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%

mistral-large-4NewMistral AI

Input: $0.68/M
Output: $2.09/M
Discount: At market
Context: 524.3K
TTFT p50: 1.2 s

TextImage inputReasoningTool useStructured output

mistral-medium-3.5NewMistral AI

Input: $1.50/M
Output: $7.50/M
Discount: At market
Context: 262.1K
TTFT p50: 1.2 s

TextImage inputReasoningTool useStructured output

mistral-smallNewMistral AI

Input: $0.15/M
Output: $0.60/M
Discount: At market
Context: 262.1K
TTFT p50: 1.4 s

TextImage inputTool useStructured output

moondream3NewMoondream

Input: $0.172/M
Output: $1.43/M
Discount: –
Context: 32K
TTFT p50: –

TextImage inputReasoning

morph-v3-fastNewMorph

Input: $0.80/M
Output: $1.20/M
Discount: At market
Context: 81.9K
TTFT p50: 1.8 s

TextStructured output

morph-v3-largeNewMorph

Input: $0.90/M
Output: $1.90/M
Discount: At market
Context: 81.9K
TTFT p50: 1.8 s

TextStructured output

multi-qa-mpnet-base-dot-v1NewSentence Transformers

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

Retrieval

multilingual-e5-largeNewMicrosoft

Input: $0.011/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

multilingual-e5-large-instructNewMicrosoft

Input: $0.011/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

muse-image-1.0NewMeta

Input: –
Output: $0.01/image
Discount: At market
Context: –
TTFT p50: –

ImageImage input

muse-wonder-1.0NewMeta

Input: $4.00/M
Output: $20.00/M
Discount: At market
Context: 1M
TTFT p50: 2.1 s

TextImage inputFile inputReasoningTool useStructured outputImplicit caching

namazuNewSakana AI

Input: $0.95/M
Output: $4.00/M
Discount: At market
Context: 256K
TTFT p50: 2.7 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

nemotron-3-diarizationNewNVIDIA

Input: $0.0007/min
Output: –
Discount: –
Context: –
TTFT p50: –

Transcription

nemotron-3-embed-8bNewNVIDIA

Input: $0.04/M
Output: –
Discount: –
Context: –
TTFT p50: –

Retrieval

nemotron-3.5-asr-streaming-multilingual-0.6bNewNVIDIA

Input: $0.0002/min
Output: –
Discount: –
Context: –
TTFT p50: –

Transcription

nova-2-liteNewAmazon

Input: $0.30/M
Output: $2.50/M
Discount: At market
Context: 1M
TTFT p50: 1 s

TextImage inputFile inputVideo inputReasoningTool useStructured outputExplicit caching

nova-liteNewAmazon

Input: $0.06/M
Output: $0.24/M
Discount: At market
Context: 300K
TTFT p50: 1.3 s

TextImage inputFile inputVideo inputTool useStructured outputExplicit caching

nova-microNewAmazon

Input: $0.035/M
Output: $0.14/M
Discount: At market
Context: 128K
TTFT p50: 1.2 s

TextTool useStructured outputExplicit caching

nova-proNewAmazon

Input: $0.80/M
Output: $3.20/M
Discount: At market
Context: 300K
TTFT p50: 1 s

TextImage inputFile inputVideo inputTool useStructured outputExplicit caching

o1NewOpenAI

Input: $15.00/M
Output: $60.00/M
Discount: At market
Context: 200K
TTFT p50: 2.2 s

TextImage inputFile inputReasoningTool useStructured outputImplicit caching

Model				Context		Capabilities
mistral-large-4NewMistral AI	$0.68/M	$2.09/M	At market	524.3K	1.2 s
mistral-medium-3.5NewMistral AI	$1.50/M	$7.50/M	At market	262.1K	1.2 s
mistral-smallNewMistral AI	$0.15/M	$0.60/M	At market	262.1K	1.4 s
moondream3NewMoondream	$0.172/M	$1.43/M	–	32K	–
morph-v3-fastNewMorph	$0.80/M	$1.20/M	At market	81.9K	1.8 s
morph-v3-largeNewMorph	$0.90/M	$1.90/M	At market	81.9K	1.8 s
multi-qa-mpnet-base-dot-v1NewSentence Transformers	$0.006/M	–	–	–	–
multilingual-e5-largeNewMicrosoft	$0.011/M	–	–	–	–
multilingual-e5-large-instructNewMicrosoft	$0.011/M	–	–	–	–
muse-image-1.0NewMeta	–	$0.01/image	At market	–	–
muse-wonder-1.0NewMeta	$4.00/M	$20.00/M	At market	1M	2.1 s
namazuNewSakana AI	$0.95/M	$4.00/M	At market	256K	2.7 s	+1
nemotron-3-diarizationNewNVIDIA	$0.0007/min	–	–	–	–
nemotron-3-embed-8bNewNVIDIA	$0.04/M	–	–	–	–
nemotron-3.5-asr-streaming-multilingual-0.6bNewNVIDIA	$0.0002/min	–	–	–	–
nova-2-liteNewAmazon	$0.30/M	$2.50/M	At market	1M	1 s	+1
nova-liteNewAmazon	$0.06/M	$0.24/M	At market	300K	1.3 s
nova-microNewAmazon	$0.035/M	$0.14/M	At market	128K	1.2 s
nova-proNewAmazon	$0.80/M	$3.20/M	At market	300K	1 s
o1NewOpenAI	$15.00/M	$60.00/M	At market	200K	2.2 s

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