Model Library
DeepSeekReleased April 24, 2026DeepSeek V4 Flash
DeepSeek · Released April 24, 2026
Intelligence score
29
At a glance
- Intelligence
- 29
- Speed
- 126.4tokens/sec
- Latency
- 1.25stime to first token
- Input price
- $0.14per 1M tokens
- Output price
- $0.28per 1M tokens
- Context window
- 4tokens
- Parameters
- 284billions
Summary
Comparison summary
DeepSeek V4 Flash (Non-reasoning) scores 29 (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 Flash (Non-reasoning) generates output at 126.4 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 Flash (Non-reasoning) costs $0.14 per 1M input tokens (very competitive, median: $0.60) and $0.28 per 1M output tokens (very competitive, median: $2.40), based on DeepSeek's API.
Specifications
Technical specifications
| Model name | DeepSeek V4 Flash |
|---|---|
| Provider | DeepSeek |
| Release date | April 24, 2026 |
| Intelligence score | 29 |
| Speed | 126.4 tokens/sec |
| Latency (TTFT) | 1.25s |
| Input price | $0.14 / 1M tokens |
| Output price | $0.28 / 1M tokens |
| Context window | 4 tokens |
| Parameters | 284B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Mit |
| API availability | — |
| Source | Model Intelligence legacy profile: deepseek-v4-flash-non-reasoning |
Pricing
Token prices
Price per 1M tokens
DeepSeek V4 Flash, as listed in the catalog record
- Input$0.14
- Output$0.28
| Token type | Price per 1M |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
Model Intelligence legacy profile: deepseek-v4-flash-non-reasoning
FAQ · 20
Frequently asked questions
DeepSeek V4 Flash (Non-reasoning) was released on April 24, 2026.
DeepSeek V4 Flash (Non-reasoning) was created by DeepSeek.
DeepSeek V4 Flash (Non-reasoning) scores 29 (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 Flash (Non-reasoning) generates output at 126.4 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 Flash (Non-reasoning) has a time to first token (TTFT) of 1.25s (based on DeepSeek's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 2.28s).
DeepSeek V4 Flash (Non-reasoning) costs $0.14 per 1M input tokens (very competitive, median: $0.60) and $0.28 per 1M output tokens (very competitive, median: $2.40), based on DeepSeek's API.
DeepSeek V4 Flash (Non-reasoning) costs $0.14 per 1M input tokens and $0.28 per 1M output tokens (based on DeepSeek's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.06 per 1M tokens. Pricing may vary by provider.
No, DeepSeek V4 Flash (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
DeepSeek V4 Flash (Non-reasoning) supports text input.
DeepSeek V4 Flash (Non-reasoning) supports text output.
No, DeepSeek V4 Flash (Non-reasoning) does not support image input. It can only process text.
No, DeepSeek V4 Flash (Non-reasoning) is not multimodal. It only supports text input.
DeepSeek V4 Flash (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 Flash (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek V4 Flash (Non-reasoning) has 284 billion parameters (13 billion active).
DeepSeek V4 Flash (Non-reasoning) is a Mixture of Experts (MoE) model with 284 billion total parameters, but only 13 billion active parameters are used during inference.
DeepSeek V4 Flash (Non-reasoning) is released under the Mit license. This license allows commercial use.
DeepSeek V4 Flash (Non-reasoning) achieves a score of 29 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, DeepSeek V4 Flash (Non-reasoning) is available via API through 4 providers.
DeepSeek V4 Flash (Non-reasoning) is available through 4 API providers.