Mistral 7B v0.1 on Replicate API

Mistral 7B · MistralAI

ServerlessOpen Source

Last refreshed 2026-05-05. Next refresh: weekly.

Why use Mistral 7B v0.1 on Replicate API?

Replicate API offers Mistral 7B v0.1 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.

Compare Mistral 7B v0.1 across 16 providers to find the best fit for your use case
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(
    "mistralai/mistral-7b-v0.1",
    input={"prompt": "Hello"}
Model ID
mistralai/mistral-7b-v0.1

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# mistralai/mistral-7b-v0.1 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "mistralai/mistral-7b-v0.1",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "mistralai/mistral-7b-v0.1", not the LLMReference slug "mistral-7b-v0.1".
  • 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 Mistral 7B v0.1 Across Providers

ProviderInput (per 1M)Output (per 1M)
GCP Vertex AI$0.08$0.24
OctoAI API (Deprecated)——
DeepInfra$0.05$0.15
Mistral AI Studio$0.25$0.25
Baseten API——
View all 16 providers →

Pricing

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

Capabilities

No model capability flags are currently sourced.

About Mistral 7B v0.1

Mistral 7B v0.1 is an advanced open-source large language model built by Mistral AI, consisting of 7 billion parameters. It's designed to deliver high performance and efficiency, outperforming many similar-sized models in various benchmarks. The model employs a transformer architecture with innovative features like Sliding Window Attention, Grouped-Query Attention, and a Byte-fallback BPE tokenizer, enhancing speed, reducing computational costs, and improving robustness. Capable of generating human-like text, following instructions effectively, and excelling in areas such as reasoning and mathematics, Mistral 7B v0.1 does have limitations, such as a lack of built-in moderation and a potential for hallucinations.

Get Started