Last refreshed 2026-06-29. Next refresh: weekly.
Why use DeepSeek V3 on SiliconFlow?
SiliconFlow offers DeepSeek V3 with pay-as-you-go pricing at $0.15/1M input tokens. SiliconFlow is a model serving platform for open and closed model inference, offering fast and cost-effective API access to popular AI models.
Compare DeepSeek V3 across 13 providers to find the best fit for your use caseInput / 1M
$0.15
Output / 1M
$0.50
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: deepseek-v3Model ID
deepseek-v3Request example
Curated snippets for this provider have not been sourced yet.
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare DeepSeek V3 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| DeepInfra | $0.32 | $0.89 |
| Fireworks AI | $0.56 | $1.68 |
| DeepSeek Platform | $0.14 | $0.28 |
| Microsoft Foundry | — | — |
| OpenRouter | $0.25 | $0.38 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $0.50 |
Capabilities
JSON / Tool useStructured Outputs
About DeepSeek V3
DeepSeek V3: Latest flagship model. 685B total with MoE. 128K context. Open-source.
Get Started
Model Specs
Released2024-12-26
Parameters671B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-04