3 chat models combining prompt caching, reasoning, structured output.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs deepseek-reasoner |
|---|---|---|---|---|
| mimo-v2.5 | OpenRouter | $0.14 | $0.28 | 0% |
| minimax-m2.5 | OpenRouter | $0.15 | $0.90 | +7% |
| DeepSeek-V4-Flash | Tensormesh | $0.14 | $0.28 | 0% |
Similar chat models from other providers
No. deepseek-reasoner costs $0.14 per 1M input tokens while mimo-v2.5 costs $0.14 per 1M input tokens, making mimo-v2.5 0% more affordable for input. However, deepseek-reasoner may offer different capabilities or performance characteristics that justify the price difference.
deepseek-reasoner input pricing is $0.14 per 1M tokens, which is 75% below the median of $0.55 for chat models. It ranks 409 out of 2292 chat models by input cost, making it cheaper than 81% of models in this category. For output, it costs $0.28 per 1M tokens compared to the median of $1.50.
Among DeepSeek's 8 chat models, deepseek-reasoner ranks 3 by input cost. Its combination of prompt caching, reasoning, structured output is shared by only 2 other chat models.
The most comparable chat models to deepseek-reasoner are: mimo-v2.5 from OpenRouter ($0.14/1M input tokens); minimax-m2.5 from OpenRouter ($0.15/1M input tokens); DeepSeek-V4-Flash from Tensormesh ($0.14/1M input tokens); gemma-4-31B-it from Tensormesh ($0.14/1M 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 DeepSeek service health in real time on the Bifrost DeepSeek Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
deepseek-reasoner 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 $0.14 and generating 1M output tokens costs $0.28.
