DeepSeek V3 on Replicate API

DeepSeek V3 · DeepSeek

ServerlessOpen Source

Last refreshed 2026-04-19. Next refresh: weekly.

Why use DeepSeek V3 on Replicate API?

Replicate API offers DeepSeek V3 with pay-as-you-go pricing at $1.45/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare DeepSeek V3 across 13 providers to find the best fit for your use case
Input / 1M
$1.45
Output / 1M
$1.45
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "deepseek-ai/deepseek-v3",
    input={"prompt": "Hello"}
Model ID
deepseek-ai/deepseek-v3

Request example

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))

Gotchas

  • Use provider model ID "deepseek-ai/deepseek-v3", not the LLMReference slug "deepseek-v3".
  • Replicate 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.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare DeepSeek V3 Across Providers

ProviderInput (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
View all 13 providers →

Pricing

TypePrice (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.

Get Started

Model Specs

Released2024-12-26
Parameters671B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-04

Related Models on Replicate API