DeepSeek Math 7B on Replicate API

DeepSeek Math · DeepSeek

ServerlessOpen Weights

Last refreshed 2026-09-18. Next refresh: weekly.

Why use DeepSeek Math 7B on Replicate API?

Replicate API offers DeepSeek Math 7B with pay-as-you-go pricing at $0.05/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Input / 1M
$0.050
Output / 1M
$0.25
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-math-7b",
    input={"prompt": "Hello"}
Model ID
deepseek-math-7b

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# deepseek-math-7b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "deepseek-math-7b",
    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.

Pricing

TypePrice (per 1M)
Input tokens$0.05
Output tokens$0.25

Capabilities

No model capability flags are currently sourced.

About DeepSeek Math 7B

DeepSeek Math 7B is a powerful family of large language models by DeepSeek AI, crafted for advanced mathematical reasoning. The base model begins as DeepSeek-Coder-v1.5 7B, further pre-trained with 500 billion tokens, encompassing math-focused and general data sources. This model attains a 51.7% score on the MATH benchmark, demonstrating competitive prowess without external aids. Enhanced by instruction tuning, DeepSeekMath-Instruct 7B boosts its mathematical expertise. The DeepSeekMath-RL 7B model, further refined by a novel Group Relative Policy Optimization algorithm, capitalizes on reinforcement learning for superior performance.

Get Started

Model Specs

Released2024-02-05
Parameters7B
ArchitectureDecoder Only