anoman

Mistral

Mixtral 8X22B

modelopenrouter/mixtral-8x22b
MidStableStreamingToolsBatchUnited States

Context

66K

Input / 1M tokens

$2.00

Output / 1M tokens

$6.00

About this model

Mixtral 8X22B

Mixtral 8x22B — Mistral's open-weights MoE model. Strong general-purpose model with 64K context.

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

Workloads that fit Mixtral 8X22B often fit these too. Compare benchmarks and pricing before locking in a default.

Use Mixtral 8X22B through Anoman.