DeepSeek-V4-Flash

DeepSeek's fast V4 model for cost-sensitive, OpenAI-compatible text and reasoning workloads.

FastCost EfficientOpenAI Compatible

Context Window

Tokens

Max Output

384K

Tokens

Output

$0.252$0.28

10% off

1M tokens

Model Codedeepseek-v4-flash

Playground

Model Code

deepseek-v4-flash

Enter your prompt here...

Output

No output yet

Pricing

Plan	Context Window	Max Output	Input	Output	Cache Write	Cache Read
deepseek-v4-flash	1M tokens	-	-	$0.252$0.2810% off 1M tokens	-	$0.00252$0.002810% off 1M tokens

Cache Miss Input · $0.126 · 1M tokens

Cache read or cached input pricing applies to reused prompt tokens.

README

DeepSeek-V4-Flash is the lower-cost DeepSeek V4 option for enterprise teams that need responsive text generation, practical reasoning, and efficient token economics.

DeepSeek-V4-Flash is appropriate for high-volume assistants, routing tiers, extraction tasks, and latency-sensitive workflows where cost control is important.
The model's OpenAI-compatible chat interface helps teams adopt it behind existing API gateways, SDKs, and observability pipelines.
Cache-hit pricing can materially reduce repeated context cost for stable prompts, retrieval wrappers, and policy-heavy enterprise applications.

API

Use the API docs for request format, parameters, and integration details.

DeepSeek's fast V4 model for cost-sensitive, OpenAI-compatible text and reasoning workloads.

Model Code

deepseek-v4-flash

View API Docs

API

Endpoint

POST /v1/messages

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/messages" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.2
  }'

Related Models

Other models from the same vendor

GLM-5.3

Z.AI's GLM-5.3 flagship model for coding, reasoning, and agentic workloads.

GLM-5.3-Flash

Z.AI's faster, lower-cost model for coding, agentic, and multimodal workloads.

GLM-5.2

Z.AI's GLM-5.2 model for enterprise text generation, reasoning, and OpenAI-compatible API workloads.

DeepSeek-V4.1-Flash

DeepSeek's V4.1 text model, served over Claude Messages with peak token pricing.

DeepSeek-V4-Pro

DeepSeek's stronger V4 model for OpenAI-compatible reasoning, coding, and enterprise text workloads.

Kimi K3

Kimi's flagship reasoning model for long-horizon coding, visual understanding, and end-to-end knowledge work.