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 12 providers to find the best fit for your use caseInput / 1M
$1.45
Output / 1M
$1.45
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"deepseek-v3",
input={"prompt": "Hello"}Model ID
deepseek-v3Request example
import replicate
# reads REPLICATE_API_TOKEN from env
# deepseek-v3 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"deepseek-v3",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- 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
| 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 | $1.45 |
| Output tokens | $1.45 |
Capabilities
Function CallingTool UseStructured Outputs
About DeepSeek V3
DeepSeek V3: Latest flagship model. 685B total with MoE. 128K context. Open-source.
FAQ
What does DeepSeek V3 cost on Replicate API?
On Replicate API, DeepSeek V3 costs $1.45 per 1M input tokens and $1.45 per 1M output tokens.
What is the context window for DeepSeek V3 on Replicate API?
DeepSeek V3 supports a 64,000 token context window on Replicate API.
How does Replicate API compare to other DeepSeek V3 providers?
DeepSeek V3 is available from 12 providers. The cheapest input pricing is $0.1/1M tokens from Bitdeer AI.
Who created DeepSeek V3?
DeepSeek V3 was created by DeepSeek as part of the DeepSeek V3 model family.
Is DeepSeek V3 open source?
DeepSeek V3 is open source according to the seed data.
Get Started
Model Specs
Released2024-12-26
Parameters671B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-04