DeepSeek V4.1 Flash API pricing

DeepSeek's current Flash model with native multimodal support and strong coding, reasoning and agentic capabilities.

How much does DeepSeek V4.1 Flash API cost?

DeepSeek V4.1 Flash uses variable TokenGate pricing. The rates below depend on the request conditions listed in each row.

Historical pricing
Condition	Input tokens / 1M	Cached input / 1M	Output tokens / 1M
Cache hit, off-peak	$0.0030	—	—
Cache hit, peak	$0.0060	—	—
Cache miss, off-peak	$0.15	—	—
Cache miss, peak	$0.30	—	—
Output, off-peak	—	—	$0.60
Output, peak	—	—	$1.20

Pricing depends on cache hit or miss and on peak or off-peak hours.

Use DeepSeek V4.1 Flash with the OpenAI SDK

curl https://api.tokengate.com/v1/chat/completions \
  -H "Authorization: Bearer $TOKENGATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'

Change the model identifier to use another supported model through the same TokenGate integration.

Model specifications

Provider: DeepSeek
API model identifier: deepseek-flash
Generation: 4.1
Provider lifecycle: Active
Input modalities: Text, Image
Output modalities: Text
Capabilities: Streaming, Function calling, Structured outputs, Vision, Reasoning, Tool use