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...
Performance
The last 24 hours, all hosts combined. When one host fails, BazaarLink automatically routes to the next healthy one.
Hosts
Each host has its own price, and prices can differ between hosts. You can name a preferred host in your request.
| Host | Input /M | Output /M | Cache read /M | Cache write /M | First token | Throughput | Availability (24h) |
|---|---|---|---|---|---|---|---|
  Wafer | $0.10 | $0.23 | $0.10 | — | 0.49s | 80 tps | 100.0% |
 DigitalOcean | $0.11 | $0.22 | $0.03 | — | — | — | 100.0% |
  Baseten | $0.13 | $0.26 | $0.03 | — | 1.54s | 228 tps | 100.0% |
 Alibaba Cloud (Europe) | $0.14 | $0.28 | $0.03 | — | — | — | — |
| Alibaba Cloud (Japan) | $0.14 | $0.28 | $0.03 | — | — | — | — |
Benchmarks
All scores come from Artificial Analysis's independent third-party evaluation; BazaarLink takes no part in the testing.
| 1 | Muse Spark 1.3 (max) __aa_parking__58a40aba-a44f-457f-9cca-75b43d4e6934 | 76 | $1.25 / $4.25 |
| 2 | GPT-6 Astra (Non-reasoning) gpt-6-astra-non-reasoning | 76 | — / — |
| 3 | Agnes 2.5 Pro Alpha (based on Qwen3.5 397B A17B) agnes-ai/agnes-2-5-pro-alpha | 59 | $0.45 / $0.9 |
| 4 | Solar Pro 4 __aa_parking__1b64aa81-c223-4b8f-909b-82185a234765 | 53 | $0.3 / $1.2 |
| 5 | G9v3-39A5B ai9star/__aa_parking__c5ccda86-5e84-4b69-9247-6d4287fc3336 | 32 | $0 / $0 |
Price comparison
BazaarLink's price, next to the market standard Artificial Analysis observes.
BazaarLink price This site
Market reference Artificial Analysis
Quick start
Just change base_url to use DeepSeek V4 Flash through the BazaarLink API.
from openai import OpenAI
client = OpenAI(
base_url="https://api.bazaarlink.ai/v1",
api_key="sk-bl-YOUR_API_KEY",
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)FAQ
What is 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...
How much does the DeepSeek V4 Flash API cost?
DeepSeek V4 Flash costs $0.14 per 1M input tokens and $0.28 per 1M output tokens when accessed through BazaarLink.
How do I use DeepSeek V4 Flash with the OpenAI SDK?
Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "deepseek/deepseek-v4-flash". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.
What is the context window for DeepSeek V4 Flash?
DeepSeek V4 Flash supports a context window of 1,000,000 tokens.
Is DeepSeek V4 Flash available for free?
DeepSeek V4 Flash is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.
Explore
- Billed in USD with TWD quotes plus Taiwan e-invoices, so Taiwanese teams do not need an overseas card
- OpenAI-compatible API, no code rewrite
- When an upstream source has a problem, the request can try another available source; if none is available you get an error
- Chinese-language support from a local team