AIGROW vs Requesty

Requesty routes requests to 600+ models from 30+ providers at each provider’s rate, and adds 5% on pay as you go or nothing when you bring your own provider keys. AIGROW sells discounted credit for a short list of current Claude, GPT, Gemini, Grok, Qwen and Kimi models. 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 Requesty, on input and on output.

15AIGROW vs Requestymodels both sell, priced side by side
Less through AIGROW credit
15 of 15
Requesty prices read
18 November 2026
Model check
11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
Sponsored placement
none
Nothing on this page is paid for by anyone.

Price per model: Requesty 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 Requesty and through AIGROW credit
ModelRequestyAIGROW creditDifference
Claude Opus 5.5$4.20$21.00$1.60$8.0061% less61% less
Claude Fable 5.2$8.40$42.00$3.20$16.0061% less61% less
Claude Sonnet 5.5$2.10$10.50$0.80$4.0061% less61% less
Claude Haiku 5.5$0.105$0.525$0.04$0.2061% less61% less
GPT-6.1 Terra$1.05$5.25$0.25$1.2576% less76% less
GPT-6 Luna$0.105$0.525$0.025$0.12576% less76% less
Grok 4.7$2.10$6.30$0.50$1.5076% less76% less
Gemini 4 Argon$2.10$10.50$1.00$5.0052% less52% less
Kimi K3.1 Pro$2.10$10.50$1.00$5.0052% less52% less
Gemini 4 Hydrogen$1.575$7.875$0.75$3.7552% less52% less
Gemini 3.8 Flash$0.7875$3.9375$0.375$1.87552% less52% less
Claude Fable 5.1Previous version, replaced by Claude Fable 5.2$10.50$52.50$4.00$20.0061% less61% less
GPT-6 AstraPrevious version, replaced by GPT-6.2 Astra$10.50$52.50$2.50$12.5076% less76% less
GPT-6.1 SolPrevious version, replaced by GPT-6.2 Sol$2.10$10.50$0.50$2.5076% less76% less
Qwen3.8 MaxPrevious version, replaced by Qwen4-Max$2.10$6.30$1.00$3.0052% less52% less

Requesty’s prices as published on 18 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.

Requesty’s model pages print each provider’s rate and say pay as you go adds 5%. The table shows the rate with that 5% added. Its Gemini 4 Argon and Gemini 3.8 Flash rates were marked 50% off on the day we read them.

Fees and terms

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

TermsAIGROWRequesty
Fee when you buy creditNone: $10 buys $40 of credit5% on model cost on pay as you go, none with your own provider keys
Smallest purchase$10No minimum spend and no per-seat price
Credit expiryNo expiry date in our TermsNot stated on its pricing page
RefundsSpent credit: never. Unspent credit: within 14 days of buying it, for consumers in the EU, EEA, UK and Switzerland.Not stated on its pricing page
PaymentCard, Apple Pay, Google Pay or Amazon Pay at the Stripe checkout; WeChat Pay, Pix, UPI or crypto for a one-off packMajor credit cards, and invoices by ACH or wire for enterprise customers
Models17 models from Anthropic, OpenAI, Google and xAI600+ models from 30+ providers

Requesty’s terms as published on the pages below, read on 18 November 2026. AIGROW’s are from our Terms of Service.

Requesty pricing · Requesty models

Is the model the one you paid for?

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

Requesty
Requesty’s model pages name the provider behind each id, such as Anthropic, OpenAI or Google Vertex AI. On 18 November 2026 we found no published test of those routes beside the makers’ own APIs on the pages we read, and we have not run our check on Requesty. The script below can produce a result for either side.
Certified genuine by AIGROW
On 11 November 2026, 15 November 2026, 16 November 2026 and 18 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. 15 of the 15 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, 15 November 2026, 16 November 2026 and 18 November 2026
ModelHereAt the maker
Compared with Anthropic’s API
Claude Opus 5.512 of 1212 of 12
Claude Fable 5.212 of 1212 of 12
Claude Sonnet 5.512 of 1212 of 12
Claude Haiku 5.512 of 1212 of 12
Claude Fable 5.112 of 1212 of 12
Compared with the same model through OpenRouter
GPT-6.1 Terra11 of 1212 of 12 with effort set to high12 of 1211 of 12 with effort set to high
GPT-6 Luna8 of 128 of 12 with effort set to high9 of 1210 of 12 with effort set to high
Grok 4.75 of 55 of 5
Gemini 4 Argon7 of 1212 of 12 with effort set to low11 of 126 of 12 with effort set to low
Kimi K3.1 Pro11 of 1212 of 12
Gemini 4 Hydrogen0 of 1211 of 12 with effort set to medium12 of 1211 of 12 with effort set to medium
Gemini 3.8 Flash10 of 1211 of 12
GPT-6 Astra12 of 1212 of 12
GPT-6.1 Sol12 of 1212 of 12
Qwen3.8 Max5 of 55 of 5

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 Requesty’s GPT-6.1 Sol beside the same model through OpenRouter, with an OpenRouter key as the reference. To test AIGROW the same way, leave out --base and MAKER_MODEL, use an AIGROW key and name the model gpt-6.1-sol.

MODEL_CHECK_KEY=your_requesty_key MAKER_KEY=sk-or-your_key MAKER_MODEL=openai/gpt-6.1-sol node model-check.mjs --base https://router.requesty.ai/v1 openai/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 Requesty is the better choice

Many more models, with fallback
Requesty lists 600+ models from 30+ providers behind one endpoint, with routing policies, automatic fallbacks and load balancing. AIGROW serves a short list of current models.
Your own provider keys at no markup
With your own provider keys, Requesty adds nothing to the provider’s rate.
EU data residency on every plan
Requesty says EU data residency is available on every plan, with traffic, logs and analytics kept in EU-based infrastructure by default.
Enterprise sign-on and controls
Its Enterprise plan adds SSO through Okta, Azure AD, Google Workspace or custom OIDC, role-based access, audit logs and custom SLAs.

Switching from Requesty

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

  • At Requesty today: base URL https://router.requesty.ai/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 Requesty’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.

Requesty bills each provider’s rate plus 5% on pay as you go. The table on this page sets each model’s price through AIGROW credit beside that figure, with the difference worked out from the rates our endpoint bills with.

Requesty’s model pages name the provider each id is sent to. Run the same test on both. Our public script sends any endpoint twelve questions with one right answer, a two-word prompt, four short questions and a tool call, and prints the score and the prompt tokens beside the same model at its maker or through OpenRouter. We have not run it on Requesty.

Yes. Both take OpenAI-style requests, so a tool that lets you set a base URL per provider can send the models in the table to AIGROW and everything else to Requesty.

The plain ids do, such as claude-opus-5-5 and gpt-6.1-sol, and so do ids with a maker prefix, such as anthropic/claude-opus-5-5. Ids that name a cloud route, such as vertex/gemini-4-argon, do not: use gemini-4-argon.

600+ models, free models with a daily request allowance, routing with fallback, your own provider keys at no markup, EU data residency and enterprise sign-on. AIGROW serves a short list of current models at a discount.

Run your own workload on both, then compare the bills.

Start with the $10 pack, run your real workload against it, and check the dashboard before buying more.

Monthly plans or one-off packs · redemption code delivered at once · usage dashboard included