How do I call mercury-2.5 from my code?
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘inception/mercury-2.5’ and supply your Synapse Garden API key. No code changes beyond the base URL.
Inception · Single modalityReleased 2026-09-08
mercury-2.5
inception/mercury-2.5 idMercury 2.5 is Inception’s diffusion-based reasoning model for chat, agents, and structured workflows, with tool calling, structured outputs, and a 260K context window.
Tool useReasoningStructured output
Type
Use mercury-2.5
# Drop-in OpenAI-compatible client$ import { generateText } from 'ai'$$ const { text } = await generateText({$ model: 'inception/mercury-2.5',$ baseURL: 'https://synapse.garden/api/v1',$ apiKey: process.env.MG_KEY,$ prompt: 'Why is the sky blue?',$ })
260K
CONTEXT WINDOW65.5K
MAX OUTPUT$0.044/M
INPUT · PER M$0.165/M
OUTPUT · PER MPRICING
List prices, every modality.
| Rate | Per million tokens · USD |
|---|---|
| Input | $0.044/M |
| Output | $0.165/M |
| Cache read | $0.0044/M |
Honest list pricesHow we calculate prices
MORE FROM INCEPTION
See all 3Other Inception models
Model
Input
Output
Context
Type
- Input$0.275/MOutput$0.825/MContext128K
- Input$0.275/MOutput$1.10/MContext32K
FAQ · MERCURY-2.5
Frequently asked
How much does mercury-2.5 cost?
Input: $0.044/M per million tokens. Output: $0.165/M per million tokens. The free tier includes a million tokens every month at no cost.
What's the context window for mercury-2.5?
mercury-2.5 supports a context window of 260K tokens, with a maximum output of 65.5K tokens.
Do I need a separate Anthropic or OpenAI account?
No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.
READY
Try mercury-2.5 in three minutes.
Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.