# Mercury 2

> Mercury 2 is a proprietary language model from Inception Labs, released on 24 Feb 2026. It accepts text and generates text, with a 128K-token context window and up to 50K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.25 per million input tokens and $0.75 per million output tokens (Inception API), across 2 providers we track.

Source page: https://www.aimodel.directory/models/mercury-2
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Inception Labs
- **Release date:** 24 Feb 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Max output:** 50K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Knowledge cutoff:** 1 Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/inception/models/mercury-2.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Inception API | $0.25 | $0.75 | $0.03 | 128K |
| OpenRouter | $0.25 | $0.75 | $0.03 | 128K |

## FAQ

### What is the context window of Mercury 2?

Mercury 2 has a context window of 128,000 tokens (128K) and can generate up to 50,000 tokens in a single response, according to models.dev.

### How much does the Mercury 2 API cost?

Through Inception API, Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens. Prices last verified 4 Oct 2026.

### Is Mercury 2 open source?

No. Mercury 2 is a proprietary model; Inception Labs has not released its weights. It is available through APIs including Inception API, OpenRouter.

### When was Mercury 2 released?

Inception Labs released Mercury 2 on 24 Feb 2026, according to models.dev.

### Which providers offer Mercury 2?

We track Mercury 2 on 2 providers: Inception API, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Mercury 2", https://www.aimodel.directory/models/mercury-2