Mercury 3: API pricing, providers and specs
Mercury 3 is a text model by Inception. 5 providers serve it, from $0.35 to $0.741 /1M; the lowest price is at Venice AI.
How Mercury 3 compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.35 /1M, its lowest price undercuts 72% of comparable models (median $1.10).
- Its 1M-token context window is larger than 67% of them (median 262K), about 1500 pages of text.
- 5 providers serve it; 65% of comparable models have fewer.
Mercury 3 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Venice AI | $0.10/1M | $0.35/1M | $0.01/1M | — |
| Vercel AI Gateway | $0.10/1M | $0.35/1M | $0.01/1M | 1M |
| OpenRouter | $0.10/1M | From$0.35/1M | $0.01/1M | 1M |
 Poe | $0.101/1M | $0.353/1M | $0.01/1M | 1M |
| AI/ML API | $0.212/1M | $0.741/1M | $0.021/1M | — |
- Venice AI$0.35
- Vercel AI Gateway$0.35
- OpenRouterFrom$0.35
- Poe$0.353
- AI/ML API$0.741
Specs
- Type
- Text
- Maker
- Inception
- Inputs
- Text
- Outputs
- Text
- Context
- 1M≈ 1500 pages of text
- Max output
- 131K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling
- Released
- Oct 19, 2026
- License
- proprietary
- Open weights
- No, API only
- Monthly searches
- 9K
Alternatives to Mercury 3
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Mercury 3this model | $0.35/1M | 1M | — | 5 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
 Sonar | $1/1M | 127K | — | 9 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 MiMo-V2.6-Pro | $0.696/1M | 1.05M | 1625 | 21 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
More from Inception
Mercury 3 FAQ
The lowest price for Mercury 3 is $0.35 /1M, at Venice AI.
Venice AI, at $0.35 /1M. 5 providers serve Mercury 3; the table above lists every one with its price.
Mercury 3 reads up to 1M tokens per request and writes up to 131K.
No. Mercury 3 is only available through an API; Inception does not publish its weights.
5 API providers serve Mercury 3. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us