Mercury

Other chatreasoningtool_use

API ID: inception/mercury

Input Price
$0.25
/1M tokens
Output Price
$1.00
/1M tokens

About Mercury

Mercury is Inception's language model, delivering strong performance on general AI tasks. The model excels at conversation, content generation, and analysis. Mercury variants include coding-specialized versions for development tasks. The series demonstrates Inception's advancement in language model development. For developers seeking capable AI from Inception, Mercury offers reliable performance.

๐Ÿ’ฐ
Price Ranking
#430 lowest price among 599 Chat models

Model Specifications

Context Length
128k
Max Output
16k
Release Date
2025-06-26
Capabilities
chat reasoning tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Complex reasoning, math problems, multi-step logic
  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)
  • Simple Q&A (cheaper models available)

๐Ÿ’ฐ Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.41
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$12.75
/month
1000 tickets/day, ~800 tokens each
Data Analysis Pipeline
$17.63
/month
500 analyses/day, ~2k tokens each

Other Model Lineup

Compare all models from Other to find the best fit

Model Input Output Context Capabilities
Mercury Current Free Free 128k chat reasoning tool_use
Sarvam-M Free Free 33k chat
Caller Large Free Free 33k chat
Arcee Blitz Free Free 33k chat
InternVL3 14B Free Free 32k chat vision
InternVL3 2B Free Free 32k chat vision

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Google Gemma 2 27B
Input: $0.65
Output: $0.65
Context: 8k
MiniMax MiniMax-01
Input: $0.20
Output: $1.10
Context: 1.0M
Zhipu AI GLM 4.6V
Input: $0.30
Output: $0.90
Context: 131k
MiniMax MiniMax M2
Input: $0.20
Output: $1.00
Context: 197k

๐Ÿš€ Quick Start

Get started with Mercury API

OpenAI-compatible SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="inception/mercury",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)