DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro-0423DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes
Context
1M
1,000,000 tokens
Max output
384K
384,000 tokens
Input
$1.32
per 1M tokens
Output
$3.96
per 1M tokens
Providers
2
2 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Ofox
| Token type | Standard |
|---|---|
| Input | $1.32 |
| Output | $3.96 |
| Cache read | $0.15 |
Lowest input price across providers: $1.32.
Capabilities
ReasoningYes
On / off · Effort: high, max
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsYes
ModeratedUnknown
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 2
2 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Merge Gateway | deepseek/deepseek-v4-pro-0423 | 1M | — | 393K | $1.65 | $3.30 | — | — | — | — | — | Yes | Yes | Yes | Yes | Apr 23, 2026 |
 Ofox | deepseek/deepseek-v4-pro-0423 | 1M | — | 384K | $1.32 | $3.96 | — | $0.15 | — | — | — | Yes | Yes | Yes | Yes | Apr 23, 2026 |