Mercury 3
by Inceptioninception/mercury-3
LLMCompare cannot run Mercury 3 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowMercury 3 at a glance
- Context length
- 1,000,000 tokens
- Maximum output
- 131,072 tokens
- Accepts
- Text
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt caching
- Reasoning effort levels
highmediumlownoneReasoning can be turned off.- Released
- 16 Oct 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Mercury 3 pricing by route
A route is the service LLMCompare calls to reach the model. Mercury 3 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $0.10 | $0.35 | $0.01 | openrouter.ai/inception/mercury-3 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to Mercury 3 costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.00028
- 1 credits
- Cost of 100 calls
- $0.0275
- 100 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
max_tokens | Integer | 1 to 131,072 | Provider default |
reasoning_effort | One of | highmediumlownone | medium |
response_format | One of | textjson_object | Provider default |
About Mercury 3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Mercury 3
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Mercury 2Inceptioninception/mercury-2 | 128k | 50k | $0.25 | $0.75 | ReasoningJSONToolsCache | No route yet | ||
Mercury 2.5Inceptioninception/mercury-2.5 | 260k | 65.5k | $0.04 | $0.15 | ReasoningJSONToolsCache | No route yet | ||
GPT-5 NanoOpenAIopenai/gpt-5-nano | 400k | 128k | $0.05 | $0.40 | ReasoningJSONToolsCacheVision | No route yet | ||
GLM 4.7 FlashZ.aiz-ai/glm-4.7-flash | 200k | 118k | $0.0605 | $0.40 | JSONTools | No route yet | ||
Gemma 3 27BGooglegoogle/gemma-3-27b-it | 131k | 118k | $0.08 | $0.35 | JSONToolsCacheVision | No route yet | ||
MiMo-V2.6-FlashXiaomixiaomi/mimo-v2.6-flash | 1.05M | 131k | $0.14 | $0.28 | JSONToolsCacheVision | No route yet |
Questions about Mercury 3
- How much does Mercury 3 cost?
- On the OpenRouter route, Mercury 3 costs $0.10 per 1 million input tokens and $0.35 per 1 million output tokens, in US dollars. Input tokens that Mercury 3 reads from the prompt cache cost $0.01 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Mercury 3?
- Mercury 3 has a context length of 1,000,000 tokens and returns up to 131,072 output tokens in one call.
- What inputs does Mercury 3 accept?
- Mercury 3 accepts these inputs: Text. Mercury 3 returns: Text.
- Which reasoning effort levels does Mercury 3 support?
- Mercury 3 supports these reasoning effort levels: high, medium, low, none. Reasoning can be turned off for Mercury 3.
- Can I test Mercury 3 on my own data?
- Not yet. LLMCompare lists the prices and parameters of Mercury 3, but no route to Mercury 3 is configured on LLMCompare, so it cannot be selected for an evaluation.