Open-source LLM (via OpenRouter)
Mercury 2
model
mercury-2BudgetStableCommunityStreamingToolsBatchLong contextGlobal
Context
128K
Input / 1M tokens
$0.2500
Output / 1M tokens
$0.7500
Cached input / 1M tokens
$0.0588
Cache write / 1M tokens
— (bills at input price)
About this model
Mercury 2
Mercury 2 is available through the Anoman AI OpenAI-compatible API with a 128K-token context window. It costs $0.2500 per 1M input tokens and $0.7500 per 1M output tokens, and is available from the Pro plan.
Key facts
- Context window
- 128K tokens
- Max output
- 50K tokens
- Lane
- Community: needs account opt-in; the provider may use data for training
- Modality
- Text
- Input price
- $0.2500 per 1M tokens
- Output price
- $0.7500 per 1M tokens
- Processing region(s)
- global
- Route
- Via OpenRouter
- Cheapest plan
- Available from the Pro plan
- Price comparison
- Priced below 88 of 115 pro-band community models on Anoman (blended price: 1 part input to 3 parts output).
Code example
Chat completion with Mercury 2
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="mercury-2",
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 Mercury 2 in the Anoman catalog.