Mistral
Mixtral 8x22B Instruct
model
mixtral-8x22b-instruct-openrouterMidStableStreamingToolsBatchGlobal
Context
66K
Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Weighted tokens formula
1× provider × 4× tier
About this model
Mixtral 8x22B Instruct
Mixtral 8x22B Instruct is a mid-tier model available through the Anoman gateway. Detailed performance benchmarks and use-case guidance for this model are coming soon. In the meantime, see the code example below to integrate it into your workflow, and the tier + region information in the hero for pricing and residency.
Code example
Chat completion with Mixtral 8x22B Instruct
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="mixtral-8x22b-instruct-openrouter",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 4×: 5,000,000 raw tokens available.