DeepSeek V4.1 Flash
deepseek-v4.1-flashOperationalDeepSeek V4.1 Flash is DeepSeek's language model, available through the FlyRouter API. Input costs $0.01275 and output costs $0.14175 per 1M tokens. That is 75% below the official price.
API pricing
USD per 1M tokens ·
| Uncached input | Output | Cache read | Cache write (5 min) |
|---|---|---|---|
| $0.01275 | $0.14175 | $0.001875 | $0.01275 |
Rates below use a single public group, with the same group selection as the pricing directory. Your key's group and the rules at request time determine the charge. At page load, the server uses snapshots no older than 5 minutes. Reload for an updated quote.
Live status
- 24h success rate
- 100.0%
- Avg. response latency
- 5.0 s
- Avg. generation speed
- 198 tokens/s
- Success rate ≥ 95%
- 80% – 95%
- < 80%
- No requests this hour
Measured from real requests through the gateway over the last 24 hours. Each bar is one hour, oldest on the left.
API access
cURL
curl https://api.flyrouter.ai/v1/chat/completions \
-H "Authorization: Bearer $FLYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'
FlyRouter