Using DeepSeek V3 on Replicate API
Implementation guide · DeepSeek V3 · DeepSeek
ServerlessOpen Source
Replicate API exposes DeepSeek V3 through model ID deepseek-ai/deepseek-v3. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-04-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
deepseek-ai/deepseek-v3— see the documentation for request format. - 3
Code Examples
Install
pip install replicateAPI key
REPLICATE_API_TOKENModel ID
deepseek-ai/deepseek-v3Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
import replicate
# reads REPLICATE_API_TOKEN from env
# deepseek-ai/deepseek-v3 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"deepseek-ai/deepseek-v3",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.45 |
| Output tokens | $1.45 |
Capabilities
JSON / Tool useStructured Outputs
About DeepSeek V3
DeepSeek V3: Latest flagship model. 685B total with MoE. 128K context. Open-source.
Model Specs
Released2024-12-26
Parameters671B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-04