DeepSeek V4 Pro
Wandb textwandb/deepseek-ai/DeepSeek-V4-Pro
Input
$1.15
per 1M input tokens
Output
$2.55
per 1M output tokens
Cache read
$0.2000
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,049,000
Max output
1,048,576
Effective date
Oct 27, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Oct 27, 2026 | $1.15 | $2.55 | $1.50 |
| Sep 18, 2026 | $1.15 | $2.55 | $1.50 |
| Aug 28, 2026 | $1.15 | $2.55 | $1.50 |
DeepSeek V4 Pro on other providers
Openrouter
· $0.2873 in / $0.5745 out
Clf Ai Gateway
· $0.5280 in / $1.58 out
Aiand
· $1.00 in / $2.50 out
Fireworks Ai
· $1.20 in / $1.20 out
Fireworks Ai
· $1.20 in / $1.20 out
Deepinfra
· $1.30 in / $2.60 out
Opencode Go
· $1.32 in / $3.96 out
DeepSeek
· $1.32 in / $3.96 out
DeepSeek
· $1.32 in / $3.96 out
Novita
· $1.60 in / $3.20 out
Empiriolabs
· $1.65 in / $3.30 out
Aihubmix
· $1.69 in / $3.38 out
Other Wandb models
wandb/openai/gpt-oss-120b
· $0.1700/Mtok out
wandb/openai/gpt-oss-20b
· $0.1300/Mtok out
wandb/ibm-granite/granite-4.1-8b
· $0.1000/Mtok out
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
· $0.1000/Mtok out
wandb/OpenPipe/Qwen3-14B-Instruct
· $0.2200/Mtok out
wandb/ibm-granite/granite-4.2-8b
· $0.1500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.