AI Observatory / Model Radar
DeepSeek / deepseek/deepseek-v4-flash
DeepSeek: DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
1,048,576
Context
384,000
Max output
$0.14 / 1M
Prompt price
2026-04-24
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | DeepSeek | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.14 / 1M |
| Completion price | $0.28 / 1M | Request price | N/A |
| Context length | 1,048,576 | Max completion tokens | 384,000 |
| Supported parameters | frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p | ||
Best for
deepseek/deepseek-v4-flash
DeepSeek: DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Long context
High-volume usage
Coding workflows
new
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.