Live price comparison

Every model. Real prices, zero markup.

Compare transparent pay-as-you-go token prices across 11 providers · 117 models, USD per 1M tokens. Live from /api/pricing.

Get your API key LLM cost calculator Compare two models

Sort

Provider

OpenAI

28 models

GPT family · frontier reasoning

gpt-4o-mini-transcribe16K

transcription

Input/1M
Output/1M
Cache/1M: $3.00Audio
$1.25; $5.00; -

gpt-4o-transcribe16K

transcription

Input/1M
Output/1M
Cache/1M: $6.00Audio
$2.50; $10.00; -

gpt-4o-transcribe-diarize16K

transcription

Input/1M
Output/1M
Cache/1M: $6.25Audio
$2.50; $2.50; -

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $1.75; $14.00; $0.875

gpt-5.3-codex400K

chatcodetoolsreasoning

Input/1M
Output/1M
Cache/1M: $1.75; $14.00; $0.875

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $2.50; $15.00; $1.25

gpt-5.4-mini400K

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $0.750; $4.50; $0.375

gpt-5.4-nano400K

chatcodetoolsreasoning

Input/1M
Output/1M
Cache/1M: $0.200; $1.25; $0.100

gpt-5.4-pro922K

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $30.00; $180.00; $15.00

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $5.00; $30.00; $0.500

gpt-5.5-pro1.1M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $30.00; $180.00; -

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $5.00+; $30.00; $0.500

gpt-5.6-luna1.1M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $1.00; $6.00; $0.100

gpt-5.6-sol1.1M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $5.00+; $30.00; $0.500

gpt-5.6-terra1.1M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $2.50+; $15.00; $0.250

gpt-6-astra1.1M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $10.00+; $50.00; $1.00

image

Input/1M
Output/1M
Cache/1M: $5.00; $40.00; -

gpt-image-1-mini

image

Input/1M
Output/1M
Cache/1M: $2.00; $8.00; -

image

Input/1M
Output/1M
Cache/1M: $5.00; $32.00; -

image

Input/1M
Output/1M
Cache/1M: $5.00; $30.00; -

realtimeaudio

Input/1M
Output/1M
Cache/1M: $32.00Audio
$4.00; $16.00; $0.400

gpt-realtime-2.1

realtimeaudio

Input/1M
Output/1M
Cache/1M: $32.00Audio
$4.00; $24.00; $0.400

gpt-realtime-2.1-mini

realtimeaudio

Input/1M
Output/1M
Cache/1M: $10.00Audio
$0.600; $2.40; $0.060

video

Input/1M
Output/1M
Cache/1M: $0.10/s; -; -

video

Input/1M
Output/1M
Cache/1M: $0.30 - $0.50/s; -; -

speech

Input/1M
Output/1M
Cache/1M: $15.00; -; -

speech

Input/1M
Output/1M
Cache/1M: $30.00; -; -

transcription

Input/1M
Output/1M
Cache/1M: $0.006/min; -; -

Anthropic

10 models

Claude · long context, reliable tools

claude-fable-5-11M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $10.00; $50.00; $0.250

claude-haiku-4-5200K

chatcodetools

Input/1M
Output/1M
Cache/1M: $1.00; $5.00; $0.100

claude-opus-4-61M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $5.00; $25.00; $0.500

claude-opus-4-71M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $5.00; $25.00; $0.500

claude-opus-4-81M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $5.00; $25.00; $0.500

claude-opus-51M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $5.00; $25.00; $0.500

claude-sonnet-4200K

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $3.00; $15.00; $0.300

claude-sonnet-4-5200K

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $3.00; $15.00; $0.300

claude-sonnet-4-61M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $3.00; $15.00; $0.300

claude-sonnet-51M

chatcodethinkingtools

Input/1M
Output/1M
Cache/1M: $2.00; $10.00; $0.200

Google

24 models

Gemini · multimodal, large context

transcription

Input/1M
Output/1M
Cache/1M: $0.016/min; -; -

transcription

Input/1M
Output/1M
Cache/1M: $0.016/min; -; -

gemini-2.5-flash1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $1.00Audio
$0.300; $2.50; $0.030

gemini-2.5-flash-image

image

Input/1M
Output/1M
Cache/1M: $0.300; $30.00; -

gemini-2.5-flash-lite1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $0.300Audio
$0.100; $0.400; $0.010

gemini-2.5-flash-native-audio

realtimeaudio

Input/1M
Output/1M
Cache/1M: $3.00Audio
$0.500; $2.00; -

gemini-2.5-pro1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $1.25Audio
$1.25; $10.00; $0.125

gemini-3-flash-preview1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $1.00Audio
$0.500; $3.00; $0.050

gemini-3-pro-image-preview

image

Input/1M
Output/1M
Cache/1M: $2.00; $120.00; -

gemini-3.1-flash-image

image

Input/1M
Output/1M
Cache/1M: $0.500; $60.00; -

gemini-3.1-flash-lite-image

image

Input/1M
Output/1M
Cache/1M: $0.250; $30.00; -

gemini-3.1-flash-lite-preview1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $0.750Audio
$0.250; $1.50; -

gemini-3.1-flash-live

realtimeaudio

Input/1M
Output/1M
Cache/1M: $3.00Audio
$0.750; $4.50; -

gemini-3.1-pro-preview1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $2.00Audio
$2.00; $12.00; $0.200

gemini-3.5-flash1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $5.00Audio
$1.50; $9.00; $0.150

gemini-3.5-flash-lite1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $0.300Audio
$0.300; $2.50; $0.030

gemini-3.6-flash1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $5.00Audio
$1.50; $7.50; $0.150

gemini-3.7-flash1.0M

chatvisioncodetools

Input/1M
Output/1M
Cache/1M: $0.750Audio
$0.750; $3.75; $0.075

google-tts-chirp3-hd4K

speech

Input/1M
Output/1M
Cache/1M: $30.00; -; -

google-tts-neural24K

speech

Input/1M
Output/1M
Cache/1M: $16.00; -; -

google-tts-standard4K

speech

Input/1M
Output/1M
Cache/1M: $4.00; -; -

veo-2.0-generate-001

video

Input/1M
Output/1M
Cache/1M: $0.50/s; -; -

veo-3.1-fast-generate-001

video

Input/1M
Output/1M
Cache/1M: $0.15/s; -; -

veo-3.1-generate-001

video

Input/1M
Output/1M
Cache/1M: $0.40/s; -; -

Alibaba

23 models

Qwen · cost-efficient, open weights

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

fun-asr-realtime

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

paraformer-realtime-v2

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

image

Input/1M
Output/1M
Cache/1M: $0.04/call; -; -

qwen-image-2.0-pro

image

Input/1M
Output/1M
Cache/1M: $0.07/call; -; -

image

Input/1M
Output/1M
Cache/1M: $0.03/call; -; -

qwen3-asr-flash

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

qwen3-asr-flash-realtime

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

qwen3-coder-next262K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.110; $0.800; $0.022

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.20+; $6.00; $0.359

qwen3-tts-instruct-flash4K

speech

Input/1M
Output/1M
Cache/1M: $11.50; -; -

qwen3-vl-flash256K

chatvisionreasoningtools

Input/1M
Output/1M
Cache/1M: $0.050+; $0.400; $0.022

qwen3-vl-plus256K

chatvisionreasoningtools

Input/1M
Output/1M
Cache/1M: $0.200+; $1.60; $0.143

qwen3.5-flash1.0M

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.100; $0.400; $0.029

qwen3.5-plus1.0M

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.400+; $2.40; $0.115

qwen3.6-flash256K

chatcodetools

Input/1M
Output/1M
Cache/1M: $0.250; $1.50; $0.050

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $2.50; $7.50; $0.500

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.400+; $1.60; $0.080

qwen3.8-max984K

chatvisioncodereasoning

Input/1M
Output/1M
Cache/1M: $2.00; $6.00; $0.250

image

Input/1M
Output/1M
Cache/1M: $0.03/call; -; -

wan2.7-image-pro

image

Input/1M
Output/1M
Cache/1M: $0.07/call; -; -

DeepSeek

5 models

DeepSeek · strong reasoning, open weights

deepseek-3.2128K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.280; $0.420; $0.028

deepseek-v4-flash1M

chatcodetools

Input/1M
Output/1M
Cache/1M: $0.138; $0.275; $0.003

deepseek-v4-flash-07311M

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.440; $1.32; $0.044

deepseek-v4-pro1M

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.32; $3.96; $0.132

deepseek-v4-pro-08131M

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.32; $3.96; $0.132

Moonshot

3 models

Kimi · long context

chatvisioncodereasoning

Input/1M
Output/1M
Cache/1M: $0.574; $3.01; $0.115

kimi-k2.7-code256K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.950; $4.00; $0.190

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $3.00; $15.00; $0.300

MiniMax

2 models

MiniMax · multimodal, agentic

minimax-m2.1205K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.300; $1.20; $0.060

minimax-m2.5205K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.220; $0.900; $0.044

Z.ai

6 models

GLM · bilingual, tool use

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.00; $3.20; $0.200

glm-5-turbo205K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.20; $4.00; $0.240

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.40; $4.40; $0.260

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.40; $4.40; $0.260

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $1.40; $4.40; $0.260

glm-5.3-flash1.0M

chatcodereasoningvision

Input/1M
Output/1M
Cache/1M: $0.150; $0.500; $0.030

ByteDance

14 models

Doubao · high-throughput inference

ByteDance-Seed-1.8262K

chattools

Input/1M
Output/1M
Cache/1M: $0.250+; $2.00; $0.050

Dola-Seed-2.0-lite262K

chatcodetools

Input/1M
Output/1M
Cache/1M: $0.250+; $2.00; $0.050

Dola-Seed-2.0-mini262K

chattools

Input/1M
Output/1M
Cache/1M: $0.100+; $0.400; $0.020

Dola-Seed-2.0-pro262K

chatcodereasoningtools

Input/1M
Output/1M
Cache/1M: $0.500+; $3.00; $0.100

dreamina-seedance-2-0-260128

video

Input/1M
Output/1M
Cache/1M: -; $7.00; -

dreamina-seedance-2-0-fast-260128

video

Input/1M
Output/1M
Cache/1M: -; $5.60; -

dreamina-seedance-2-0-mini-260615

video

Input/1M
Output/1M
Cache/1M: -; $3.50; -

seed-asr-bigmodel

transcription

Input/1M
Output/1M
Cache/1M: $0.002/min; -; -

speech

Input/1M
Output/1M
Cache/1M: $30.00; -; -

seedance-1-0-pro-fast-251015

video

Input/1M
Output/1M
Cache/1M: -; $1.00; -

seedance-1-5-pro-251215

video

Input/1M
Output/1M
Cache/1M: -; $2.40; -

seedream-4-0-250828

image

Input/1M
Output/1M
Cache/1M: $0.03/call; -; -

seedream-4-5-251128

image

Input/1M
Output/1M
Cache/1M: $0.04/call; -; -

seedream-5-0-260128

image

Input/1M
Output/1M
Cache/1M: $0.04/call; -; -

Amazon

1 model

Nova · realtime speech

realtimeaudio

Input/1M
Output/1M
Cache/1M: $3.00Audio
$0.060; $0.240; -

Tencent

1 model

Hunyuan · long context, tool use

chatcodetoolsreasoning

Input/1M
Output/1M
Cache/1M: $0.140; $0.580; $0.035

Pricing notes

All prices are in USD. Billing is based on actual token usage.
Input tokens = your prompt. Output tokens = the model’s response.
Tiered pricing: a request’s entire token count is charged at the rate of the tier its input falls into. Larger inputs cross over to a higher tier.
Cache hit: when the same prompt prefix is reused (context caching), input tokens are billed at the discounted Cache/1M rate shown above.
Image and audio generation models are billed per API call.
Volume discounts available for enterprise customers. Contact us.

Found your model? Start calling it in 60 seconds.

Get your API key

Frequently asked questions

How do I compare LLM API prices across providers?

Synthorai's models page is a live price comparison across every major provider - sort by input or output price per million tokens, filter by provider, always in sync with the gateway's actual list prices. Every figure is exactly what a request draws from your balance, with a 0% platform surcharge.

Which LLM API providers does Synthorai support?

Synthorai is a multimodal AI gateway with one API and one bill for GPT (OpenAI), Claude (Anthropic), Gemini (Google), Qwen (Alibaba), DeepSeek, and more - across chat, image, and audio, with native prompt caching, BYOK, and zero data retention by default. The table above lists every model with its live price.

Which LLM API is the cheapest?

The table above is sorted by list price, so you can pick the cheapest model that meets your quality bar. Prompt caching bills cache hits at about 10% of the input price, and there is no platform fee - so effective cost is often lower than an aggregator at the same list price.

How do I compare speech-to-text API pricing?

Audio models bill two different ways - per minute of audio or per token - so sticker prices aren't directly comparable. Our speech-to-text API pricing comparison converts 14 models to the same per-minute unit, from $0.002 to $0.016 a minute.