Calculate the cost of using deepseek-v4-pro:variant3 from Empiriolabs for your AI applications
Pricing data last updated:
Mode: Chat
Max: 1,000,000 tokens
Max: 393,216 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
deepseek-v4-pro:variant3 is a chat model from Empiriolabs, one of 92 chat models they offer. It is priced at $2.40 per 1M input tokens and $4.80 per 1M output tokens, ranking 3430 out of 4195 chat models by cost and cheaper than 18% of models in this category. deepseek-v4-pro:variant3 supports function calling, reasoning, structured output. Its 1,000K-token context window is in the top 30% among chat models.
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 1,000,000 input tokens. The maximum output length is 393,216 tokens.
At $2.40 per 1M input tokens and $4.80 per 1M output tokens, deepseek-v4-pro:variant3 ranks 3430 out of 4195 chat models by input cost. It is more expensive compared to the median of $0.60 for chat models, and is cheaper than 18% of models in this category.
deepseek-v4-pro:variant3 is one of 92 Empiriolabs chat models, with support for function calling, reasoning, structured output. its 1,000K-token context window places it in the top 30% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs deepseek-v4-pro:variant3 |
|---|---|---|---|---|
| abliterated-model-large | Abliteration | $3.00 | $5.00 | +25% |
| abliterated-model-large-v2 | Abliteration | $3.00 | $5.00 | +25% |
| anthropic.claude-3-7-sonnet-20240620-v1:0 | AWS Bedrock | $3.00 | $15.00 | +25% |
Similar chat models from other providers
Yes. deepseek-v4-pro:variant3 costs $2.40 per 1M input tokens compared to abliterated-model-large's $3.00 per 1M input tokens, making it 25% more affordable. Both are chat models and share support for function calling, reasoning, prompt caching, structured output.
deepseek-v4-pro:variant3 input pricing is $2.40 per 1M tokens, which is 300% above the median of $0.60 for chat models. It ranks 3430 out of 4195 chat models by input cost, making it cheaper than 18% of models in this category. For output, it costs $4.80 per 1M tokens compared to the median of $1.88.
Among Empiriolabs's 92 chat models, deepseek-v4-pro:variant3 ranks 78 by input cost.
The most comparable chat models to deepseek-v4-pro:variant3 are: abliterated-model-large from Abliteration ($3.00/1M input tokens); abliterated-model-large-v2 from Abliteration ($3.00/1M input tokens); anthropic.claude-3-7-sonnet-20240620-v1:0 from AWS Bedrock ($3.00/1M input tokens); anthropic.claude-3-7-sonnet-20250219-v1:0 from AWS Bedrock ($3.00/1M 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.
deepseek-v4-pro:variant3 supports up to 1,000,000 input tokens, placing it in the top 30% of chat models by context window size (rank 1079 of 3925). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
deepseek-v4-pro:variant3 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 $2.40 and generating 1M output tokens costs $4.80.