Unified LLM Pricing — Live Dashboard

Providers

Models

4,454

Models on 2+ providers

180

Cheapest input /1M

$0.0001

fireworks_ai/accounts/fireworks/models/SSD-1B · litellm

Average standard input price per provider

groq

$0.4367

doubleword

$0.8113

baseten

$1.7947

wafer

$2.5658

google

$5.9583

anthropic

$10.9457

openai

$14.5108

openrouter

$184.9243

litellm

$329.412

Cheapest model per provider

Provider	Model	Input $/1M
openai	Embedding	$0.02
anthropic	Claude Haiku 3.5 (retired, except on Bedrock and Google Cloud)	$0.80
google	Gemini 2.0 Flash-Lite	$0.075
groq	Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m	$0.03
doubleword	GPT OSS 20B	$0.02
openrouter	Perplexity: Embed V1 0.6B	$0.004
litellm	fireworks_ai/accounts/fireworks/models/SSD-1B	$0.0001
baseten	GPT OSS 120B	$0.10
wafer	DeepSeek-V4-Flash-0731-Fast	$0.28

Modality coverage

text · 3,620audio · 206embedding · 173image · 124rerank · 32video · 24

Data source

Source: Live — GitHub raw

Snapshot generated Aug 19, 2026, 12:56:30 AM UTC

Fetched Aug 19, 2026, 12:59:45 AM UTC