How much does Mercury 2.5 cost per million tokens?

$0.04 per million input tokens and $0.15 per million output tokens, as listed on OpenRouter on October 22, 2026.

Does Mercury 2.5 support prompt caching?

Yes. OpenRouter lists cached input at $0.004 per million tokens, against $0.04 for uncached input.

Is there a cheaper model as good as Mercury 2.5?

Ling 3.0 Flash scores 29.6 on the Vibe Coding Index, within two points of Mercury 2.5 or above it, and costs $0.1215 per million output tokens.

Mercury 2.5 API pricing

As of October 22, 2026, Inception Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens, the median of 1 providers on OpenRouter, with cached input at $0.004 per million.

Mercury 2.5 benchmarks and specs · Every Inception model's price

Input, per million tokens$0.04
Output, per million tokens$0.15
Cached input, per million$0.004
Context window260K tokens
Max output66K tokens
Output speed559 tok/s

What a request costs

Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.

Cost of three workloads on Mercury 2.5
Workload	Tokens	One request	1,000 requests	Fits the context window
Chat turn	1K input + 500 output tokens	$0.0001	$0.115	Yes
Repository review	50K input + 3K output tokens	$0.0024	$2.45	Yes
Agent loop	200K input + 10K output tokens	$0.0095	$9.50	Yes
Solved coding task	One SWE-bench Verified attempt, divided by the share that succeed	Not computable	Not computable

Price history

The price of Mercury 2.5 here is the median across 1 providers on OpenRouter, so we do not track price changes for it.

Cheaper models as good as Mercury 2.5

Models within two points of Mercury 2.5 or above it on the Vibe Coding Index, with a lower output price. Cheapest first.

Mercury 2.5 pricing questions

How much does Mercury 2.5 cost per million tokens?: $0.04 per million input tokens and $0.15 per million output tokens, as listed on OpenRouter on October 22, 2026.
Does Mercury 2.5 support prompt caching?: Yes. OpenRouter lists cached input at $0.004 per million tokens, against $0.04 for uncached input.
Is there a cheaper model as good as Mercury 2.5?: Ling 3.0 Flash scores 29.6 on the Vibe Coding Index, within two points of Mercury 2.5 or above it, and costs $0.1215 per million output tokens.
Has the price of Mercury 2.5 changed?: The price of Mercury 2.5 here is the median across 1 providers on OpenRouter, so we do not track price changes for it.