Cheaper Inference / Markets / Live catalog

Every model, priced from the market.

One key reaches the live catalog. Each quote follows the cost of available capacity and is capped at the provider's published list price. Where no list price is published, we quote cost plus margin and make no discount claim.

01 · models: 0
02 · providers: 0
03 · below list on average: 0%

seedance-2.0ByteDance

Input: –
Output: $0.3742/second$0.3181/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

seedance-2.0-fastNewVenice AI

Input: –
Output: $0.0538/second$0.0457/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

seedance-2.0-miniNewByteDance

Input: –
Output: $0.0336/second$0.0286/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputVideo input

seedance-2.5NewByteDance

Input: –
Output: $0.5686/second$0.4833/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

seedream-5.0-liteNewVenice AI

Input: –
Output: $0.035/image$0.0298/image
Discount: 15.00% off
Context: –
TTFT p50: –

ImageImage inputImage editing

seedream-5.0-proNewByteDance

Input: –
Output: $0.035/image$0.0298/image
Discount: 15.00% off
Context: –
TTFT p50: –

ImageImage input

step-3.7-flashNewStepFun

Input: $0.20/M$0.17/M
Output: $1.15/M$0.978/M
Discount: 15.00% off
Context: 256K
TTFT p50: 3.4 s

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

step-5-previewNewStepFun

Input: $1.00/M$0.85/M
Output: $2.70/M$2.30/M
Discount: 15.00% off
Context: 1M
TTFT p50: 6.7 s

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

wan-3.0-videoNewAlibaba

Input: –
Output: $0.20/second$0.17/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

wan-3.0-video-primeNewAlibaba

Input: –
Output: $0.28/second$0.238/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

wizardlm-2-8x22bNewMicrosoft

Input: $0.62/M$0.527/M
Output: $0.62/M$0.527/M
Discount: 15.00% off
Context: 65.5K
TTFT p50: 11 s

TextStructured output

deepseek-v3.2-thinkingNewDeepSeek

Input: $0.28/M$0.26/M
Output: $0.42/M$0.38/M
Discount: 8.57% off
Context: 128K
TTFT p50: 1.7 s

TextTool useImplicit caching

all-minilm-l12-v2NewSentence Transformers

Input: $0.006/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

all-minilm-l6-v2NewSentence Transformers

Input: $0.006/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

all-mpnet-base-v2NewSentence Transformers

Input: $0.006/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

apexNewCallstack

Input: $0.50/M
Output: $3.00/M
Discount: At market
Context: 262.1K
TTFT p50: 3.6 s

TextImage inputReasoningTool useImplicit caching

arrow-2NewQuiverAI

Input: $4.00/M
Output: $20.00/M
Discount: At market
Context: 131.1K
TTFT p50: –

TextImage inputReasoningTool useImplicit caching

arrow-2-telosNewQuiverAI

Input: $6.00/M
Output: $30.00/M
Discount: At market
Context: 131.1K
TTFT p50: –

TextImage inputReasoningTool useImplicit caching

autoglm-phone-9b-multilingualNewZ.ai

Input: $0.04/M
Output: $0.158/M
Discount: –
Context: 65.5K
TTFT p50: 3 s

TextImage input

beamNewReflection AI

Input: $0.015/M
Output: $0.058/M
Discount: –
Context: 1M
TTFT p50: –

TextReasoningTool useStructured outputImplicit caching

Model				Context
seedance-2.0ByteDance	–	$0.3742/second$0.3181/second	15.00% off	–	–
seedance-2.0-fastNewVenice AI	–	$0.0538/second$0.0457/second	15.00% off	–	–
seedance-2.0-miniNewByteDance	–	$0.0336/second$0.0286/second	15.00% off	–	–
seedance-2.5NewByteDance	–	$0.5686/second$0.4833/second	15.00% off	–	–
seedream-5.0-liteNewVenice AI	–	$0.035/image$0.0298/image	15.00% off	–	–
seedream-5.0-proNewByteDance	–	$0.035/image$0.0298/image	15.00% off	–	–
step-3.7-flashNewStepFun	$0.20/M$0.17/M	$1.15/M$0.978/M	15.00% off	256K	3.4 s
step-5-previewNewStepFun	$1.00/M$0.85/M	$2.70/M$2.30/M	15.00% off	1M	6.7 s
wan-3.0-videoNewAlibaba	–	$0.20/second$0.17/second	15.00% off	–	–
wan-3.0-video-primeNewAlibaba	–	$0.28/second$0.238/second	15.00% off	–	–
wizardlm-2-8x22bNewMicrosoft	$0.62/M$0.527/M	$0.62/M$0.527/M	15.00% off	65.5K	11 s
deepseek-v3.2-thinkingNewDeepSeek	$0.28/M$0.26/M	$0.42/M$0.38/M	8.57% off	128K	1.7 s
all-minilm-l12-v2NewSentence Transformers	$0.006/M	–	–	–	–
all-minilm-l6-v2NewSentence Transformers	$0.006/M	–	–	–	–
all-mpnet-base-v2NewSentence Transformers	$0.006/M	–	–	–	–
apexNewCallstack	$0.50/M	$3.00/M	At market	262.1K	3.6 s
arrow-2NewQuiverAI	$4.00/M	$20.00/M	At market	131.1K	–
arrow-2-telosNewQuiverAI	$6.00/M	$30.00/M	At market	131.1K	–
autoglm-phone-9b-multilingualNewZ.ai	$0.04/M	$0.158/M	–	65.5K	3 s
beamNewReflection AI	$0.015/M	$0.058/M	–	1M	–

One key reaches every model above — and hundreds more across the marketplace, priced exactly the same way. Call GET /v1/models to list them all.

Every model, priced from the market.

Product

Developers

Company

Legal