Model Library
DeepSeekReleased April 24, 2026DeepSeek V4 Pro
DeepSeek · Released April 24, 2026
Intelligence score
31
At a glance
- Intelligence
- 31
- Speed
- 70.5tokens/sec
- Latency
- 2.03stime to first token
- Input price
- $0.43per 1M tokens
- Output price
- $0.87per 1M tokens
- Context window
- 4tokens
- Parameters
- 49billions
Summary
Comparison summary
DeepSeek V4 Pro (Non-reasoning) scores 31 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17). DeepSeek V4 Pro (Non-reasoning) generates output at 70.5 tokens per second (based on DeepSeek's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 58.7 t/s). DeepSeek V4 Pro (Non-reasoning) costs $0.43 per 1M input tokens (better than average, median: $0.60) and $0.87 per 1M output tokens (very competitive, median: $2.40), based on DeepSeek's API.
Specifications
Technical specifications
| Model name | DeepSeek V4 Pro |
|---|---|
| Provider | DeepSeek |
| Release date | April 24, 2026 |
| Intelligence score | 31 |
| Speed | 70.5 tokens/sec |
| Latency (TTFT) | 2.03s |
| Input price | $0.43 / 1M tokens |
| Output price | $0.87 / 1M tokens |
| Context window | 4 tokens |
| Parameters | 49B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Mit |
| API availability | — |
| Source | Model Intelligence legacy profile: deepseek-v4-pro-non-reasoning |
Pricing
Token prices
Price per 1M tokens
DeepSeek V4 Pro, as listed in the catalog record
- Input$0.43
- Output$0.87
| Token type | Price per 1M |
|---|---|
| Input | $0.43 |
| Output | $0.87 |
Model Intelligence legacy profile: deepseek-v4-pro-non-reasoning
FAQ · 20
Frequently asked questions
DeepSeek V4 Pro (Non-reasoning) was released on April 24, 2026.
DeepSeek V4 Pro (Non-reasoning) was created by DeepSeek.
DeepSeek V4 Pro (Non-reasoning) scores 31 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17).
DeepSeek V4 Pro (Non-reasoning) generates output at 70.5 tokens per second (based on DeepSeek's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 58.7 t/s).
DeepSeek V4 Pro (Non-reasoning) has a time to first token (TTFT) of 2.03s (based on DeepSeek's API), which is better than average compared to other open weight non-reasoning models of similar size (median: 2.28s).
DeepSeek V4 Pro (Non-reasoning) costs $0.43 per 1M input tokens (better than average, median: $0.60) and $0.87 per 1M output tokens (very competitive, median: $2.40), based on DeepSeek's API.
DeepSeek V4 Pro (Non-reasoning) costs $0.43 per 1M input tokens and $0.87 per 1M output tokens (based on DeepSeek's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.18 per 1M tokens. Pricing may vary by provider.
No, DeepSeek V4 Pro (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek V4 Pro (Non-reasoning) supports text input.
DeepSeek V4 Pro (Non-reasoning) supports text output.
No, DeepSeek V4 Pro (Non-reasoning) does not support image input. It can only process text.
No, DeepSeek V4 Pro (Non-reasoning) is not multimodal. It only supports text input.
DeepSeek V4 Pro (Non-reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek V4 Pro (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek V4 Pro (Non-reasoning) has 1.6 trillion parameters (49 billion active).
DeepSeek V4 Pro (Non-reasoning) is a Mixture of Experts (MoE) model with 1.6 trillion total parameters, but only 49 billion active parameters are used during inference.
DeepSeek V4 Pro (Non-reasoning) is released under the Mit license. This license allows commercial use.
DeepSeek V4 Pro (Non-reasoning) achieves a score of 31 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, DeepSeek V4 Pro (Non-reasoning) is available via API through 4 providers.
DeepSeek V4 Pro (Non-reasoning) is available through 4 API providers.