DeepSeek V4 Pro 0813
Inferenceapis textinferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813
Input
$1.72
per 1M input tokens
Output
$5.15
per 1M output tokens
Cache read
$0.1700
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,048,576
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 | $1.72 | $5.15 | $2.58 |
| Oct 16, 2026 | $1.72 | $5.15 | $2.58 |
DeepSeek V4 Pro 0813 on other providers
Sail
· $0.9200 in / $2.77 out
Gmi
· $1.06 in / $3.17 out
Deepinfra
· $1.30 in / $2.60 out
Wandb
· $1.31 in / $3.96 out
Baseten
· $1.32 in / $3.96 out
Openrouter
· $1.32 in / $3.96 out
Fireworks Ai
· $1.32 in / $3.96 out
Nebius
· $1.32 in / $3.96 out
Tencent
· $1.32 in / $3.96 out
Novita
· $1.32 in / $3.96 out
Streamlake
· $1.32 in / $3.96 out
Fireworks Ai
· $1.32 in / $3.96 out
Other Inferenceapis models
inferenceapis/gpt-oss-20b
· $0.1900/Mtok out
inferenceapis/openai/gpt-oss-20b
· $0.1900/Mtok out
inferenceapis/Qwen/Qwen3.8-Flash
· $0.5000/Mtok out
inferenceapis/qwen3.8-flash
· $0.5000/Mtok out
inferenceapis/deepseek-ai/DeepSeek-V3
· $0.3800/Mtok out
inferenceapis/deepseek-ai/DeepSeek-V4-Flash
· $0.3800/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.