Mercury 2.5
Summary
Mercury 2.5 is a proprietary language model from Inception Labs, released on 8 Sept 2026. It accepts text and generates text, with a 260K-token context window and up to 66K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.20 per million input tokens and $0.75 per million output tokens (Inception API), across 1 provider we track. It is scheduled for retirement on 8 Nov 2026.
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Inception Labs |
|---|---|
| Release date | 8 Sept 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 260K (260,000 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Knowledge cutoff | 1 Nov 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Retirement date | 8 Nov 2026 [OpenRouter] |
Mercury 2.5 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Inception API mercury-2.5 | $0.20 | $0.75 | $0.02 | 260K | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Mercury 2.5?
Mercury 2.5 has a context window of 260,000 tokens (260K) and can generate up to 65,536 tokens in a single response, according to models.dev.
How much does the Mercury 2.5 API cost?
Through Inception API, Mercury 2.5 costs $0.20 per million input tokens and $0.75 per million output tokens. Prices last verified 18 Nov 2026.
Is Mercury 2.5 open source?
No. Mercury 2.5 is a proprietary model; Inception Labs has not released its weights. It is available through APIs including Inception API.
When was Mercury 2.5 released?
Inception Labs released Mercury 2.5 on 8 Sept 2026, according to models.dev.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Mi:dm K 3.0 Pro | KT | 5 Nov 2026 | 262K | $0.20 | $0.80 | – |
| Aion 3.5 Mini | Aion Labs | 23 Sept 2026 | 262K | $0.70 | $1.40 | – |
| Toast 1 | Mixedbread | 13 Aug 2026 | 131K | $0.30 | $0.72 | Closed |
| Ling 3.0 Flash Sante | Inclusionai | 4 Sept 2026 | 256K | $0.07 | $0.22 | Closed |
| Solar Pro 4 | Upstage | 6 Aug 2026 | 524K | $0.15 | $0.60 | Closed |
| Glimpse | Elorian | 17 Oct 2026 | 262K | $0.60 | $3 | – |
Change history
- No longer listed on vercel
- No longer listed on openrouter
- Retirement date changed from none to 8 Nov 2026
- Inception API price changed: input $0.04 → $0.20, output $0.15 → $0.75 per 1M tokens
- Now listed on vercel