Ship AI products without provider friction.
Undercut the price, not the model.
An OpenAI- and Anthropic-compatible gateway for Claude Code and production apps. Choose the right model, pay only for tokens used, and track every request.
$ export ANTHROPIC_BASE_URL=https://undercut.pro
$ export ANTHROPIC_API_KEY=gw_••••••••••••
$ claude
✓ Connected through UndercutAIModel routing
The right intelligence for every request.
Switch models with one parameter. No new SDK, billing account, or infrastructure.
Claude Opus
Deep reasoning
Claude Sonnet
Balanced & fast
Claude Fable
Everyday workloads
GPT-5.6
Frontier intelligence
Temporary launch pricing
55% below public API prices.
The current 55% launch discount is temporary. Standard savings will be 30% below reference public API prices. One table, every rate: each token category is priced and billed separately.
| Model | Standard tokens | Cached tokens | Savings | ||
|---|---|---|---|---|---|
| Input | Output | Cache read | Cache write | ||
Claude Opus 5 claude-opus-5 | $5.00$2.25 | $25.00$11.25 | $0.50$0.225−95.5% vs public input | $6.25$2.8125 | −55% |
Claude Sonnet 5 claude-sonnet-5 | $2.00$0.90 | $10.00$4.50 | $0.20$0.09−95.5% vs public input | $2.50$1.125 | −55% |
Claude Fable 5 claude-fable-5 | $10.00$4.50 | $50.00$22.50 | $1.00$0.45−95.5% vs public input | $12.50$5.625 | −55% |
GPT-5.6 Sol gpt-5.6-sol | $5.00$2.25 | $30.00$13.50 | $0.50$0.225−95.5% vs public input | $6.25$2.8125 | −55% |
GPT-5.6 Terra gpt-5.6-terra | $3.00$1.35 | $18.00$8.10 | $0.30$0.135−95.5% vs public input | $3.75$1.6875 | −55% |
GPT-5.6 Luna gpt-5.6-luna | $0.50$0.225 | $2.50$1.125 | $0.05$0.0225−95.5% vs public input | $0.625$0.2813 | −55% |
Gemini 3.6 Flash gemini-3.6-flash | $0.30$0.135 | $1.20$0.54 | $0.03$0.0135−95.5% vs public input | $0.375$0.1688 | −55% |
Grok 4.5 grok-4.5 | $3.00$1.35 | $15.00$6.75 | $0.30$0.135−95.5% vs public input | $3.75$1.6875 | −55% |
Kimi K3 kimi-k3 | $0.60$0.27 | $3.00$1.35 | $0.06$0.027−95.5% vs public input | $0.75$0.3375 | −55% |
Built for developers
Familiar APIs. Full visibility.
Keep your OpenAI or Anthropic client. Change the base URL and API key, then monitor model, input tokens, output tokens, and derived cost from one dashboard.
Usage-based billing
USD balance with request-level spend history.
Keys you control
Create and revoke credentials instantly.
Transparent pricing
Configured per-million input and output rates.
Claude Code ready
Use a custom Anthropic-compatible endpoint.
Current balance
$48.27
claude-sonnet-5
12,480 tokens
$0.084
gpt-5.6-sol
7,234 tokens
$0.037
claude-opus-5
3,902 tokens
$0.126
Frequently asked questions
Questions worth asking.
Clear answers about pricing, model authenticity, verification, and what stays private to protect the service.
A practical trust policy
We do not treat a model's self-reported name as proof. Controlled, repeatable comparisons are more meaningful than screenshots or unverifiable claims.
01What is UndercutAI?
UndercutAI is a prepaid AI API gateway. One key and one balance give you access to supported frontier models through familiar OpenAI- and Anthropic-compatible endpoints. You choose the model in every request and see token-level usage and cost in one dashboard.
02Why is it cheaper than buying from each provider directly?
The savings come from aggregated demand, infrastructure and routing optimization, cache-aware billing, batch processing where supported, and a lower service margin—not from silently replacing the model you request. Rates are shown per token category, so you can estimate and audit costs before scaling.
03Is the 55% discount permanent?
No. The current 55% discount is temporary launch pricing. The standard discount is planned to be 30% below reference public API prices. The pricing table always shows the rate currently applied, so check it before making a cost-sensitive deployment decision.
04Are requested models replaced with cheaper models?
No. UndercutAI does not intentionally substitute a requested model with an unrelated lower-cost model. That is the whole point of "Undercut the price, not the model." — the model identifier in your request is the product you are buying. Routing details may remain confidential, but a lower price is not permission to silently downgrade the model.
05How can I verify that a model is genuine?
No black-box API can offer cryptographic proof of a model's identity without exposing sensitive upstream access. The strongest practical check is a controlled side-by-side test: send the same prompts and settings through UndercutAI and the model's official console, then compare model-specific capabilities such as tool calling, structured output, long-context recall, known feature limits, token usage patterns, and quality across multiple runs. Use a test suite—not a single prompt.
06Can I just ask the model what it is?
No. Self-identification is weak evidence: a system prompt can change the answer, and different models can imitate the same response. Capability tests with fixed inputs, low temperature, repeat runs, and an official baseline are much harder to fake and produce a more useful comparison.
07Why don't you publish upstream accounts or raw provider headers?
Publishing credentials, account identifiers, raw upstream headers, or routing topology would make the infrastructure easy to abuse or copy and could reduce availability for every customer. We keep those operational details private while exposing the information customers need to audit their own usage: requested model, token categories, applied rate, cost, and history.
08Why might two answers differ from the official console?
Model output is probabilistic. Temperature, system instructions, tool definitions, context, provider-side model updates, and even repeated runs can change an answer. For a fair comparison, keep every input and parameter identical, run several samples, and judge capability and consistency rather than exact wording.
09What do I need to change in my application?
Usually only the base URL and API key. Keep your existing OpenAI or Anthropic client, select a supported model, and monitor usage from the dashboard. The quickstart page includes ready-to-copy examples for popular SDKs and developer tools.
Launch pricing active · 55% off
Your next model is one API call away.
Create an account, add funds, and issue your first key in minutes.
Create free account