DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
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) |
|---|---|---|---|---|---|---|---|
| Boundless | $0.04 | $0.21 | $0.02 | — | 0.69s | 49 tps | 100.0% |
  DeepInfra | $0.06 | $0.18 | $0.01 | — | 0.72s | 56 tps | 100.0% |
  Relace | $0.07 | $0.14 | $0.01 | — | 1.07s | 72 tps | 99.9% |
 Runware | $0.08 | $0.15 | $0.01 | — | 1.73s | 97 tps | 100.0% |
 DigitalOcean | $0.08 | $0.25 | $0.03 | — | 0.47s | 224 tps | 99.4% |
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
Source: artificialanalysis.ai
Quick start
Just change base_url to use DeepSeek V4 Flash 0731 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-0731",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)FAQ
What is DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
How much does the DeepSeek V4 Flash 0731 API cost?
DeepSeek V4 Flash 0731 costs $0.44 per 1M input tokens and $1.32 per 1M output tokens when accessed through BazaarLink.
How do I use DeepSeek V4 Flash 0731 with the OpenAI SDK?
Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "deepseek/deepseek-v4-flash-0731". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.
What is the context window for DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 supports a context window of 1,048,576 tokens.
Is DeepSeek V4 Flash 0731 available for free?
DeepSeek V4 Flash 0731 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