Last refreshed 2026-06-15. Next refresh: weekly.
Why use Mixtral 8x22B v0.1 on DeepInfra?
DeepInfra offers Mixtral 8x22B v0.1 with pay-as-you-go pricing at $0.65/1M input tokens. DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models.
Compare Mixtral 8x22B v0.1 across 8 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport DEEPINFRA_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["DEEPINFRA_API_KEY"],mixtral-8x22b-v0.1Request example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["DEEPINFRA_API_KEY"],
base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
model="mixtral-8x22b-v0.1",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- DeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
- The examples expect DEEPINFRA_API_KEY; rename it only if your application config maps the new variable.
Compare Mixtral 8x22B v0.1 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| OctoAI API (Deprecated) | — | — |
| Fireworks AI | $1.20 | $1.20 |
| DeepInfra | $0.65 | $0.65 |
| Baseten API | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.65 |
| Output tokens | $0.65 |
Capabilities
No model capability flags are currently sourced.
About Mixtral 8x22B v0.1
The Mixtral 8x22B v0.1 is a pretrained generative Sparse Mixture of Experts (MoE) model created by Mistral AI [1][2][4]. It utilizes a specialized architecture where different sub-models, termed "experts," manage distinct input segments, enhancing both efficiency and performance relative to traditional large language models [2][10][12]. This model features an impressive 176 billion parameters and supports a context length of 65,000 tokens [10][13]. It excels in text generation, completion, and question answering, outperforming models like LLaMA 2 70B on various benchmarks [4][5][7]. Nonetheless, as a base model, it lacks inherent moderation capabilities, potentially generating inappropriate or harmful content without filtration [2][4][10].