Model Library
InceptionReleased February 20, 2026Mercury 2
Inception · Released February 20, 2026
Intelligence score
25
At a glance
- Intelligence
- 25
- Speed
- 1121.6tokens/sec
- Latency
- 5.03stime to first token
- Input price
- $0.25per 1M tokens
- Output price
- $0.75per 1M tokens
- Context window
- 130Ktokens
- Parameters
- —
Summary
Comparison summary
Mercury 2 scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 15). Mercury 2 generates output at 1,121.6 tokens per second (based on Inception's API), which is well above average compared to other reasoning models in a similar price tier (median: 99.0 t/s). Mercury 2 costs $0.25 per 1M input tokens (better than average, median: $0.25) and $0.75 per 1M output tokens (better than average, median: $0.87), based on Inception's API.
Specifications
Technical specifications
| Model name | Mercury 2 |
|---|---|
| Provider | Inception |
| Release date | February 20, 2026 |
| Intelligence score | 25 |
| Speed | 1121.6 tokens/sec |
| Latency (TTFT) | 5.03s |
| Input price | $0.25 / 1M tokens |
| Output price | $0.75 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | — |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: mercury-2 |
Pricing
Token prices
Price per 1M tokens
Mercury 2, as listed in the catalog record
- Input$0.25
- Output$0.75
| Token type | Price per 1M |
|---|---|
| Input | $0.25 |
| Output | $0.75 |
Model Intelligence legacy profile: mercury-2
FAQ · 18
Frequently asked questions
Mercury 2 was released on February 20, 2026.
Mercury 2 was created by Inception.
Mercury 2 scores 25 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 15).
Mercury 2 generates output at 1,121.6 tokens per second (based on Inception's API), which is well above average compared to other reasoning models in a similar price tier (median: 99.0 t/s).
Mercury 2 has a time to first token (TTFT) of 5.03s (based on Inception's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.96s).
Mercury 2 costs $0.25 per 1M input tokens (better than average, median: $0.25) and $0.75 per 1M output tokens (better than average, median: $0.87), based on Inception's API.
Mercury 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens (based on Inception's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.14 per 1M tokens. Pricing may vary by provider.
Yes, Mercury 2 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Mercury 2 supports text input.
Mercury 2 supports text output.
No, Mercury 2 does not support image input. It can only process text.
No, Mercury 2 is not multimodal. It only supports text input.
Mercury 2 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
No, Mercury 2 is proprietary. The model weights are not publicly available.
Mercury 2 is a proprietary model and Inception has not disclosed the model size or parameter count.
Mercury 2 achieves a score of 25 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Mercury 2 is available via API through 1 provider.
Mercury 2 is available through 1 API provider.