DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 preview weights, a higher-capability hybrid-thinking model with 1M context and 384K max output.
- Input price
- $0.99list $1.6540% off
- Output price
- $1.9806list $3.30140% off
- Context
- 1M
- Max output
- 384K
- Capability
- 150 (#60 of 82)
- Human preference
- 1451
- 30-day uptime
- —
- Released
- 2026-04-24
InputTextOutputText
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
All prices for this model, by service tier.
- Input
- $0.99list $1.6540% off
- per 1M tokens
- Output
- $1.9806list $3.30140% off
- per 1M tokens
- Cache read
- $0.0828list $0.13840% off
- per 1M tokens
- Explicit cache read
- $0.099list $0.16540% off
- per 1M tokens
- Cache write (5 min)
- $1.2375list $2.062540% off
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.00396
- 3K input tokens
- Agent first turn
- $0.125
- 100K tokens of context, none cached
- Each later agent turn
- $0.0117
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $0.348
- 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