DeepSeek V4.1 Flash
DeepSeek V4.1 Flash: natively multimodal vision understanding with 1M context and 384K max output.
- Input price
- $0.073–$0.33list $0.14650% off
- Output price
- $0.292–$1.32list $0.58450% off
- Context
- 1M
- Max output
- 384K
- Capability
- 157 (#32 of 82)
- Human preference
- 1463
- 30-day uptime
- —
- Released
- 2026-09-10
InputTextImageOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
Prices vary by provider. Showing ByteDance (Volcano Engine), the lowest. Pick a provider above to see its prices.
Off-peakAll other times
- Input
- $0.073list $0.14650% off
- per 1M tokens
- Output
- $0.292list $0.58450% off
- per 1M tokens
- Cache read
- $0.00292
- per 1M tokens
Peak01:00–04:00, 06:00–10:00 UTCMon, Tue, Wed, Thu, Fri
- Input
- $0.146list $0.29250% off
- per 1M tokens
- Output
- $0.584list $1.16850% off
- per 1M tokens
- Cache read
- $0.00584
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.000368
- 3K input tokens
- Agent first turn
- $0.00745
- 100K tokens of context, none cached
- Each later agent turn
- $0.000588
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.0186
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text