Mercury 2.5
Inception · released 2026-09-08
The official API price of Mercury 2.5 is $0.2 per 1M input tokens and $0.75 per 1M output tokens (as of 2026-11-12). Context window: 260K tokens, up to 65.5K output tokens per request. 3 providers sell it. The lowest is Vercel AI Gateway: $0.04 input, $0.15 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| InceptionOfficialmercury-2.5 | $0.2 | $0.75 | $0.02 | Official | Official docs |
 Vercel AI GatewayLowestinception/ | $0.04 | $0.15 | $0.004 | Lowest | Official docs |
 AI/ML APIinception/ | $0.2116 | $0.7935 | $0.02116 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception
Description from models.dev.
Specs
- Type
- Text
- Context
- 260K
- Max output
- 65.5K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-11-01
- Open weights
- No
- Released
- 2026-09-08
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.