DeepSeek V4 Pro 0813
Deepinfra textdeepinfra/deepseek-ai/DeepSeek-V4-Pro-0813
Input
$1.30
per 1M input tokens
Output
$2.60
per 1M output tokens
Cache read
$0.1000
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 | $1.30 | $2.60 | $1.63 |
| Aug 28, 2026 | $1.30 | $2.60 | $1.63 |
DeepSeek V4 Pro 0813 on other providers
Sail
· $0.9200 in / $2.77 out
Gmi
· $1.06 in / $3.17 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
Together Ai
· $1.32 in / $3.96 out
Other Deepinfra models
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
· $0.0400/Mtok out
deepinfra/meta-llama/Llama-3.2-3B-Instruct
· $0.0200/Mtok out
deepinfra/google/gemma-4-E4B-it
· $0.1000/Mtok out
deepinfra/mistralai/Mistral-Nemo-Instruct-2407
· $0.0300/Mtok out
deepinfra/openai/gpt-oss-20b
· $0.1400/Mtok out
deepinfra/meta-llama/Meta-Llama-3-8B-Instruct
· $0.0600/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.