Palmyra X5 API Pricing

Palmyra X5 pricing by provider

2 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Palmyra X5 costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

Palmyra X5 features

• Function calling
• PDF input

Use Palmyra X5 with LiteLLM

Call Palmyra X5 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="writer.palmyra-x5-v1:0",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: palmyra-x5
    litellm_params:
      model: writer.palmyra-x5-v1:0
      aws_region_name: os.environ/AWS_REGION_NAME

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "palmyra-x5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Palmyra X5 FAQ