Loading

Markets · CheaperInference

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%

grok-4.20-multi-agentNewxAI

Input: $1.25/M$0.813/M
Output: $2.50/M$1.63/M
Discount: 35.00% off
Context: 2M
TTFT p50: 5.8 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

Input: $1.25/M$0.813/M
Output: $2.50/M$1.63/M
Discount: 35.00% off
Context: 1M
TTFT p50: 2.9 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

Input: $2.00/M$1.30/M
Output: $6.00/M$3.90/M
Discount: 35.00% off
Context: 500K
TTFT p50: 2.8 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

Input: $2.00/M$1.30/M
Output: $6.00/M$3.90/M
Discount: 35.00% off
Context: 500K
TTFT p50: 8.7 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

Input: $2.00/M$1.30/M
Output: $6.00/M$3.90/M
Discount: 35.00% off
Context: 500K
TTFT p50: 7.3 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

grok-imagine-imageNewxAI

Input: –
Output: $0.02/image$0.013/image
Discount: 35.00% off
Context: –
TTFT p50: –

ImageImage inputStructured outputImage editing

grok-imagine-video-1.5NewxAI

Input: –
Output: $0.25/second$0.1625/second
Discount: 35.00% off
Context: –
TTFT p50: –

VideoImage input

happyhorse-1.0NewAlibaba

Input: –
Output: $0.24/second$0.156/second
Discount: 35.00% off
Context: –
TTFT p50: –

VideoImage inputAudio inputVideo input

hy3NewTencent

Input: $0.14/M$0.091/M
Output: $0.58/M$0.377/M
Discount: 35.00% off
Context: 262.1K
TTFT p50: 4.6 s

TextReasoningTool useStructured outputImplicit caching

inklingNewThinking Machines

Input: $1.00/M$0.65/M
Output: $4.05/M$2.63/M
Discount: 35.00% off
Context: 1M
TTFT p50: 3.2 s

TextImage inputFile inputReasoningTool useStructured outputImplicit caching

jev-1.13.0NewTypeSafe

Input: $0.042/M$0.027/M
Output: –
Discount: 35.00% off
Context: 32K
TTFT p50: –

DecisionImage input

kimi-k2-thinkingMoonshot

Input: $0.47/M$0.306/M
Output: $2.00/M$1.30/M
Discount: 35.00% off
Context: 256K
TTFT p50: 2.2 s

TextReasoningTool useStructured output

kimi-k2.5NewMoonshot

Input: $0.60/M$0.39/M
Output: $3.00/M$1.95/M
Discount: 35.00% off
Context: 256K
TTFT p50: 5.4 s

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

kimi-k2.6Moonshot

Input: $0.95/M$0.618/M
Output: $4.00/M$2.60/M
Discount: 35.00% off
Context: 256K
TTFT p50: 3.4 s

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

kimi-k2.7-codeMoonshot

Input: $0.95/M$0.618/M
Output: $4.00/M$2.60/M
Discount: 35.00% off
Context: 262.1K
TTFT p50: 4.8 s

TextImage inputFile inputVideo inputReasoningTool useStructured outputImplicit caching

llama-3.3-70bMeta

Input: $0.10/M$0.065/M
Output: $0.32/M$0.208/M
Discount: 35.00% off
Context: 128K
TTFT p50: –

TextTool useStructured output

ltx-2-v2.3-fastNewLightricks

Input: –
Output: $0.06/second$0.039/second
Discount: 35.00% off
Context: –
TTFT p50: –

VideoImage input

mai-transcribe-2NewMicrosoft

Input: $0.0017/min$0.0011/min
Output: –
Discount: 35.00% off
Context: –
TTFT p50: –

TranscriptionAudio input

mercury-2NewInception

Input: $0.25/M$0.163/M
Output: $0.75/M$0.488/M
Discount: 35.00% off
Context: 128K
TTFT p50: 1.9 s

TextReasoningTool useStructured output

mercury-2.5NewInception

Input: $0.04/M$0.026/M
Output: $0.15/M$0.098/M
Discount: 35.00% off
Context: 260K
TTFT p50: 1.9 s

TextReasoningTool useStructured outputImplicit caching

Model				Context		Capabilities
grok-4.20-multi-agentNewxAI	$1.25/M$0.813/M	$2.50/M$1.63/M	35.00% off	2M	5.8 s	+1
grok-4.3xAI	$1.25/M$0.813/M	$2.50/M$1.63/M	35.00% off	1M	2.9 s	+1
grok-4.5NewxAI	$2.00/M$1.30/M	$6.00/M$3.90/M	35.00% off	500K	2.8 s	+1
grok-4.6xAI	$2.00/M$1.30/M	$6.00/M$3.90/M	35.00% off	500K	8.7 s	+1
grok-4.7xAI	$2.00/M$1.30/M	$6.00/M$3.90/M	35.00% off	500K	7.3 s	+1
grok-imagine-imageNewxAI	–	$0.02/image$0.013/image	35.00% off	–	–
grok-imagine-video-1.5NewxAI	–	$0.25/second$0.1625/second	35.00% off	–	–
happyhorse-1.0NewAlibaba	–	$0.24/second$0.156/second	35.00% off	–	–
hy3NewTencent	$0.14/M$0.091/M	$0.58/M$0.377/M	35.00% off	262.1K	4.6 s
inklingNewThinking Machines	$1.00/M$0.65/M	$4.05/M$2.63/M	35.00% off	1M	3.2 s
jev-1.13.0NewTypeSafe	$0.042/M$0.027/M	–	35.00% off	32K	–
kimi-k2-thinkingMoonshot	$0.47/M$0.306/M	$2.00/M$1.30/M	35.00% off	256K	2.2 s
kimi-k2.5NewMoonshot	$0.60/M$0.39/M	$3.00/M$1.95/M	35.00% off	256K	5.4 s
kimi-k2.6Moonshot	$0.95/M$0.618/M	$4.00/M$2.60/M	35.00% off	256K	3.4 s
kimi-k2.7-codeMoonshot	$0.95/M$0.618/M	$4.00/M$2.60/M	35.00% off	262.1K	4.8 s	+1
llama-3.3-70bMeta	$0.10/M$0.065/M	$0.32/M$0.208/M	35.00% off	128K	–
ltx-2-v2.3-fastNewLightricks	–	$0.06/second$0.039/second	35.00% off	–	–
mai-transcribe-2NewMicrosoft	$0.0017/min$0.0011/min	–	35.00% off	–	–
mercury-2NewInception	$0.25/M$0.163/M	$0.75/M$0.488/M	35.00% off	128K	1.9 s
mercury-2.5NewInception	$0.04/M$0.026/M	$0.15/M$0.098/M	35.00% off	260K	1.9 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.