Claude Haiku 4.5

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

How much this model is actually called here.

The same model answering different prompt shapes — measured, not benchmarked.

Kyma measures this model twice. Both are real; they answer different questions.

The gap is prompt length, not the model degrading. Use the probe figure to choose between models, the traffic figure to budget for your own.

Pay per token. Cached input bills at this model’s own cached rate, listed below.

Against the peers people actually weigh it against.

Up and running in under two minutes.

1. 1

   Create an API key

   Sign up and grab a key from the dashboard. Claude Haiku 4.5 needs a top-up — the signup credit covers the free tier.

   Get API key →
2. 2

   Make your first request

   Drop in your key and send a chat completion — fully OpenAI-compatible.

   cURLPythonTypeScript

   Copy

   curl https://kymaapi.com/v1/chat/completions \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "claude-haiku-4-5",
       "messages": [
         {"role": "user", "content": "Explain prompt caching in one paragraph."}
       ]
     }'

3. 3

   Stream responses

   Add "stream": true to receive tokens as they arrive.

   cURL

   Copy

   curl https://kymaapi.com/v1/chat/completions \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "claude-haiku-4-5",
       "stream": true,
       "messages": [{"role": "user", "content": "Hello!"}]
     }'