DeepSeek V4 Flash
Fast 1M-context MoE model for chat, coding, and agents
DeepSeek's efficiency-first V4 model: a 284B-parameter Mixture-of-Experts with 13B active parameters, a 1M-token context window, optional thinking mode, and native tool calling for chat, coding, and agent loops.
Live playground
Try DeepSeek V4 Flash in your browser
Run the model, inspect its schema, then move the same request into production with one imageat API key.
Sign in to use the live model.
Your response will appear here
DeepSeek V4 Flash at a glance
DeepSeek's efficiency-first V4 model: a 284B-parameter Mixture-of-Experts with 13B active parameters, a 1M-token context window, optional thinking mode, and native tool calling for chat, coding, and agent loops.
- Developer
- DeepSeek
- Released
- April 2026
- Architecture
- Mixture-of-Experts, hybrid compressed sparse attention
- Parameters
- 284B total, 13B active per token
- Context window
- 1,000,000 tokens
- Input / output
- Text in, text out (no image, audio, or video input)
- Reasoning
- Thinking mode with low, medium, or high effort, or off
- Tool calling
- Native function calls, parallel calls
- Weights
- Open, MIT license (FP4 + FP8 mixed precision)
- imageat model ID
- deepseek/v4-flash
DeepSeek V4 Flash API pricing
API-key requests are billed on the tokens each request actually uses, rounded up to the cent. Reasoning tokens count as output, so thinking mode costs more than direct answers. In the playground, website credits are reserved and settle to the measured cost; most short answers use 1 credit.
Input
$0.88 / 1M tokens
Output (incl. reasoning)
$2.64 / 1M tokens
One third the price of DeepSeek V4 Pro.
See all API pricesV4 Flash vs V4 Pro
DeepSeek's published results for both V4 models in their deepest thinking mode. Pro leads everywhere, by the widest margins on factual recall and terminal-based agent work; Flash stays close on math and competitive coding at a third of the price.
| Benchmark | Metric | V4 Flash | V4 Pro |
|---|---|---|---|
| MMLU-Pro | EM | 86.2 | 87.5 |
| GPQA Diamond | Pass@1 | 88.1 | 90.1 |
| Humanity's Last Exam | Pass@1 | 34.8 | 37.7 |
| SimpleQA-Verified | Pass@1 | 34.1 | 57.9 |
| LiveCodeBench | Pass@1 | 91.6 | 93.5 |
| Codeforces | Rating | 3052 | 3206 |
| HMMT 2026 Feb | Pass@1 | 94.8 | 95.2 |
| SWE-bench Verified | Resolved | 79.0 | 80.6 |
| Terminal Bench 2.0 | Accuracy | 56.9 | 67.9 |
| MRCR 1M | MMR | 78.7 | 83.5 |
Source: DeepSeek V4 model card on Hugging Face. Scores are DeepSeek's own and were not reproduced by imageat.
Call the DeepSeek V4 Flash API
One OpenAI-compatible endpoint and your imageat API key. Point any OpenAI SDK, opencode, Cline, or the Vercel AI SDK at https://api.imageat.com/v1; the /v1 is required.
messagesSystem, user, assistant, and tool messages, OpenAI format.enable_thinkingfalse skips reasoning for the fastest, cheapest answer.reasoninglow, medium (default), or high thinking effort.max_tokensCaps the reply when thinking is off (up to 4,000).tools & tool_choiceOpenAI function definitions; replies with tool_calls.parallel_tool_callsAllow several tool calls in one turn (default true).streamOpenAI-style server-sent events.user & session_idOptional identifiers for your end users and sessions.
curl https://api.imageat.com/v1/chat/completions \
-H "Authorization: Bearer iat_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/v4-flash",
"messages": [
{"role": "system", "content": "You are a senior software engineer."},
{"role": "user", "content": "Find the bug in this function and fix it."}
],
"reasoning": "high"
}'from openai import OpenAI
client = OpenAI(base_url="https://api.imageat.com/v1", api_key="iat_live_YOUR_KEY")
response = client.chat.completions.create(
model="deepseek/v4-flash",
messages=[{"role": "user", "content": "Summarize this contract in five bullet points."}],
extra_body={"enable_thinking": False}, # fastest answer; max_tokens applies
max_tokens=800,
)
print(response.choices[0].message.content)DeepSeek V4 Flash questions
How much does the DeepSeek V4 Flash API cost on imageat?
+
API-key requests are billed on measured usage at $0.88 per 1M input tokens and $2.64 per 1M output tokens, rounded up to the cent per request. Reasoning tokens count as output, so thinking mode costs more than direct answers. With website credits, most short answers settle to 1 credit.
What is the DeepSeek V4 Flash model size?
+
DeepSeek V4 Flash is a Mixture-of-Experts model with 284B total parameters, of which 13B are active for each token. That small active size is what makes it fast and cheap to run compared with DeepSeek V4 Pro (1.6T total, 49B active).
What is the context window of DeepSeek V4 Flash?
+
1 million tokens. Your messages and the completion, including reasoning, share that window.
Is DeepSeek V4 Flash OpenAI-compatible?
+
Yes. Send model "deepseek/v4-flash" to https://api.imageat.com/v1/chat/completions with your imageat API key. OpenAI SDKs, opencode, Cline, and the Vercel AI SDK work by setting the base URL to https://api.imageat.com/v1, and streaming is supported.
How do I turn thinking off?
+
Send "enable_thinking": false for the fastest, cheapest answers; max_tokens then caps the reply. Leave it on and set "reasoning" to low, medium, or high to choose how long the model thinks first. Only the final answer is returned in message.content.
Does DeepSeek V4 Flash support tool calling?
+
Yes. Pass OpenAI-format tools and the response returns tool_calls with finish_reason "tool_calls", including several parallel calls in one turn.
DeepSeek V4 Flash vs Pro: which should I use?
+
Flash for high-volume chat, extraction, coding help, and agent loops where speed and cost matter; it costs one third of Pro. Pro for the hardest agentic coding, research, and factual recall, where it scores higher (for example 67.9 vs 56.9 on Terminal Bench 2.0).
Can DeepSeek V4 Flash read images?
+
No. It is a text-only model, and requests with image content parts are rejected before any charge.
Reason with context
Use the model for analysis, planning, and multi-step knowledge work.
Build and code
Apply it to software development, structured output, and agent workflows.
Generate text
Create clear answers, summaries, drafts, and conversational experiences.
What DeepSeek V4 Flash is built for
DeepSeek's efficiency-first V4 model: a 284B-parameter Mixture-of-Experts with 13B active parameters, a 1M-token context window, optional thinking mode, and native tool calling for chat, coding, and agent loops.
- High-volume chat, extraction, and summarization
- Coding assistants and agent loops with native tool calls
- Long-document Q&A across a 1M-token context
- Thinking on for hard problems, off for the fastest answers
Call DeepSeek V4 Flash from your app
Use the OpenAI-compatible chat endpoint with your imageat API key and pay-as-you-go balance.