Skip to main content
We’ve worked to make migration from OpenAI to Telnyx as painless as possible. You will only need to:
  1. Set the OPENAI_BASE_URL and OPENAI_API_KEY environment variables
  2. Use an open-source model supported by Telnyx
Set the environment variables…
  • export OPENAI_BASE_URL='https://api.telnyx.com/v2/ai'
  • export OPENAI_API_KEY='KEY***'
and this code will work!

​
OpenAI example

from openai import OpenAI

client = OpenAI()
chat_completion = client.chat.completions.create(
    # model="gpt-3.5-turbo",
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "Tell me about Telnyx"}
    ],
    temperature=0.0,
    stream=True,
)
If you’d like to use different environment variables, you may also pass these fields in the client constructor 
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("TELNYX_API_KEY"),
    base_url=os.getenv("TELNYX_BASE_URL")
)
chat_completion = client.chat.completions.create(
    # model="gpt-3.5-turbo",
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "Tell me about Telnyx"}
    ],
    temperature=0.0,
    stream=True,
)
Telnyx supports the vast majority of parameters for Chat and Audio (and a few helpful ones that OpenAI does not). See the full compatibility matrix below.

​
Chat Completions

// TODO: Re-add API reference link in navigation once Mintlify supports external links in nested groups.
ParameterDescriptionTelnyxOpenAI
messagesProvides chat context✅✅
modelAdjusts speed + quality✅✅
streamStreams response✅✅
max_tokensLimits output length✅✅
temperatureAdjusts predictability✅✅
top_pAdjusts variety✅✅
frequency_penaltyDecreases repetition✅✅
presence_penaltyDecreases repetition…✅✅
nReturns n responses✅✅
stopForces model to stop✅✅
logit_biasTweaks odds of results✅✅
logprobsReturns odds of outputs✅✅
top_logprobs-> For how many candidates?✅✅
seedReduces randomness✅✅
response_formatEnsures syntax (e.g. JSON)✅✅
tool_choiceHow does model choose?✅✅
toolsHelps model respond✅✅
function-> Outputs JSON for your code✅✅
retrieval-> Uses your docs (e.g. PDFs)✅❌
guided_jsonEnsures output conforms to schema✅❌
guided_regexEnsures output conforms to regex✅❌
guided_choiceEnsures output conforms to choice✅❌
min_ptop_p alternative✅❌
use_beam_searchExplores more options✅❌
best_of-> How many options?✅❌
length_penalty-> Are long options bad?✅❌
early_stopping-> How hard should it try?✅❌
userTracks users❌✅

​
Transcriptions (BETA)

ParameterWhat does this do?TelnyxOpenAI
fileProvides audio data✅✅
modelAdjusts speed + quality✅✅
response_formatAdjusts output format✅✅
timestamp_granularities[]Adds timestamps✅✅
-> segment-> per audio segment✅✅
-> word-> per word❌✅
languageImproves accuracy❌✅
promptGuides style❌✅
temperatureAdjusts “creativity”❌✅