Skip to content
API pricing

OpenRouter API pricing, checked at the source

Per-model prices on OpenRouter, read off OpenRouter's own model list with a link on every row, plus the fees it charges. Estimate a monthly bill below.

10
Models priced
$0.10
Lowest input / 1M
$0.50
Lowest output / 1M
2026-10-25
Prices checked
Prices

OpenRouter API prices per 1M tokens

Standard prices in USD. Each row links to OpenRouter's pricing page and shows the day we checked it.

OpenRouter API prices in USD per 1M tokens, checked 2026-10-25
ModelInputCached inputOutputNotesSource
Anthropic: Claude Opus 5.5$4.00$0.20$20.00Sourcechecked 2026-10-25
Anthropic: Claude Sonnet 5.5$2.00$0.10$10.00Sourcechecked 2026-10-25
Anthropic: Claude Haiku 5.5$0.10$0.01$0.50Sourcechecked 2026-10-25
OpenAI: GPT-6.1 Sol$2.00$0.10$10.00Sourcechecked 2026-10-25
OpenAI: GPT-6 Luna$0.10$0.01$0.50Sourcechecked 2026-10-25
Google: Gemini 4 Argon$2.00$0.10$10.00Sourcechecked 2026-10-25
SpaceXAI: Grok 4.7$2.00$0.50$6.00Sourcechecked 2026-10-25
MoonshotAI: Kimi K3.1 Pro$2.00$0.20$10.00Sourcechecked 2026-10-25
DeepSeek: DeepSeek V4.1 Flash 1017$0.15$0.003$0.60Sourcechecked 2026-10-25
OpenAI: gpt-oss-120b$0.15$0.075$0.60Sourcechecked 2026-10-25

Terms on this page: Token · Prompt caching · Context window · Batch API

Estimator

Estimate your OpenRouter bill

Enter your monthly tokens and how they split between new input, cached input and output. The result updates as you type.

Write 40k, 250M or 5B. Input, cached input and output tokens together.

Token split (%)

100M tokens a month costs from $6.78 (Anthropic: Claude Haiku 5.5) to $259.60 (Anthropic: Claude Opus 5.5).

ModelPer monthPer 1M tokens at this split
Anthropic: Claude Haiku 5.5$6.78$0.0678
OpenAI: GPT-6 Luna$6.78$0.0678
DeepSeek: DeepSeek V4.1 Flash 1017$8.72$0.08724
OpenAI: gpt-oss-120b$12.90$0.129
Anthropic: Claude Sonnet 5.5$129.80$1.298
OpenAI: GPT-6.1 Sol$129.80$1.298
Google: Gemini 4 Argon$129.80$1.298
SpaceXAI: Grok 4.7$133.00$1.33
MoonshotAI: Kimi K3.1 Pro$135.60$1.356
Anthropic: Claude Opus 5.5$259.60$2.596

Standard prices in USD on 2026-10-25, before tax. Long-prompt tiers are left out; see the price table.

Billing

How the bill is worked out

No markup on tokens

Inference is billed at the provider's list price on every plan. OpenRouter's fee is charged when you buy credits, never on single requests.

Credit purchase fee

The fee on credit purchases is 5.5% on Standard and 8% on Business. Enterprise can get fee discounts.

BYOK allowance

With your own provider key, the provider bills you directly. Standard and Business include $25,000 of list-price inference per month with no fee, then 5% of the list price, taken from your credits.

Free models and failed calls

Free models are capped at 50 requests a day, or 1,000 a day after buying at least $10 of credits. Failed or fallback attempts are not charged for model tokens.
FAQ

OpenRouter API pricing questions

How much does the OpenRouter API cost?

OpenRouter bills its language models per million tokens, with separate prices for input, cached input and output. On 2026-10-25, standard prices ran from $0.10 (Anthropic: Claude Haiku 5.5) to $4.00 (Anthropic: Claude Opus 5.5) per 1M input tokens, and $0.50 (Anthropic: Claude Haiku 5.5) to $20.00 (Anthropic: Claude Opus 5.5) per 1M output tokens.

Does OpenRouter offer a batch discount?

Its pricing page lists no batch price for the rows here. Inference is billed at the provider's list price on every plan. OpenRouter's fee is charged when you buy credits, never on single requests.

Where do these prices come from?

From OpenRouter's own pricing page, https://openrouter.ai/pricing, checked on 2026-10-25. Every row links to it. When a price cannot be confirmed, the row says to check the vendor's page instead of showing a number.

Does OpenRouter add a markup on model prices?

No markup on tokens. OpenRouter bills inference at the provider's list price and charges a fee when you buy credits: 5.5% on Standard and 8% on Business. With your own provider key, $25,000 of list-price inference a month carries no fee, then 5%.

Related

Compare and plan

Building with the OpenRouter API? OceanLab builds AI into business workflows, with people kept in charge. AI automation →

START YOUR CONVERSATION

Your Next Mission-Critical
System Starts Here

Speak with a senior engineer about your requirements. No sales process, just a direct technical conversation about what you need to build.

OceanLab

Enterprise Software Engineering - Human + AI

Languages

Locations

Global Headquarters

21 Merchant Road, 3rd Floor, Singapore 058267

Main corporate office and leadership operations

North America Office

548 Market Street, PMB 12472, San Francisco, CA 94104

Client operations and business development

India Office

402 Shivalik Shilp II, SG Highway, Ahmedabad 380015

Engineering and delivery center

© 2026 - Copyright. All Rights reserved OceanLab