No KYC
No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.
Navigation
MODEL REFERENCE
DeepSeek V4 Flash
A text model for long-context reasoning, coding and tool workflows, with a configured 1,048,576-token window.
No added content filters
WeightsAPI adds no content filter at the gateway. A model’s own training can still lead it to refuse a request.
INPUT / 1M$0.09
OUTPUT / 1M$0.18
SERVICE CONTEXT*128K
MEASURED SPEED— not measured
API model IDdeepseek-ai/DeepSeek-V4-Flash
Published context1,048,576 tokens
QuantizationNot verified
LicenseMIT ↗
Best for#
Long text analysis, coding and tool workflows that warrant evaluating different reasoning budgets. DeepSeek publishes this checkpoint as an early release with non-thinking and reasoning modes. Check the publisher’s release status and capabilities in the model card.
Choose another model when#
Your application needs image input or a serving stack without DeepSeek-V4 support. This is a text model with a dedicated conversation encoding format. Encoding reference.
Deployment details#
The configuration supports 1,048,576 positions using YaRN scaling. Serving must handle its encoding, mixed-precision weights and output parsing. Publisher specifications are separate from WeightsAPI availability. Confirm the service context, serving precision and supported modes for the selected deployment.
Shared inference is billed at the input and output prices shown on this page, in USD per million tokens. The same rates apply throughout WeightsAPI’s service context window; no cache or batch discount applies to this standard rate. Confirm the deployed context before using the listed 131,072-token service ceiling. See pricing and service status before use.
License and provenance#
The exact official checkpoint is deepseek-ai/DeepSeek-V4-Flash. Its repository and weights are released under the MIT License.
Call this model#
Prepare model: "deepseek-ai/DeepSeek-V4-Flash" using the quickstart. On an available deployment, validate reasoning-mode settings and tool parsing with short inputs before using long contexts.
Sign-in, one confirmed top-up of at least USD 100 and enough available credit are required for AI access. Published prices do not activate a model: check service status for deployment availability.
Request example
curl https://weightsapi.com/v1/chat/completions \
-H "Authorization: Bearer $WEIGHTSAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-ai/DeepSeek-V4-Flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'