AllocateOx Alpha
APIOx Alpha is a language model from Stealth with a 1M-token context window. Provider list price is $0 per million input tokens and $0 per million output; on Allocate you pay $0 and $0. It is a closed model served over API; the weights are not published.
Pricing
Prices checked 2026-07-21.
Price against its peers
Provider list prices per M tokens, Ox Alpha against its nearest language peers by price.
What a real workload costs
Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0 + 350 × $0 = $0 a month. Billed on Allocate it is $0.
Ox Alpha is served over API. Route traffic to it by name, meter every token, and swap it out in one click when a better fit ships.
Example usage
Point a route at stealth/ox-alpha and the endpoint never changes; swap the model behind it whenever you want.
curl https://api.allocate.network/v1/chat/completions \ -H "Authorization: Bearer $ALLOCATE_KEY" \ -d '{ "model": "stealth/ox-alpha", "messages": [{"role": "user", "content": "Summarise the attached contract."}] }'
Common questions
How much does Ox Alpha cost per million tokens?
Provider list price is $0 per million input tokens and $0 per million output tokens. On Allocate you pay $0 in and $0 out.
What context window does Ox Alpha have?
1,048,576 tokens (1M). At roughly 0.75 words per token, that is about 786k words of English text per request.
Can I fine-tune Ox Alpha?
No. Ox Alpha is a closed model served over API; the weights are not published. If you want a model you can train and own, start from an open-weights base in the catalog and fine-tune that.
How do I call Ox Alpha on Allocate?
Send stealth/ox-alpha in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.