AI API

AIGROW vs OpenRouter

OpenRouter routes requests to 600+ models from 80+ providers at each provider’s list price, and adds its fee when you buy credit. AIGROW sells discounted credit for current Claude, GPT, Gemini and Grok models only. The table compares the models both sell, price by price.

See the table

Every model both sell costs less per token through AIGROW credit than at OpenRouter, on input and on output.

9models both sell, priced side by side

Less through AIGROW credit: 9 of 9
OpenRouter prices read: 12 November 2026
Model check: 11 November 2026
Sponsored placement: none

Nothing on this page is paid for by anyone.

Price per model: OpenRouter and AIGROW credit

USD per million tokens, input on the first line and output on the second. The difference is rounded so it never overstates a saving.

Prices per million tokens at OpenRouter and through AIGROW credit
Model	OpenRouter	AIGROW credit	Difference
Claude Opus 5.5	$4.00$20.00	$1.60$8.00	60% less60% less
Claude Fable 5.2	$8.00$40.00	$3.20$16.00	60% less60% less
Claude Fable 5.1	$10.00$50.00	$4.00$20.00	60% less60% less
GPT-6 Astra	$10.00$50.00	$2.50$12.50	75% less75% less
Claude Sonnet 5.5	$2.00$10.00	$0.80$4.00	60% less60% less
GPT-6.1 Sol	$2.00$10.00	$0.50$2.50	75% less75% less
GPT-6.1 Terra	$1.00$5.00	$0.25$1.25	75% less75% less
Grok 4.7	$2.00$6.00	$0.50$1.50	75% less75% less
Gemini 4 Argon	$2.00$10.00	$1.00$5.00	50% less50% less

OpenRouter’s prices as published on 12 November 2026, each linked from its row. AIGROW’s are the rates the endpoint bills with, at the price credit sells for. Prices change, so check theirs before you decide.

The table shows the standard price on each model’s page and leaves out OpenRouter’s fee, which it adds when you buy credit: 5.5% on Standard and 8% on Business. Some models also have endpoints at other prices: flex endpoints at half price for the GPT models and Gemini 4 Argon, and regional, fast or priority endpoints that cost more.

Fees and terms

What each one charges beyond the tokens, and what happens to credit you have not spent.

TermsAIGROWOpenRouter

Fee when you buy creditNone: $25 buys $100 of credit5.5% on Standard, 8% on Business

Smallest purchase$25Not stated on its pricing page

Credit expiryNo expiry date in our TermsUnused credit may expire one year after purchase, under its terms

RefundsSpent credit: never. Unspent credit: within 14 days of buying it, for consumers in the EU, EEA, UK and Switzerland.Unused credit, if asked within 24 hours of purchase; fees and crypto payments are not refunded

PaymentBy card, at the Stripe checkoutCards, Alipay and crypto (USDC); invoices on Enterprise

Models9 models from Anthropic, OpenAI, Google and xAI600+ models from 80+ providers

OpenRouter’s terms as published on the pages below, read on 12 November 2026. AIGROW’s are from our Terms of Service.

OpenRouter pricing · OpenRouter FAQ

Is the model the one you paid for?

How each side shows that the model answering is the one it sells.

OpenRouter: OpenRouter sends each request to the model’s maker or to a cloud that hosts the same model, such as Amazon Bedrock, Azure or Google Vertex, and names every provider on the model’s page. For the models in its Auto Exacto program, it benchmarks each provider endpoint and shows the results on that page. Our own check used OpenRouter as the reference for GPT, Gemini and Grok.
Certified genuine by AIGROW: On 11 November 2026 we sent each model we sell the same prompts as the same model at its maker or through OpenRouter, and compared the answers, the prompt tokens and the tool calls. 9 of the 9 models on this page met our rule. This is AIGROW’s own check: no model maker reviewed or endorsed it. See every result and the method

Results of the model check of 11 November 2026
Model	Here	At the maker
Compared with Anthropic’s API
Claude Opus 5.5	12 of 12	12 of 12
Claude Fable 5.2	12 of 12	12 of 12
Claude Fable 5.1	12 of 12	12 of 12
Claude Sonnet 5.5	12 of 12	12 of 12
Compared with the same model through OpenRouter
GPT-6 Astra	12 of 12	12 of 12
GPT-6.1 Sol	12 of 12	12 of 12
GPT-6.1 Terra	11 of 1212 of 12 with effort set to high	12 of 1211 of 12 with effort set to high
Grok 4.7	5 of 5	5 of 5
Gemini 4 Argon	7 of 1212 of 12 with effort set to low	11 of 126 of 12 with effort set to low

A 2026 study by the CISPA Helmholtz Center for Information Security tested 17 unofficial APIs that claim to give access to the makers’ models, and found identity verification failures in 45.83% of its fingerprint tests. It left out routing platforms that disclose where they send requests, such as OpenRouter. Any seller below list price can be checked with the script below, AIGROW included. Read the study.

Run the check yourself

Tests AIGROW’s GPT-6.1 Sol beside the same model through OpenRouter, with your OpenRouter key. Change the id to check another GPT, Gemini or Grok model; a Claude model compares with Anthropic’s API and needs an Anthropic key.

MODEL_CHECK_KEY=ag_your_key MAKER_KEY=sk-or-your_key node model-check.mjs gpt-6.1-sol

Download model-check.mjs

Every request is billed as usual. The battery is the costly one: a few cents of credit on most models, more when a model thinks for long. To test another seller’s API, pass its address with --base.

When OpenRouter is the better choice

Hundreds more models: OpenRouter lists 600+ models from 80+ providers, free models among them. AIGROW serves current models from Anthropic, OpenAI, Google and xAI, and nothing else.
Fallback to another provider: When a provider fails, OpenRouter can retry the request with another provider of the same model, or with another model you name.
Your own keys and invoices: OpenRouter can route through your own provider keys, with $25,000 of list-price inference a month free of its fee, and its Enterprise plan pays by invoice with a support SLA.
Half-price flex endpoints: For the GPT models and Gemini 4 Argon, OpenRouter also lists flex endpoints at half the standard price. Compare them with the AIGROW column before you choose.

Switching from OpenRouter

A base URL and a key that starts with ag_, created in API access on the dashboard.

At OpenRouter today: base URL https://openrouter.ai/api/v1
Anthropic SDK and Claude Code: base URL https://aigrow.gg
OpenAI SDK, Cline, Aider, OpenCode: base URL https://aigrow.gg/v1
Model ids: ours, such as claude-opus-5.5, and OpenRouter’s spelling, such as anthropic/claude-opus-5.5, both work.

Some lines behave differently from the maker’s endpoint, for example on max_tokens and on the starting reasoning effort: the model check lists each difference with its numbers. Codex sends Responses API requests, which this endpoint does not take.

The setup guide covers every other tool, and the Claude Code page walks through its settings one by one.

Questions about OpenRouter and AIGROW

Other comparisonsAIGROW vs CometAPI AIGROW vs AIHubMix AIGROW vs the Anthropic API AIGROW vs the OpenAI API OpenRouter alternatives

The table on this page sets each model’s price through AIGROW credit beside OpenRouter’s, with the difference worked out from the rates our endpoint bills with. OpenRouter also adds 5.5% when you buy credit on its Standard plan, which the table leaves out.

Yes. OpenRouter sends each request to the model’s maker or to a cloud that hosts the same model, such as Amazon Bedrock, Azure or Google Vertex, and names the provider on each model page. We used OpenRouter as the reference for GPT, Gemini and Grok when we checked our own models.

Yes. Both take OpenAI-style requests, so a tool that lets you set a base URL per provider can send Claude, GPT, Gemini and Grok calls to AIGROW and everything else to OpenRouter.

Yes, for the models in the table. AIGROW accepts the vendor prefix OpenRouter uses, such as anthropic/claude-opus-5.5, as well as the plain id.

600+ models, free models, automatic fallback to another provider, routing through your own provider keys, and invoices on its Enterprise plan. AIGROW serves current models from Anthropic, OpenAI, Google and xAI, and nothing else.