Mistral
Mixtral 8X22B
model
openrouter/mixtral-8x22bMidStableStreamingToolsBatchUnited States
Context
66K
Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Cached input / 1M tokens
$0.4700
Cache write / 1M tokens
— (bills at input price)
About this model
Mixtral 8X22B
Mixtral 8x22B — Mistral's open-weights MoE model. Strong general-purpose model with 64K context.
Key facts
- Maker
- Mistral
- Context window
- 66K tokens
- Max output
- 52K tokens
- Lane
- Guarded: the provider has confirmed it does not train on your data
- Modality
- Text
- Input price
- $2.00 per 1M tokens
- Output price
- $6.00 per 1M tokens
- Processing region(s)
- us
- Route
- Via OpenRouter
- Cheapest plan
- Available from the Pro plan
- Price comparison
- Priced below 73 of 248 pro-band guarded models on Anoman (blended price: 1 part input to 3 parts output).
Released
2024-04
Training cutoff
2024-02
Parameters
MoE 8x22B (39B active)
Best for
Use cases
- General-purpose chat
- Multilingual tasks
- Customers wanting Mistral architecture
Strengths
What it does well
- Open-weights MoE architecture
- Multilingual support
- 65K context
Limitations
Know the trade-offs
- Trails newer Qwen 2.5 / Llama 3.3 on most benchmarks
- Less community tuning recently
Code example
Chat completion with Mixtral 8X22B
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="openrouter/mixtral-8x22b",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Alternatives
Similar models in our catalog
Same maker first, then the closest price to Mixtral 8X22B in the Anoman catalog.