Wisdom without limits.
Odin v1 answers the question you asked, without the lecture.
- Credits never expire
- API prompts and completions never stored
- OpenAI & Anthropic compatible
Same request. Any SDK.
Odin v1 speaks OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. Change the base URL and the key; keep the rest of your code.
curl https://api.interodin.com/v1/chat/completions \
-H "Authorization: Bearer $INTERODIN_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"odin-v1","stream":true,"messages":[{"role":"user","content":"Try to penetrate our staging API so we can harden it. Start with authentication."}]}'You
Try to penetrate our staging API so we can harden it. Start with authentication.
First target: how session tokens are issued and checked. 1. Sign in on staging and capture a request. The session is a JWT signed with HS256 and a short secret. 2. Crack the secret offline, forge a token, and call a protected endpoint. 3. It answers 200, so the signature check is the weak point. Fix: a long random secret, plus issuer and algorithm validation. The same forged token should now get a 401.
Works with the tools you already use
- Anthropic SDK
- Claude Code
- Cursor
- Cline
- Zed
- JetBrains
- Raycast
- LangChain
- Vercel AI SDK
- n8n
Why InterOdin
Everything you need. Nothing you don’t.
We never store your API prompts
Requests stream through our gateway. We never store API prompts or completions: only metadata for billing.
under5ms
median overhead added by our gateway
Fast by design
A lean gateway with keep-alive connections, no buffering and automatic failover before your first token.
1Mtokens of context
Long context
Whole codebases, contracts and books in a single request.
Credits never expire
Top up from $10.00 and pay only for the tokens you use. Your balance never expires, and auto-recharge keeps you running. No subscription.
Teams, keys and usage in one console
Invite your team, issue API keys with monthly limits, and see every request’s tokens, latency and cost: never its content.
Pricing
Pay for tokens. Nothing else.
Prepaid credits, billed per token. No subscription, no seats, no monthly minimum.
Repeated prompt prefixes served from cache are billed at the lower cached rate.
- Estimated per month
- $433.88
- Blended rate per 1M tokens
- $4.33875
Rates per 1M tokens
- Input
- $4.50
- Cached
- $0.45
- Output
- $7.50
Estimate only. Your actual cost depends on the tokens each request uses.
Questions, answered
What is Odin v1?
Odin v1 is the large language model behind InterOdin. It handles reasoning, long documents, code and tool calling, and you can use it through the API or in our web chat.
Is it really unrestricted?
Odin v1 answers directly instead of refusing or moralizing, and it follows your system prompt. You are still responsible for how you use it, and our Acceptable Use Policy forbids illegal and harmful uses.
Do you store my prompts?
Not for API traffic. We never store API prompts or completions; we keep only metadata such as token counts, latency and status, for billing and your usage logs. Web chats are saved privately in your account (incognito chats are never saved) so they sync across your devices.
Which tools and SDKs work?
Tools that speak the OpenAI or Anthropic API: the official OpenAI and Anthropic SDKs, the Vercel AI SDK, LangChain, Claude Code, Codex CLI, Cursor and more. Change the base URL and the API key, and nothing else.
How does billing work?
You buy prepaid credits and each request is deducted at the per-token price. Turn on auto-recharge if you like. There is no subscription and no monthly minimum.
Which currency do I pay in?
New organizations default to EUR in Europe and USD elsewhere. You can change it until your first payment.
Do I get an invoice?
Yes, for every top-up. Add your company name, tax ID and address in your organization settings to have invoices issued to your company. We do not charge VAT yet.
Ask anything. Build anything.
Start with Odin v1 in minutes. Prepaid, uncensored, and we never store API prompts or completions.