Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getpatter.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Cerebras LLM

CerebrasLLM plugs Cerebras’s OpenAI-compatible Inference API at https://api.cerebras.ai/v1 into Patter’s pipeline mode. It is a thin wrapper around OpenAILLMProvider with a Cerebras-specific base URL and optional msgpack + gzip payload compression (both enabled by default) for faster TTFT on large prompts.

​
Why Cerebras for voice

Cerebras runs inference on the WSE-3 wafer-scale chip, which serves the default model gpt-oss-120b at ~3000 tok/sec. Patter’s downstream TTS consumption rate is ~150-300 tok/sec, so any model on Cerebras saturates the pipeline regardless of weight size — meaning you can ship a 120B model with no realtime latency penalty over an 8B model. Picking the larger one buys higher answer quality for free.

​
Install

pip install "getpatter[cerebras]"

npm install getpatter

​
Usage

# Namespaced import
from getpatter.llm import cerebras

llm = cerebras.LLM()                                        # reads CEREBRAS_API_KEY
llm = cerebras.LLM(api_key="csk-...", model="gpt-oss-120b")
llm = cerebras.LLM(
    model="gpt-oss-120b",
    gzip_compression=True,                                  # defaults to True
    msgpack_encoding=True,                                  # defaults to True
    response_format={"type": "json_object"},                # OpenAI-style structured outputs
)

# Flat alias (equivalent)
from getpatter import CerebrasLLM

llm = CerebrasLLM()
The namespaced import (from getpatter.llm import cerebras / import * as cerebras from "getpatter/llm/cerebras") auto-resolves the API key from CEREBRAS_API_KEY and exposes a uniform LLM class — the same pattern Patter uses for STT and TTS namespaces.
Plug it into an agent: 
import asyncio
from getpatter import Patter, Twilio, DeepgramSTT, CerebrasLLM, ElevenLabsTTS

phone = Patter(carrier=Twilio(), phone_number="+15550001234")

agent = phone.agent(
    stt=DeepgramSTT(),
    llm=CerebrasLLM(),                                      # CEREBRAS_API_KEY from env
    tts=ElevenLabsTTS(voice_id="rachel"),
    system_prompt="You are a helpful assistant.",
    first_message="Hi, how can I help?",
)

asyncio.run(phone.serve(agent))

​
Supported models

Pricing in USD per 1M tokens. Availability is gated per-tier — when a 404 model_not_found lands, the provider logs a recovery hint with override candidates and lets the call continue (voice pipelines treat LLM failures as recoverable).
ModelTierInputOutputNotes
gpt-oss-120b (default)productionn/an/aHighest throughput on WSE-3 (~3000 tok/sec). No deprecation date.
llama3.1-8bproductionn/an/aSmaller-context alternative. Deprecating 2026-05-27.
llama-3.3-70bpaid$0.85$1.20Listed in LLM_PRICING.
qwen-3-32bpaid$0.40$0.80Listed in LLM_PRICING.
qwen-3-235b-a22b-instruct-2507previewn/an/aMultilingual, strong on European languages.
zai-glm-4.7previewn/an/aPreview model, opt-in.
gpt-oss-120b and llama3.1-8b are billed under Cerebras’s tier plans rather than per-token rate cards, so they are not present in LLM_PRICING — pass pricing={...} overrides if your dashboard needs cost figures for them.
llama3.1-8b is deprecating 2026-05-27. Switch to gpt-oss-120b (the default), llama-3.3-70b (paid tier), or qwen-3-235b-a22b-instruct-2507 (preview) before that date.

​
Environment variables

VariableRequiredNotes
CEREBRAS_API_KEYyesAuto-loaded when api_key / apiKey is omitted.

​
Options

OptionDefaultNotes
api_key / apiKeyNoneReads from CEREBRAS_API_KEY when omitted.
model"gpt-oss-120b"Any Cerebras chat model id. Use GET /v1/models to discover tier-available IDs.
base_url / baseUrlhttps://api.cerebras.ai/v1Override the Cerebras endpoint (rarely needed).
gzip_compression / gzipCompressionTrueGzip request payloads for faster TTFT on large prompts.
msgpack_encodingTrueEncode request payloads with msgpack for smaller wire size (Python only — TS uses gzip alone).
temperature, max_tokens, top_p, seed, frequency_penalty, presence_penalty, stop, response_format, parallel_tool_calls, tool_choiceunsetAll forwarded to chat.completions.create. See Cerebras docs for accepted values.

​
Payload compression

Cerebras supports msgpack + gzip request bodies — see Cerebras payload optimization. Patter enables both by default for Python (msgpack + gzip) and gzip for TypeScript, which reduces wire size on large prompts and shaves time-to-first-token. Disable per-request by passing gzip_compression=False / msgpack_encoding=False.

​
Error handling

When chat.completions.create returns a 404 model_not_found, the provider logs an ERROR-level recovery hint including the upstream message and lists override candidates (llama3.1-8b, qwen-3-235b-a22b-instruct-2507, llama-3.3-70b on paid tier) — then returns silently. Voice pipelines treat LLM failures as recoverable so the call continues and the user simply hears no LLM response for that turn. All other errors raise PatterError after one retry with exponential backoff and honour x-ratelimit-reset-* advisory headers.