A Portkey alternative with 0% fee and a budget on every key
Portkey, now Prisma AIRS AI Gateway, has a Production plan at $49 a month that includes 100K recorded logs. Hopscotch needs no monthly plan to start, charges 0% on credit, and puts a budget on every key of its AI gateway.
Portkey Production includes 100K recorded logs, then $9 per extra 100K. Its pricing page lists no fee on tokens. Checked Nov 6, 2026.
0% fee on every top-up.
Credit from $5, and every token at the provider's list price. Or pick a Pass: each seat gets twice its price in model use every month.
A budget, fallbacks and guardrails on every key.
Refused and blocked requests cost $0.
A 99.9% availability target, with service credits.
On every account, not only an enterprise tier.
- Anthropic
- OpenAI
- DeepSeek
- Qwen
- Meta
- Mistral AI
- Moonshot AI
- MiniMax
- Z.ai
- Cohere
Hopscotch vs Portkey
Hopscotch is an LLM gateway: one API key for 500+ models from Anthropic, OpenAI, Google and DeepSeek, with spend limits, fallbacks and request logs built in. It is a Portkey alternative for teams that want the single key with no monthly plan to manage.
A budget on every key, without an Enterprise contract
Every key, teammate and workspace gets its own cap. A request over it is refused before it reaches the provider, so it costs $0. Portkey puts budget limits on Enterprise and select Pro customers.
Passes: 2x what you pay in model use
Each seat gets twice its price in model use, on every model, frontier included, at provider rates with no markup. Portkey's $49 Production plan buys log volume and features, and every token is still billed at full price by the provider.
Monthly, per seat.
Hopscotch vs Portkey: where the routes split
| Feature | Hopscotch | Portkey |
|---|---|---|
| Monthly plan | Not needed: credit from $5. Optional Passes from $20 a seat give twice the price in model use (limited time) | Free tier, then $49 a month (Portkey pricing page, Nov 6, 2026) |
| Platform fee on tokens | 0% on credit purchases | None listed on its pricing page; plans carry a monthly fee instead (Nov 6, 2026) |
| Request logs | Request logs built in | 10K logs a month kept 3 days (free) or 100K kept 30 days (Production), then $9 per 100K up to 3M |
| Fallbacks | Up to five models per routing profile, tried in the order you set, changed in the dashboard without a deploy | Automatic fallbacks, retries and load balancing on every plan, open source included. |
| Self-host | No, managed only | Open-source gateway you host yourself; VPC hosting on Enterprise |
| Uptime commitment | 99.9% monthly availability target with service credits, on every account | SLAs on Enterprise only; no uptime figure on its pricing page |
Three questions that decide it
On Hopscotch you can buy credit from $5 with no plan, and every token is billed at the provider's list price. Want a monthly plan anyway? Passes give each seat twice its price in model use: $20 for $40, $50 for $100 or $200 for $400, at provider rates with no markup. Limited time offer.
See pricingEvery Hopscotch key carries its own budget, and a request over the limit is refused before it reaches the provider. The loop stops, and the refused requests cost nothing. Teammates and the whole workspace get ceilings too.
See spend controlsOn Hopscotch, requests on your own OpenAI, Anthropic or Google key are billed by that provider, with no Hopscotch fee at any volume.
See bring your own keyHow to switch from Portkey in four steps
- 01
Sign up, add credit from $5, and copy the key from the dashboard.
- 02
In the OpenAI SDK you already use, set base_url to https://api.hopscotchlabs.ai/v1 and api_key to your Hopscotch key. Nothing else in your client changes.
- 03
Model IDs take the form provider/model, such as anthropic/claude-sonnet-5. A bare ID is refused with a 400 so nothing silently routes to a provider you did not pick. Pull the list from GET /v1/models or the models catalog.
- 04
Portkey configs and virtual keys have no one-click import. Put backups in a routing profile and call it as profile/your-name. Set a routing profile as your default and it calls that profile in the order you set; until you do, it answers from Hopscotch's balanced shortlist for your workspace.
Your coding agent moves the same way. Setup guides exist for OpenCode, Cline, Codex CLI, Cursor, Aider, Continue and Zed. The quickstart walks through your first request.
from openai import OpenAI
client = OpenAI(
base_url="https://api.hopscotchlabs.ai/v1", # was: your Portkey gateway URL
api_key="YOUR_HOPSCOTCH_KEY", # was: your Portkey key
)
# model ids gain a provider: anthropic/claude-sonnet-5
client.chat.completions.create(model="anthropic/claude-sonnet-5", messages=[...])How Hopscotch compares with other Portkey alternatives
Here is what each gateway costs you, in fees or in work.
More comparisons: OpenRouter alternative, LiteLLM alternative, Vercel AI Gateway alternative, OrcaRouter alternative and Cheaper Inference alternative.
| Gateway | What it is | What you take on |
|---|---|---|
| Hopscotch | Managed gateway: one key, provider list price, budgets and guardrails on every key | Nothing on top: 0% fee on credit |
| Prisma AIRS AI Gateway (formerly Portkey) | Centralized AI governance and LLMOps platform | A plan fee and a monthly log allowance, with budget limits on Enterprise |
| OpenRouter | Managed gateway with public usage rankings and a large app ecosystem | A 5.5% to 8% fee on every top-up |
| Vercel AI Gateway | Managed gateway that works from any server, with no markup or platform fee on tokens | A Vercel team account, and card processing fees where they apply |
| LiteLLM | Open-source proxy on your own provider keys | Hosting, scaling and patching the proxy yourself |
| Cloudflare AI Gateway | Proxy for caching, logging and rate limits | A 5% fee on Cloudflare credit, or a key and bill per provider |
| Direct provider APIs | Each provider's own API and key | No failover, and a key and bill per provider |
Portkey alternatives: questions people ask before switching
Does Hopscotch charge a gateway fee?
No. Hopscotch charges 0% on credit. Portkey's pricing page, checked Nov 6, 2026, lists plan fees and log overages, and no fee on tokens.
How does Portkey pricing compare?
Hopscotch needs no plan: pay as you go from $5. Or pick a Pass: Starter is $20 a month for $40 of model use, Growth $50 for $100 and Pro $200 for $400, for a limited time. Portkey lists a free tier, a $49 a month Production plan and custom Enterprise pricing (pricing page, Nov 6, 2026).
How do Portkey's log limits work?
Hopscotch has request logs built in on every account. Portkey's pricing page lists 10K recorded logs a month on the free tier, kept 3 days, and 100K on Production, kept 30 days, then $9 per 100K up to 3M (Nov 6, 2026).
Does Portkey have budgets and guardrails too?
On Hopscotch, guardrails are free and every key has a budget, on every account. Portkey lists deterministic guardrails on its free tier and LLM and partner guardrails on Production; its docs put budget limits on Enterprise and select Pro customers (Nov 6, 2026).
Is Hopscotch a Portkey AI gateway alternative for production?
Yes. Hopscotch is a managed gateway with a 99.9% monthly availability target, service credits, per-key budgets and fallbacks on every account.
Can I self-host Hopscotch?
No, Hopscotch is a managed gateway. Portkey's open-source gateway can be self-hosted. For a self-hosted proxy, see the LiteLLM comparison.
Portkey vs LiteLLM: where does Hopscotch fit?
Hopscotch is managed, pay as you go, with no server to run. Portkey, now Prisma AIRS AI Gateway, is a gateway with plans, and LiteLLM is a proxy you host.
Can I move my Portkey setup to Hopscotch?
Yes. Set the base URL to https://api.hopscotchlabs.ai/v1, paste your key and use provider/model names. Rebuild Portkey configs as routing profiles; there is no one-click import.
Same models, one base URL change, a budget on every key
Connect your SDK to Hopscotch, add credit and send a request. If a plan fee was the reason you looked for a Portkey alternative, you can skip it.