NanoGPT
Mercury 2.5 Preview
Canonical ID:
nano-gpt/inception/mercury-2.5-preview
Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.
Overview
Pricing and Limits
Token pricing
- Input
- $0.04/1M
- Output
- $0.15/1M
- Cached input
- N/A
Context and output
- Context window
- 260,000
- Max output tokens
- 65,536
- Qualified ID
- nano-gpt/inception/mercury-2.5-preview
Model Summary
Mercury 2.5 Preview is a model listing in the NanoGPT provider catalog. It is categorized under the mercury family.
The model supports text modalities across input/output paths. Reported context capacity is 260,000. Pricing is listed at $0.04/1M input and $0.15/1M output.
More From NanoGPT
Related models from the same provider catalog.
NanoGPT
Abliterated Model
nano-gpt/abliteration-ai/abliterated-model
NanoGPT
Abliterated Model Large
nano-gpt/abliteration-ai/abliterated-model-large
NanoGPT
Abliterated Model Large V2
nano-gpt/abliteration-ai/abliterated-model-large-v2
NanoGPT
Agnes 3.0 Flash
nano-gpt/agnes-3.0-flash
NanoGPT
AionLabs: Aion-2.0
nano-gpt/aion-labs/aion-2.0
NanoGPT
AionLabs: Aion 3.0
nano-gpt/aion-labs/aion-3.0
NanoGPT
AionLabs: Aion 3.0 Mini
nano-gpt/aion-labs/aion-3.0-mini
NanoGPT
AionLabs: Aion 3.5
nano-gpt/aion-labs/aion-3.5
Same Family: mercury
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Inception: Mercury
openrouter/inception/mercury
|
OpenRouter
|
128,000 | $0.25/1M | $0.75/1M |
Tools
|
|
Inception: Mercury
kilo/inception/mercury
|
Kilo Gateway
|
128,000 | $0.25/1M | $1/1M |
Tools
|
|
Inception: Mercury 2.5
kilo/inception/mercury-2.5
|
Kilo Gateway
|
260,000 | $0.2/1M | $0.75/1M |
Reasoning
Tools
|
|
Inception: Mercury 3
kilo/inception/mercury-3
|
Kilo Gateway
|
1,000,000 | $0.2/1M | $0.7/1M |
Reasoning
Tools
|
|
Mercury
inception/mercury
|
Inception
|
128,000 | $0.25/1M | $1/1M |
Tools
|
|
Mercury 2
nano-gpt/mercury-2
|
NanoGPT
|
128,000 | $0.25/1M | $0.75/1M |
Reasoning
Tools
|
|
Mercury 2
venice/mercury-2
|
Venice AI
|
128,000 | $0.3125/1M | $0.9375/1M |
Reasoning
Tools
|
|
Mercury 2
aimlapi/inception/mercury-2
|
AI/ML API
|
128,000 | $0.34385/1M | $1.03155/1M |
Reasoning
Tools
|
|
Mercury 2
vercel/inception/mercury-2
|
Vercel AI Gateway
|
128,000 | $0.25/1M | $0.75/1M |
Reasoning
Tools
|
|
Mercury 2.5
aimlapi/inception/mercury-2.5
|
AI/ML API
|
260,000 | $0.27508/1M | $1.03155/1M |
Reasoning
Tools
|