InferenceHub charges the model provider’s native per-token rate with 0% markup. Pay as you go, or add a plan from $10/mo — either way one key runs every model and every coding agent, and you never hit a hard wall.
Launch offer: your first month matched 100% in credit.
How it compares
We don’t undercut the providers — we charge their rates. What you get for the same price is reach: every model, every agent, one key, no lock-in.
Capability
InferenceHub
Claude Code
Codex
Cursor
Models you can use
Claude, GPT, GLM, DeepSeek, Kimi, Qwen & more
Anthropic models only
OpenAI models only
A curated set, inside the editor
Coding agents on one key
Claude Code, Codex, Cursor, Kilo, Hermes
Claude Code only
Codex only
Cursor editor only
Switch model & tool without switching accounts
When you hit your limit
Keep going at pay-as-you-go — no hard stop
Blocked until the window resets
Blocked until the window resets
Throttled / blocked until reset
Deep Research included
Included — powered by GLM-5.2, doesn't touch your premium budget
Counts against your plan limits
Counts against your plan limits
Pay-as-you-go at native rates (no subscription)
Top up with crypto · no KYC
Comparison reflects each product’s standard plans as of July 2026. Per-token rates always match the native provider — no markup. Claude Code reaches Claude AND the open-weight daily drivers (GLM-5.2, DeepSeek, Kimi, MiniMax, Qwen); Cursor and other OpenAI-compatible editors reach the open-weight chat models AND Claude (via the gateway’s translation lane); Kilo Code reaches the full catalog — Claude, open-weight, and GPT-5.6.
Subscription
Every model. Three sizes.
Every plan gets every model and every coding agent on one key — a premium budget for flagship Claude and GPT, standard windows for everything else. Bigger plans buy bigger windows and bigger budgets.
All Access
every model, one key
$10/mo
Covers up to $300 of usage
≈ 30× the price, at native rates
Every model, including Opus — on one key.
$50/mo premium budget — Claude + GPT pooled, burstable, incl. Opus & GPT-5.6 Sol
Standard windows — $10 per 5-hour window, $60/week — for GLM-5.2, DeepSeek, Kimi, MiniMax, Qwen + lower-priced frontier like Sonnet
Deep Research included in hosted chat — powered by GLM-5.2
Every coding agent (Claude Code, Codex, Cursor, Kilo, Hermes, ZCode) — every open-weight model runs inside Claude Code
Overflow at 0%-markup pay-as-you-go — no hard stop
Premium models: One $50/month premium budget shared across Claude and GPT (Opus, GPT-5.6 Sol) — burstable, not weekly-paced, and pooled: spend all of it on either vendor. Every other model — open-weight and lower-priced frontier alike — draws from the much larger standard windows.
Most popular
Plus
for heavier daily driving
$25/mo
Covers up to $1,000 of usage
≈ 40× the price, at native rates
Bigger windows, serious frontier budgets.
$200/mo premium budget — Claude + GPT pooled, burstable, incl. Opus & GPT-5.6 Sol
Standard windows for multi-agent sessions — $40 per 5-hour window, $250/week
Everything in All Access — every model, every agent, Deep Research, no hard stop
Premium models: One $200/month premium budget shared across Claude and GPT (Opus, GPT-5.6 Sol) — burstable, not weekly-paced, and pooled: spend all of it on either vendor. Every other model — open-weight and lower-priced frontier alike — draws from the much larger standard windows.
Max
for all-day agent fleets
$50/mo
Covers up to $2,500 of usage
≈ 50× the price, at native rates
The heaviest windows we sell.
$500/mo premium budget — Claude + GPT pooled, burstable, incl. Opus & GPT-5.6 Sol
Standard windows for fleets — $100 per 5-hour window, $625/week
Everything in All Access — every model, every agent, Deep Research, no hard stop
Premium models: One $500/month premium budget shared across Claude and GPT (Opus, GPT-5.6 Sol) — burstable, not weekly-paced, and pooled: spend all of it on either vendor. The standard windows are sized for fleets of agents.
The premium budget covers premium models (Opus, GPT-5.6 Sol), pooled across Claude and GPT. It's burstable — spend it all on either vendor, in one day if you want. Every other model, open-weight and lower-priced frontier alike, draws the standard windows, which reset every 5 hours and weekly. Reach any limit and you keep working at pay-as-you-go rates — no hard stop. Pay by card, or by crypto (pay-per-period, no KYC).
Your first month's payment is matched 100% in bonus credit, usable for inference only and expiring 30 days after issue. New subscribers only, one per customer.
No commitment
Prefer to just pay as you go?
Skip the subscription entirely. Pay only for the tokens you use, at the model provider's native rate — the same price as going direct.
Native per-token rates — 0% markup, on every model
Start with $1 in free credit — no credit card required
No monthly commitment and no minimums
Top up by card or crypto — no lock-in, no KYC
Real-time usage and balance tracking in the portal
Subscriptions overflow here automatically — so you never hit a wall
Yes. You pay the model provider's native per-token rate with 0% markup — the price in our Models list is the price you pay. We don't surcharge your tokens; subscriptions and scale are how the business works, not a hidden markup.
One key. Every model. No markup.
Get started in minutes with $1 in free credit — no credit card required.