import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "deepseek/deepseek-v4-flash", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "deepseek/deepseek-v4-flash", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"deepseek/deepseek-v4-flash","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Terminal-Bench | 56.9% | Autonomous shell/terminal task completion | Source | July 12, 2026 |
| LiveCodeBench | 91.6% | Contamination-free competitive programming problems | Source | July 12, 2026 |
| GPQA Diamond | 88.1% | Google-proof graduate science questions (hardest subset) | Source | July 12, 2026 |
| SWE-bench Verified | 79% | Resolving verified real GitHub issues | Source | July 12, 2026 |
| Intelligence | 34.5 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 69.1 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
DeepSeek V4 Flash This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
DeepSeek V4 Flash has a 1,000,000 tokens context window and can return up to 384,000 tokens.
DeepSeek V4 Flash takes text as input and returns text.
Use deepseek/deepseek-v4-flash as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
DeepSeek V4 Flash became available on April 24, 2026.
DeepSeek V4 Flash is priced at input $0.39 / 1M tokens, output $1.56 / 1M tokens, cached input $0.0078 / 1M tokens.
Yes, DeepSeek V4 Flash can stream responses as they are generated.
DeepSeek V4 Flash was built by DeepSeek.
It is a chat and reasoning model supporting both standard and deeper thinking modes for various language tasks.