Compare Mercury 2.5 from inception and Mercury 3 from inception on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
Mercury 2.5 and Mercury 3 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Mercury 2.5, from inception, has a 260,000-token context window and is priced at $0.04/M tokens input, $0.15/M tokens output on OpenRouter.
Mercury 3, from inception, has a 1,000,000-token context window and is priced at $0.10/M tokens input, $0.35/M tokens output on OpenRouter.
| Attribute | Mercury 2.5 | Mercury 3 |
|---|---|---|
| Input price | $0.04/M tokens | $0.10/M tokens |
| Output price | $0.15/M tokens | $0.35/M tokens |
| Context window | 260,000 tokens | 1,000,000 tokens |
| Intelligence Index | 12.3 | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.00 s | 0.87 s |
| Throughput (p50) | 279.0 tok/s | 247.0 tok/s |
Benchmark data updated
Mercury 2.5 is cheaper than Mercury 3 on OpenRouter: Mercury 2.5 costs $0.04/M tokens input and $0.15/M tokens output, while Mercury 3 costs $0.10/M tokens input and $0.35/M tokens output.
Mercury 3 has the longer context window at 1,000,000 tokens, compared with 260,000 tokens for Mercury 2.5.
Mercury 2.5 is faster on OpenRouter, generating a median 279.0 tokens per second compared with 247.0 tokens per second for Mercury 3.