🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

DeepSeek V4 Flash Released 2026-04-24

DeepSeek chat code tools
Input$0.138/M
Output$0.275/M
Cache read$0.0028/M
Context1M
vs GPT-4o~97% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.0434/M. Automatic disk KV-prefix caching: cache hits bill at the discounted cache-read rate with no opt-in and no write fee.

Use DeepSeek V4 Flash in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

About DeepSeek V4 Flash

284B-parameter MoE with 13B activated
Hybrid sparse attention cuts long-context costs
MIT-licensed weights with 1M-token context

DeepSeek V4 Flash is the fast, economical member of the open-source DeepSeek-V4 series: a Mixture-of-Experts model with 284B total parameters and 13B activated.

  • It carries the series' 1M-token context window as standard and supports non-thinking and thinking modes, including higher reasoning-effort settings.
  • DeepSeek highlights hybrid sparse-attention innovations that sharply cut long-context inference compute and KV-cache cost versus DeepSeek-V3.2, with reasoning performance approaching V4 Pro at lower price and latency.
  • Weights are MIT-licensed.
  • Synthorai serves DeepSeek V4 Flash via its OpenAI-compatible endpoint with no client changes required.

Specs & limits

Max output (vendor spec)393,216
Modalitiestext → text
Parameters284B total · 13B active (MoE)
Featurestools · structured_output · streaming · reasoning · caching
LicenseMIT ↗
Notable284B/13B active MoE, 1M context, Thinking + Non-Thinking modes; hybrid sparse attention, FP4+FP8 mixed precision; the fast, economical V4 variant.
Prompt cachingautomatic

per DeepSeek official docs ↗

FAQ

Is the DeepSeek V4 Flash API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.138/M input tokens, that credit alone covers roughly 905 requests of ~8K tokens against DeepSeek V4 Flash.

What is DeepSeek V4 Flash best at?

284B-parameter MoE with 13B activated, plus hybrid sparse attention cuts long-context costs and MIT-licensed weights with 1M-token context. See the About section for the full picture from the vendor's own release notes.

How much does DeepSeek V4 Flash cost?

DeepSeek V4 Flash costs $0.138 per million input tokens and $0.275 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.0028/M.

Does DeepSeek V4 Flash support prompt caching?

Yes, automatically: DeepSeek-served prompts cache with no code changes. Cached input tokens bill at $0.0028/M vs $0.138/M uncached. Prompt caching guide →

How do I get access to DeepSeek V4 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="deepseek-v4-flash", and you're done. One API key covers every model on the gateway.

Is DeepSeek V4 Flash open source?

Yes: the weights are published under the MIT license. Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →

Related models

Get your free API key Compare your cost →