Inception: Mercury 2.5 vs Mercury 3
inception/mercury-2.5 · inception/mercury-3
As of October 24, 2026, Inception: Mercury 2.5 is the cheaper API on UberLLM: $0.0400 per million input tokens and $0.1500 per million output, versus $0.0824 / $0.2884 for Mercury 3 — about 48% less on a blended 3:1 token mix. Both are reached through one OpenAI-compatible key and routed to the cheapest healthy seller, with UberLLM's 10% fee already included, so the price you see is the price you pay. Choose Inception: Mercury 2.5 to cut cost; choose Mercury 3 when context size wins — Mercury 3 carries the larger context window (1,000,000 vs 260,000 tokens), which can matter for long-document work.
Inception: Mercury 2.5 vs Mercury 3, side by side
| Spec | Inception: Mercury 2.5 | Mercury 3 |
|---|---|---|
| Price · input / 1M | $0.0400 | $0.0824 |
| Price · output / 1M | $0.1500 | $0.2884 |
| Context length | 260,000 | 1,000,000 |
| Max output tokens | 65,536 | 131,072 |
| Input modalities | text | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Reasoning | Yes | Yes |
| Cheapest seller | UberLLM | UberLLM |
| % off list | — | 18% off |
Live prices via UberLLM, routed to the cheapest healthy seller. The price shown includes UberLLM’s 10% fee. Updated October 24, 2026.
Inception: Mercury 2.5 vs Mercury 3 — FAQ
Is Inception: Mercury 2.5 or Mercury 3 cheaper?
Inception: Mercury 2.5 is cheaper on a blended token mix, by about 48%. UberLLM routes every request to the cheapest healthy seller and bills the price shown, with its 10% fee included.
What's the price difference between Inception: Mercury 2.5 and Mercury 3?
Inception: Mercury 2.5: $0.0400 in / $0.1500 out per 1M tokens. Mercury 3: $0.0824 in / $0.2884 out per 1M tokens. That's roughly a 48% blended difference. Prices are live and include UberLLM's 10% fee.
Can I use both Inception: Mercury 2.5 and Mercury 3 with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.