Skip to content

Requesty

Pricing page

442 listings across 154 models

Data policies

from the provider's published policies

Privacy policyStatus page

On training

We do not train machine learning models on your data, and we never sell personal information.

Source: Requesty privacy policy

On keeping your data

Logging control allows you to disable prompt and output storage entirely (Zero Data Retention mode).

Source: Requesty privacy policy

More from Requesty on keeping your data (1)

When logging is enabled, data is stored encrypted within the EU for up to 30 days.

Source: Requesty privacy policy

We take these statements from Requesty's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Page 1 of 7. The lists below split this page's listings into those sold by Requesty, run by Requesty, or sent to Requesty by a marketplace.

Sold by Requesty

110 listings on this page sold by Requesty.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Claude Opus 5
Inference by Amazon Web Services
$5.00cache read $0.50$25.00cache write $6.251M
Claude Fable 5bedrock/claude-fable-5@us-east-1 · 🇺🇸 us-east-1
Inference by Amazon Web Services
$11.00cache read $1.10$55.00cache write $13.751M
GPT-5.6 Solazure/gpt-5.6-sol@eastus2 · 🇺🇸 eastus2
Inference by Microsoft Azure
$4.00cache read $0.40$20.00cache write $5.001.1M
GPT 5.5bedrock/gpt-5.5@us-east-1 · 🇺🇸 us-east-1
Inference by Amazon Web Services
$5.50cache read $0.55$33.001.1M
Claude Opus 4.8
Inference by Amazon Web Services
$5.00cache read $0.50$25.00cache write $6.251M
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash
Inference by DeepSeek
$0.30cache read $0.006$1.201M
Kimi K3
Inference by Fireworks AI
$3.00cache read $0.30$15.001M
Qwen3.8 Max
Inference by Alibaba Cloud
$2.00cache read $0.25$6.00cache write $2.501M
Claude Opus 4.7
Inference by Amazon Web Services
$5.00cache read $0.50$25.00cache write $6.251M
Grok 4.6
Inference by xAI
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00cache write $2.00500K
Claude Opus 4.6
Inference by Amazon Web Services
$5.00cache read $0.50$25.00cache write $6.251M
Inference by DeepSeek
$1.32cache read $0.044$3.961M
GPT 5.4bedrock/gpt-5.4@us-east-1 · 🇺🇸 us-east-1
Inference by Amazon Web Services
$2.75cache read $0.275$16.501.1M
Grok 4.5
Inference by xAI
$2.00>200k $4.00cache read $0.50$6.00>200k $12.00cache write $2.00500K
Gemini 3 Pro Preview
Inference by Google
$2.00>200k $4.00cache read $0.20$12.00>200k $18.00cache write $4.501M
Claude Sonnet 5
Inference by Amazon Web Services
$2.00cache read $0.20$10.00cache write $2.501M
Inference by Google
$2.00>200k $4.00cache read $0.20$12.00>200k $18.00cache write $4.501M
Gemini 3.5 Flash
Inference by Google
$1.50cache read $0.15$9.00cache write $1.5831M
GPT-5.6 Terraazure/gpt-5.6-terra@eastus2 · 🇺🇸 eastus2
Inference by Microsoft Azure
$2.00cache read $0.20$12.00cache write $2.501.1M
GPT-5.6 Lunaazure/gpt-5.6-luna@eastus2 · 🇺🇸 eastus2
Inference by Microsoft Azure
$0.20cache read $0.02$1.20cache write $0.251.1M
Qwen3.7 Max
Inference by Alibaba Cloud
$2.50cache read $0.25$7.50cache write $3.1251M
Gemini 3.6 Flash
Inference by Google
$1.50cache read $0.15$7.001M
Fugu Ultra
Inference by Sakana AI
$5.00cache read $0.50$30.001MNot enough data yetNot measuredNot measured
Claude Opus 4.5
Inference by Amazon Web Services
$5.00cache read $0.50$25.00cache write $6.25200K
GLM 5.2
Inference by Doubleword
$1.40$4.401M
Show all 110 listings

Showing 25 of 110: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

Around the web

  • Requesty
    Requesty is the control plane for AI spend and access, a single OpenAI-compatible endpoint that …Requesty is the control plane for AI spend and access, a single OpenAI-compatible endpoint that gives teams access to 600+ models from major providers without ...Read more

    uk.linkedin.com

  • Requesty AI Gateway | AWS Marketplace - Amazon.com
    Requesty is an enterprise AI gateway that provides a single API for accessing and managing …Requesty is an enterprise AI gateway that provides a single API for accessing and managing large language models across multiple providers.Read more

    aws.amazon.com

  • Requesty
    Requesty is a unified LLM gateway that provides access to over 300 large language models …Requesty is a unified LLM gateway that provides access to over 300 large language models from leading providers like OpenAI, Anthropic, Google, Mistral, AWS, ...Read more

    ai-sdk.dev

  • Requesty vs OpenRouter: A Detailed Comparison
    Requesty is a production-grade LLM router. Requesty gives you access to 300+ AI models through …Requesty is a production-grade LLM router. Requesty gives you access to 300+ AI models through a unified gateway, with built-in optimization, ...

    truefoundry.com

  • Requesty - AI Agent | Pricing, Reviews & Alternatives
    Requesty is a conversational intelligence platform designed to help businesses make data-driven decisions by analyzing …Requesty is a conversational intelligence platform designed to help businesses make data-driven decisions by analyzing customer conversations.Read more

    aiagentstore.ai

How this data works