Skip to content

Ways to buy model access

Gateways, cloud and data platforms, and developer hubs: what each adds to the token price.Updated 5h ago

11 of 22 gateways and platforms

Gateway or platformFee on tokens
Independent gateways
Helicone
0% markup on credits; plans by requests and seats (Pro $79 a month) · BYOK 0% · 100+ modelsFallbacks, Caching, Guardrails, Observability, Rate limits
None
Kong AI Gateway
$100 a month per model proxied (Konnect Plus); no token fee · BYOK no · See page modelsFallbacks, Caching, Guardrails, Observability, Rate limits
None
LiteLLM
Open source, self-hosted with your own keys; enterprise license by quote · BYOK 0% · 100+ modelsFallbacks, Caching, Guardrails, Observability, Rate limits
None
Vercel AI Gateway
Provider list prices, no markup or platform fee on tokens · BYOK 0% · See page modelsFallbacks, Caching, Observability, Rate limits
None
Cloudflare AI Gateway
Core features free; 5% fee on Unified Billing credits · BYOK yes · See page modelsFallbacks, Caching, Guardrails, Observability, Rate limits
5%
Requesty
5% on top of model costs, pay as you go · BYOK yes · 600+ modelsFallbacks, Caching, Guardrails, Observability
5%
Eden AI
Provider prices passed through; 5.5% fee on credit purchases · BYOK yes · 500+ modelsFallbacks, Observability
5.5%
OpenRouter
Provider prices passed through; 5.5% fee on card credit purchases (5% crypto) · BYOK 5% · 500+ modelsFallbacks, Caching, Observability
5.5%
Martian GatewayUnverified
No public pricing · BYOK no · 200+ modelsObservability
Not published
Portkey
Per logged request: free 10k logs a month, Production from $49 a month · BYOK yes · 250+ modelsFallbacks, Caching, Guardrails, Observability, Rate limits
$49/mo
TrueFoundry AI GatewayUnverified
Per user and per request ($25 per user a month on Pro) · BYOK no · 1,600+ modelsFallbacks, Guardrails, Observability, Rate limits
$25/mo

A tick means the vendor's own pricing page or docs say so; a dash means we did not find it stated. An amber dot marks a row with facts we could not confirm.

Claude Sonnet 5 through each

Calculator

100M input and 20M output tokens a month: $400.00 direct from the lab.

Questions

What is an AI gateway?

A proxy between your app and model providers that gives you one API for many models, with fallbacks when a provider fails, caching, logs, rate limits and spend controls.

OpenRouter vs Vercel AI Gateway: which is cheaper?

Vercel AI Gateway states no markup and no platform fee on tokens. OpenRouter passes provider prices through but charges a fee when you buy credits (5.5% by card). With your own keys, OpenRouter's first allowance is free and then 5%.

What is BYOK?

Bring your own key: you give the gateway your own provider API key, pay the provider directly, and the gateway charges nothing or a small fee for routing.

Is Claude or GPT more expensive on Bedrock, Azure or Vertex AI?

Usually not in the default region: AWS Bedrock, Azure AI Foundry and Google Vertex AI mostly charge the lab's own list price, and some regional endpoints add about 10%. Each platform page lists every model it sells with the premium against the direct API.

How do Snowflake Cortex and Databricks price LLM calls?

In their own units: Snowflake bills Cortex AI functions in credits per million tokens and Databricks bills Foundation Model APIs in DBUs per million tokens. Their pages here convert those to dollars and state the credit or DBU price assumed.

Can I self-host an AI gateway?

Yes. LiteLLM, Portkey (gateway core) and Helicone publish open-source gateways you can run yourself; you pay only for hosting.

Pricing as read from each vendor's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.