Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Context
260K
260,000 tokens
Max output
66K
65,536 tokens
Input
$0.20
per 1M tokens
Output
$0.75
per 1M tokens
Providers
5
5 listings
Intelligence
12.3
Intelligence Index
Pricing
USD per 1M tokens · listed by Inception
| Token type | Standard |
|---|---|
| Input | $0.20 |
| Output | $0.75 |
| Cache read | $0.02 |
Lowest input price across providers: $0.04.
Capabilities
ReasoningYes
Effort: low, medium, high
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsNo
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence12.3#141 of 208
- CodingNot scored—
- AgenticNot scored—
- ArenaNot scored—
Rankings
Position on each OneAtlas leaderboard
Providers · 5
5 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 AI/ML API | inception/mercury-2.5 | 260K | — | 66K | $0.21 | $0.79 | — | $0.02 | — | — | — | Yes | Yes | Yes | Yes | Sep 8, 2026 |
| Inception | mercury-2.5 | 260K | — | 66K | $0.20 | $0.75 | — | $0.02 | — | — | — | Yes | Yes | Yes | Yes | Sep 8, 2026 |
 Kilo Gateway | inception/mercury-2.5 | 260K | — | 66K | $0.20 | $0.75 | — | $0.02 | — | — | — | Yes | Yes | Yes | Yes | Sep 8, 2026 |
 Venice AI | mercury-2-5 | 260K | — | 66K | $0.25 | $0.94 | — | $0.03 | — | — | — | Yes | Yes | Yes | Yes | Sep 8, 2026 |
 Vercel AI Gateway | inception/mercury-2.5 | 260K | — | 66K | $0.04 | $0.15 | — | $0.004 | — | — | — | Yes | Yes | Yes | Yes | Sep 8, 2026 |