All models

Needle

Cactus Computecactus-compute/needle

A small tool-calling model from Cactus Compute; its contract requires at least one tool in every request.

No providers online right now
Modality
Chat
Input
$0.002
per M tokens
Output
$0.008
per M tokens
Listed
Aug 31, 2026
Uptime
0%
last 3 days, measured

Playground

Run this model right here. Billed to your account credits per use through the same signed-receipt pipeline as the API.

Checking your session…

Pricing

Charged per use against a signed receipt. Current price version v1; versions are immutable, so the chart below is the platform's actual pricing record.

Input
$0.002
per M tokens
Output
$0.008
per M tokens
$0.0068$0.008$0.0092Aug 31Today

Performance

Measured from real, settled requests over the last 30 days. No synthetic benchmarks.

Not enough traffic yet to report honestly. Numbers appear as real requests accumulate.

Availability

Provider availability polled every minute by the platform itself, replayed hour by hour.

0%online over the last 3 days

Tracking since Aug 31, 1 AM

3 days ago online down no dataNow

Use it

OpenAI-compatible: point an existing SDK at api.openmayhem.ai and use this model ID.

curl https://api.openmayhem.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cactus-compute/needle",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 2000
  }'

FAQ

What does Needle cost on OpenMayhem?

Needle currently costs $0.002 / M input · $0.008 / M output. There is no subscription: you buy credit and every request settles against a signed receipt for exactly what it used. Prices are versioned, and the full price history is published on this page.

Is Needle available right now?

No providers are online for Needle at this moment. Availability is polled every minute, and requests are rejected upfront rather than queued indefinitely.

How do I use Needle?

Send an OpenAI-compatible request to https://api.openmayhem.ai/v1/chat/completions with "model": "cactus-compute/needle" and your API key. Existing OpenAI SDKs work by changing the base URL. Create an account to get a key and starting credit.

Are my prompts stored?

OpenMayhem does not persist prompt or completion text. Requests are proxied to the serving provider and only billing metadata is retained: usage counts, the price applied, and the provider's signed receipt. The provider that serves a request necessarily processes its content.

More like this