DeepSeek V4
DeepSeekUpdated March 2026. DeepSeek V4 by DeepSeek: $0.30/M input, $0.50/M output tokens. 1.0M context, 16K max output. Function Calling & JSON Mode. Free calculator + compare 40+ models.
Input Price
$0.30
per 1M tokens
Output Price
$0.50
per 1M tokens
Context Window
1.0M
tokens
Specifications
| Provider | DeepSeek |
| Model ID | deepseek-v4 |
| Input Price | $0.3 / 1M tokens |
| Output Price | $0.5 / 1M tokens |
| Context Window | 1.0M tokens |
| Max Output | 16K tokens |
| Capabilities | textfunction_callingstructured_output |
| Release Date | 2026-02 |
| Notes | 1T params, hybrid reasoning + generation. Open-weight. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split).
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.12 | $1.44 |
| 50K | $0.60 | $7.20 |
| 100K | $1.20 | $14.40 |
| 500K | $6.00 | $72.00 |
| 1.0M | $12.00 | $144.00 |
About DeepSeek V4
DeepSeek V4 is a large language model by DeepSeek. It features a 1.0M token context window with up to 16K tokens of output per request. The model supports 3 capabilities: text, function_calling, structured_output.
At $0.3 per million input tokens and $0.5 per million output tokens, DeepSeek V4 is positioned as a cost-effective option in the DeepSeek lineup. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
DeepSeek V4 Key Details
- Pricing: $0.3/M input tokens, $0.5/M output tokens
- Context window: 1.0M tokens — one of the largest available
- Max output: 16K tokens per response
- Capabilities: text, function_calling, structured_output
- Highlights: 1T params, hybrid reasoning + generation. Open-weight.
- Released: 2026-02
Other DeepSeek Models
Similar Price Range
Related Tools
FAQ
How much does DeepSeek V4 cost?
DeepSeek V4 costs $0.3 per million input tokens and $0.5 per million output tokens. For a typical workload of 100K tokens/day, expect approximately $1.65/month.
What is DeepSeek V4's context window?
DeepSeek V4 supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 16K tokens.
Is DeepSeek V4 good for my use case?
DeepSeek V4 supports text, function_calling, structured_output. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.