Mercury 2.5 Preview
by InceptionChat
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.
- Context
- 260K tokens
- Max output
- 65,536 tokens
- Released
- 2026-09-01
- Weights
- Closed
inception/mercury-2-5-preview
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-09-01
- Weights
- Closed
- Input
- Text
- Output
- Text
- Context window
- 260,000 max across endpoints
- Max output
- 65,536
- Providers
- 0 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.04 in at NanoGPT, via gateway, fees not verified
More details
- Last updated
- 2026-09-01
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperatureunknown
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Mercury 2.5 Preview |
|---|---|---|---|---|---|
| Sarvam-105BSarvam AI | $0.06 | $0.04 | $0.16 | 131K | +3% |
| Command R7BCohere | $0.0563 | $0.0375 | $0.15 | 128K | −4% cheaper |
| Llama 3.2 1b InstructMeta | $0.056 | $0.027 | $0.201 | 131K | −4% cheaper |
| Llama 3.1 8B InstructMeta | $0.055 | $0.05 | $0.08 | 200K | −6% cheaper |
| llama-3-8bMeta | $0.055 | $0.05 | $0.08 | 8.2K | −6% cheaper |
| Mistral Small 3Mistral AI | $0.055 | $0.05 | $0.08 | 32.8K | −6% cheaper |
| Seed 1.6 FlashByteDance Seed | $0.0617 | $0.03 | $0.22 | 256K | +6% |
| GLM-4.6V-FlashZ.ai (Zhipu AI) | $0.0546 | $0.0218 | $0.218 | 128K | −6% cheaper |
More from Inception
Newest Inception models in the catalogue. All Inception models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Mercury Decide | 2026-09-30 | 65.5K | unpriced |
| Mercury 2.5 | 2026-09-08 | 260K | from $0.04 |
| Mercury Edit 2 | 2026-03-30 | 32K | from $0.25 |
| Mercury 2 | 2026-02-24 | 128K | from $0.25 |
| Mercury Coder Small Beta | 2024-01-01 | 32.8K | $0.25 via NanoGPT |