Does R1 support prompt caching?

OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.

Is there a cheaper model as good as R1?

MiMo-V2.6-Flash scores 60.8 on the LLMBenchmark Index, within two points of R1 or above it, and costs $0.28 per million output tokens.

Retired

As of October 22, 2026, DeepSeek R1 costs $0.70 per million input tokens and $2.50 per million output tokens as listed on OpenRouter.

No longer listed on OpenRouter since October 19, 2026; last listed price shown.

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 R1
Workload	Tokens	One request	1,000 requests	Fits the context window
Chat turn	1K input + 500 output tokens	$0.0019	$1.95	Yes
Repository review	50K input + 3K output tokens	$0.043	$42.50	Yes
Agent loop	200K input + 10K output tokens	$0.165	$165.00	No, it would need splitting
Solved coding task	One SWE-bench Verified attempt, divided by the share that succeed	Not computable	Not computable

The price of R1 here is the price OpenRouter lists, so we do not track price changes for it.

Models within two points of R1 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.

How much does R1 cost per million tokens?: $0.70 per million input tokens and $2.50 per million output tokens, as listed on OpenRouter on October 22, 2026.
Does R1 support prompt caching?: OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.
Is there a cheaper model as good as R1?: MiMo-V2.6-Flash scores 60.8 on the LLMBenchmark Index, within two points of R1 or above it, and costs $0.28 per million output tokens.
Has the price of R1 changed?: The price of R1 here is the price OpenRouter lists, so we do not track price changes for it.