AIGROW vs Amazon Bedrock
Amazon Bedrock serves Claude, GPT and Grok from accounts AWS operates, at the makers’ list prices on its global route and 10% more inside one region, on the monthly AWS bill. AIGROW sells discounted prepaid credit for the same models through an OpenAI-compatible endpoint, with no AWS account. The table compares the models both sell, price by price.
Every model both sell costs less per token through AIGROW credit than at Amazon Bedrock, on input and on output.
- Less through AIGROW credit
- 10 of 10
- Amazon Bedrock prices read
- 18 November 2026
- Model check
- 11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
- Sponsored placement
- none
Price per model: Amazon Bedrock 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.
| Model | Amazon Bedrock | 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 Sonnet 5.5 | $2.00$10.00 | $0.80$4.00 | 60% less60% less |
| Claude Haiku 5.5 | $0.10$0.50 | $0.04$0.20 | 60% less60% less |
| GPT-6.1 Terra | $1.00$5.00 | $0.25$1.25 | 75% less75% less |
| GPT-6 Luna | $0.10$0.50 | $0.025$0.125 | 75% less75% less |
| Grok 4.7 | $2.00$6.00 | $0.50$1.50 | 75% less75% less |
| Claude Fable 5.1Previous version, replaced by Claude Fable 5.2 | $10.00$50.00 | $4.00$20.00 | 60% less60% less |
| GPT-6 AstraPrevious version, replaced by GPT-6.2 Astra | $10.00$50.00 | $2.50$12.50 | 75% less75% less |
| GPT-6.1 SolPrevious version, replaced by GPT-6.2 Sol | $2.00$10.00 | $0.50$2.50 | 75% less75% less |
Amazon Bedrock’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.
Bedrock’s prices here are its Standard tier on the global route. In-Region and geographic routes cost 10% more, its Priority tier costs 75% more, and its Flex tier and batch requests cost 50% less. GPT prompts over 272,000 input tokens are billed at higher long-context rates. AIGROW has no batch rate.
Fees and terms
What each one charges beyond the tokens, and what happens to credit you have not spent.
Amazon Bedrock’s terms as published on the pages below, read on 18 November 2026. AIGROW’s are from our Terms of Service.
Amazon Bedrock pricing · Amazon Bedrock model cards · Amazon Bedrock on data protection · AWS Customer Agreement
Is the model the one you paid for?
How each side shows that the model answering is the one it sells.
- Amazon Bedrock
- Bedrock’s documentation says each provider’s models run in a deployment account that the Bedrock service team owns and operates, and that model providers have no access to it. As of 18 November 2026 we have not run our check on Amazon Bedrock. 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. 10 of the 10 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
| 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 Sonnet 5.5 | 12 of 12 | 12 of 12 |
| Claude Haiku 5.5 | 12 of 12 | 12 of 12 |
| Claude Fable 5.1 | 12 of 12 | 12 of 12 |
| Compared with the same model through OpenRouter | ||
| GPT-6.1 Terra | 11 of 1212 of 12 with effort set to high | 12 of 1211 of 12 with effort set to high |
| GPT-6 Luna | 8 of 128 of 12 with effort set to high | 9 of 1210 of 12 with effort set to high |
| Grok 4.7 | 5 of 5 | 5 of 5 |
| GPT-6 Astra | 12 of 12 | 12 of 12 |
| GPT-6.1 Sol | 12 of 12 | 12 of 12 |
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 Bedrock’s GPT-6.1 Sol beside the same model through OpenRouter, with a Bedrock API key and 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_bedrock_api_key MAKER_KEY=sk-or-your_key MAKER_MODEL=openai/gpt-6.1-sol node model-check.mjs --base https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1 global.openai.gpt-6.1-solEvery 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 Amazon Bedrock is the better choice
- Inside your AWS account
- Bedrock usage lands on the monthly AWS bill and requests can be signed with AWS credentials. AWS says model providers have no access to customer prompts and completions. AIGROW is a separate prepaid account with its own keys.
- Service tiers and regional routes
- Bedrock sells Reserved, Priority, Standard and Flex tiers and a batch rate, and it can keep inference inside one region or geography for 10% more. AIGROW has one rate per model and no regional endpoint.
- A wider catalogue and more APIs
- Bedrock lists models from many providers, image and video models among them, and serves them through its Converse and Invoke APIs as well as OpenAI-compatible ones. AIGROW sells a short list of current chat models.
Switching from Amazon Bedrock
A base URL and a key that starts with ag_, created in API access on the dashboard.
- At Amazon Bedrock today: base URL https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1
- Anthropic SDK and Claude Code: base URL https://aigrow.gg
- OpenAI SDK, Cline, Aider, OpenCode: base URL https://aigrow.gg/v1
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 Amazon Bedrock and AIGROW
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