DeepSeek v3
Replicate textreplicate/deepseek-ai/deepseek-v3
Input
$1.45
per 1M input tokens
Output
$1.45
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
65,536
Max output
8,192
Effective date
Jun 15, 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)One price on record so far (Jun 15, 2026). This chart fills in as the price changes over time. We check daily.
| Effective | Input | Output | Blended |
|---|---|---|---|
| Jun 15, 2026 | $1.45 | $1.45 | $1.45 |
DeepSeek v3 on other providers
Inferenceapis
· $0.1900 in / $0.3800 out
Inferenceapis
· $0.1900 in / $0.3800 out
Hyperbolic
· $0.2000 in / $0.2000 out
DeepSeek
· $0.2700 in / $1.10 out
Streamlake
· $0.2860 in / $1.14 out
Deepinfra
· $0.3200 in / $0.8900 out
Nebius
· $0.5000 in / $1.50 out
Kyma
· $0.5180 in / $0.7571 out
Fireworks Ai
· $0.9000 in / $0.9000 out
Vercel Ai Gateway
· $0.9000 in / $0.9000 out
Azure OpenAI
· $1.14 in / $4.56 out
Together Ai
· $1.25 in / $1.25 out
Other Replicate models
replicate/ibm-granite/granite-speech-3.3-8b
· $4.90/Mtok out
replicate/ibm-granite/granite-vision-3.3-2b
· $0.2500/Mtok out
replicate/ibm-granite/granite-3.3-8b-instruct
· $0.2500/Mtok out
replicate/ibm-granite/granite-3.0-2b-instruct
· $0.2500/Mtok out
replicate/ibm-granite/granite-3.1-2b-instruct
· $0.2500/Mtok out
replicate/ibm-granite/granite-3.1-8b-instruct
· $0.2500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.