Inference Pricing

Incorporate AI into your applications with an OpenAI compatible API at a fraction of the price.

Custom pricing

Get set up on a contract and get volume discounts the more you use.

Pay as you go

Pricing is based on which services you use, and how much you use them.

Pay as you go

Service pricing
ServicePrice% Cheaper
Chat Completions per tokenPrice$0.0002 / 1K tokens for 7B parameter models

$0.0003 / 1K tokens for 13B, 34B, 8x7B parameter models

$0.0006 / 1K tokens for 70B+ parameter models
% CheaperUp to 90% cheaper vs. OpenAI GPT-3.5 Turbo
Embeddings per tokenPriceSmall: $0.00005 / 1K tokens
Large: $0.0001 / 1K tokens
% CheaperUp to 50% cheaper vs. OpenAI Ada
Speech to text per minute (BETA)Price$0.003 / minute% CheaperUp to 50% cheaper vs. OpenAI Whisper
AI-enabled storage and retrievalPrice$0.02 / GB / day% CheaperAt least 90% cheaper vs. OpenAI Assistant Retrieval
Sign up

Start building with our intuitive APIs.

Volume-based pricing

Telnyx offers you discounts in exchange for monthly commitments as you scale

  • Checkmark


    Get set up on a contract with predictable monthly payments.

  • Checkmark

    Discounted rate

    Receive a discounted rate with the more you spend instead of our pay-as-you-go rates.

  • Checkmark

    24/7 support

    Free 24/7 support as well as a customer success manager dedicated to helping you.