Mixtral 8x22B Instruct v0.1 on Replicate API

Mixtral · MistralAI

ServerlessOpen Source

Last refreshed 2026-05-19. Next refresh: weekly.

Why use Mixtral 8x22B Instruct v0.1 on Replicate API?

Replicate API offers Mixtral 8x22B Instruct v0.1 with pay-as-you-go pricing at $2.10/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Mixtral 8x22B Instruct v0.1 across 4 providers to find the best fit for your use case
Input / 1M
$2.10
Output / 1M
$2.10
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(
    "mixtral-8x22b-instruct-v0.1",
    input={"prompt": "Hello"}
Model ID
mixtral-8x22b-instruct-v0.1

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# mixtral-8x22b-instruct-v0.1 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "mixtral-8x22b-instruct-v0.1",
    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 Mixtral 8x22B Instruct v0.1 Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenRouter$2.00$6.00
Fireworks AI$1.20$1.20
SiliconFlow$0.65$0.65
Replicate API$2.10$2.10

Pricing

TypePrice (per 1M)
Input tokens$2.10
Output tokens$2.10

Capabilities

No model capability flags are currently sourced.

About Mixtral 8x22B Instruct v0.1

Mixtral 8x22B Instruct v0.1 is MistralAI's Mixtral model. It offers a 64K-token context window and scores 56.3 on MMLU PRO.

Get Started

Model Specs

Released2024-04-17
Parameters8x22B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-01

Related Models on Replicate API