--- title: "DeepSeek-R1 Cost Calculator - SambaNova" description: "Calculate the cost of using DeepSeek-R1 from SambaNova. Input costs $5.00 and output $7.00 per 1M tokens." url: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-r1" markdown: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-r1.md" --- # DeepSeek-R1 Cost Calculator - SambaNova > Calculate the cost of using DeepSeek-R1 from SambaNova. Input costs $5.00 and output $7.00 per 1M tokens. ## Important Links - [View MCP Gateway](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources/mcp-gateway.md) - [Features](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/#features) - [Enterprise](https://www.getmaxim.ai/enterprise) - [Pricing](https://www.getmaxim.ai/pricing) - [Docs](https://docs.getbifrost.ai) - [GitHub](https://github.com/maximhq/bifrost) - [Book a Demo](https://www.getmaxim.ai/book-a-demo) ## About DeepSeek-R1 DeepSeek-R1 is a chat model from SambaNova, one of 19 chat models they offer. It is priced at $5.00 per 1M input tokens and $7.00 per 1M output tokens, ranking 3008 out of 3254 chat models by cost and cheaper than 6% of models in this category. It accepts up to 33K input tokens. ## Pricing Published SambaNova pricing for DeepSeek-R1. - **$5.00 / 1M tokens Input.** - **$7.00 / 1M tokens Output.** ## Technical Specifications - **Chat Mode.** - **32,768 Max Input Tokens.** - **32,768 Max Output Tokens.** - **32,768 Max Tokens.** ## How Pricing Compares At $5.00 per 1M input tokens and $7.00 per 1M output tokens, DeepSeek-R1 ranks 3008 out of 3254 chat models by input cost. It is more expensive compared to the median of $0.52 for chat models, and is cheaper than 6% of models in this category. | Model | Provider | Input $/1M | Output $/1M | vs DeepSeek-R1 | | --- | --- | --- | --- | --- | | anthropic.claude-opus-4-5-20251101-v1:0 | AWS Bedrock | $5.00 | $25.00 | 0% | | anthropic.claude-opus-4-6-v1 | AWS Bedrock | $5.00 | $25.00 | 0% | | global.anthropic.claude-opus-4-6-v1 | AWS Bedrock | $5.00 | $25.00 | 0% | | us.anthropic.claude-opus-4-6-v1 | AWS Bedrock | $5.50 | $27.50 | +10% | | eu.anthropic.claude-opus-4-6-v1 | AWS Bedrock | $5.50 | $27.50 | +10% | ## More from SambaNova - [Meta-Llama-3.1-405B-Instruct ($5.00/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/meta-llama-3.1-405b-instruct.md) - [DeepSeek-V3-0324 ($3.00/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-v3-0324.md) - [DeepSeek-V3.1 ($3.00/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-v3.1.md) - [DeepSeek-V3.2 ($3.00/1M input)](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-v3.2.md) ## Related Resources - [All SambaNova pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova.md) ## FAQ ### Is DeepSeek-R1 cheaper than anthropic.claude-opus-4-5-20251101-v1:0? No. DeepSeek-R1 costs $5.00 per 1M input tokens while anthropic.claude-opus-4-5-20251101-v1:0 costs $5.00 per 1M input tokens, making anthropic.claude-opus-4-5-20251101-v1:0 0% more affordable for input. However, DeepSeek-R1 may offer different capabilities or performance characteristics that justify the price difference. ### How does DeepSeek-R1 pricing compare to the average chat model? DeepSeek-R1 input pricing is $5.00 per 1M tokens, which is 869% above the median of $0.52 for chat models. It ranks 3008 out of 3254 chat models by input cost, making it cheaper than 6% of models in this category. For output, it costs $7.00 per 1M tokens compared to the median of $1.50. ### What makes DeepSeek-R1 different from other SambaNova models? Among SambaNova's 19 chat models, DeepSeek-R1 ranks 18 by input cost. ### What are the best alternatives to DeepSeek-R1? The most comparable chat models to DeepSeek-R1 are: anthropic.claude-opus-4-5-20251101-v1:0 from AWS Bedrock ($5.00/1M input tokens); anthropic.claude-opus-4-6-v1 from AWS Bedrock ($5.00/1M input tokens); global.anthropic.claude-opus-4-6-v1 from AWS Bedrock ($5.00/1M input tokens); us.anthropic.claude-opus-4-6-v1 from AWS Bedrock ($5.50/1M 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. ### How do I calculate DeepSeek-R1 costs? DeepSeek-R1 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 $5.00 and generating 1M output tokens costs $7.00. ## Related Resources - [All SambaNova pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova.md) - [LLM cost calculator](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator.md) - [Model library](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library.md) - [Docs: Bifrost docs](https://docs.getbifrost.ai) - [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost) - [Pricing: Bifrost pricing](https://www.getmaxim.ai/pricing) - [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise) - [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo) - [Resources: Bifrost resources](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources.md) --- *This is a markdown version of [https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-r1](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/sambanova/model/deepseek-r1) for AI/LLM consumption.*