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%

kimi-k2-0905NewMoonshot AI

Input: $0.60/M$0.51/M
Output: $2.50/M$2.13/M
Discount: 15.00% off
Context: 262.1K
TTFT p50: 3.6 s

TextTool useStructured output

kimi-k3.1-proNewMoonshotAI

Input: $2.00/M$1.70/M
Output: $10.00/M$8.50/M
Discount: 15.00% off
Context: 1M
TTFT p50: 9.4 s

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

kling-v2.6NewKuaishou (Kling)

Input: –
Output: $0.07/second$0.0595/second
Discount: 15.00% off
Context: –
TTFT p50: –

VideoImage input

ling-3.0-flash-finNewinclusionAI (Ant Group)

Input: $0.042/M$0.036/M
Output: $0.123/M$0.105/M
Discount: 15.00% off
Context: 262.1K
TTFT p50: 3.4 s

TextReasoningTool useStructured outputImplicit caching

ling-3.0-flash-santeNewinclusionAI (Ant Group)

Input: $0.042/M$0.036/M
Output: $0.123/M$0.105/M
Discount: 15.00% off
Context: 256K
TTFT p50: 3.1 s

TextReasoningTool useImplicit caching

ling-3.0-flash-vlNewinclusionAI (Ant Group)

Input: $0.06/M$0.051/M
Output: $0.18/M$0.153/M
Discount: 15.00% off
Context: 256K
TTFT p50: 4.3 s

TextImage inputVideo inputReasoningTool useStructured output

llama-3.1-8bNewMeta

Input: $0.02/M$0.017/M
Output: $0.04/M$0.034/M
Discount: 15.00% off
Context: 16.4K
TTFT p50: 1.2 s

TextTool useStructured output

llama-4-maverickNewMeta

Input: $0.188/M$0.16/M
Output: $0.60/M$0.51/M
Discount: 15.00% off
Context: 128K
TTFT p50: 1.8 s

TextImage inputTool useStructured output

llama-4-scoutNewMeta

Input: $0.10/M$0.085/M
Output: $0.30/M$0.255/M
Discount: 15.00% off
Context: 128K
TTFT p50: 1.5 s

TextImage inputTool useStructured output

minimax-m2.7-highspeedNewMiniMax

Input: $0.60/M$0.51/M
Output: $2.40/M$2.04/M
Discount: 15.00% off
Context: 204.8K
TTFT p50: 3.4 s

TextReasoningTool useStructured outputImplicit cachingExplicit caching

muse-glimmer-30bNewMeta

Input: $0.35/M$0.298/M
Output: $1.50/M$1.28/M
Discount: 15.00% off
Context: 131.1K
TTFT p50: 2.6 s

TextImage inputReasoningTool useStructured outputImplicit caching

nemotron-nano-12b-v2-vlNewNVIDIA

Input: $0.20/M$0.17/M
Output: $0.20/M$0.17/M
Discount: 15.00% off
Context: 131.1K
TTFT p50: 2 s

TextImage inputReasoningTool use

parakeet-asrNewVenice AI

Input: $0.006/min$0.0051/min
Output: –
Discount: 15.00% off
Context: –
TTFT p50: –

TranscriptionAudio inputStructured output

qwen3-14bNewAlibaba

Input: $0.08/M$0.068/M
Output: $0.20/M$0.17/M
Discount: 15.00% off
Context: 41K
TTFT p50: 1.3 s

TextReasoningTool useStructured output

qwen3-vl-30b-a3b-instructNewAlibaba

Input: $0.15/M$0.128/M
Output: $0.60/M$0.51/M
Discount: 15.00% off
Context: 16.4K
TTFT p50: 1.7 s

TextImage inputVideo inputTool useStructured output

qwen3.5-122b-a10bNewAlibaba

Input: $0.40/M$0.34/M
Output: $3.20/M$2.72/M
Discount: 15.00% off
Context: 262.1K
TTFT p50: 2.6 s

TextImage inputVideo inputReasoningTool useStructured output

qwen3.5-27bNewAlibaba

Input: $0.30/M$0.255/M
Output: $2.40/M$2.04/M
Discount: 15.00% off
Context: 262.1K
TTFT p50: 1.4 s

TextImage inputVideo inputReasoningTool useStructured output

qwen3.5-flashNewAlibaba

Input: $0.10/M$0.085/M
Output: $0.40/M$0.34/M
Discount: 15.00% off
Context: 1M
TTFT p50: 4.3 s

TextImage inputFile inputReasoningTool useStructured outputExplicit caching

seed-1.8NewByteDance

Input: $0.25/M$0.213/M
Output: $2.00/M$1.70/M
Discount: 15.00% off
Context: 256K
TTFT p50: 4.9 s

TextImage inputVideo inputReasoningTool useStructured output

seed-2.0-codeNewByteDance Seed

Input: $0.50/M$0.425/M
Output: $3.00/M$2.55/M
Discount: 15.00% off
Context: 262.1K
TTFT p50: 3.4 s

TextImage inputVideo inputReasoningTool useStructured output

Model				Context
kimi-k2-0905NewMoonshot AI	$0.60/M$0.51/M	$2.50/M$2.13/M	15.00% off	262.1K	3.6 s
kimi-k3.1-proNewMoonshotAI	$2.00/M$1.70/M	$10.00/M$8.50/M	15.00% off	1M	9.4 s
kling-v2.6NewKuaishou (Kling)	–	$0.07/second$0.0595/second	15.00% off	–	–
ling-3.0-flash-finNewinclusionAI (Ant Group)	$0.042/M$0.036/M	$0.123/M$0.105/M	15.00% off	262.1K	3.4 s
ling-3.0-flash-santeNewinclusionAI (Ant Group)	$0.042/M$0.036/M	$0.123/M$0.105/M	15.00% off	256K	3.1 s
ling-3.0-flash-vlNewinclusionAI (Ant Group)	$0.06/M$0.051/M	$0.18/M$0.153/M	15.00% off	256K	4.3 s
llama-3.1-8bNewMeta	$0.02/M$0.017/M	$0.04/M$0.034/M	15.00% off	16.4K	1.2 s
llama-4-maverickNewMeta	$0.188/M$0.16/M	$0.60/M$0.51/M	15.00% off	128K	1.8 s
llama-4-scoutNewMeta	$0.10/M$0.085/M	$0.30/M$0.255/M	15.00% off	128K	1.5 s
minimax-m2.7-highspeedNewMiniMax	$0.60/M$0.51/M	$2.40/M$2.04/M	15.00% off	204.8K	3.4 s
muse-glimmer-30bNewMeta	$0.35/M$0.298/M	$1.50/M$1.28/M	15.00% off	131.1K	2.6 s
nemotron-nano-12b-v2-vlNewNVIDIA	$0.20/M$0.17/M	$0.20/M$0.17/M	15.00% off	131.1K	2 s
parakeet-asrNewVenice AI	$0.006/min$0.0051/min	–	15.00% off	–	–
qwen3-14bNewAlibaba	$0.08/M$0.068/M	$0.20/M$0.17/M	15.00% off	41K	1.3 s
qwen3-vl-30b-a3b-instructNewAlibaba	$0.15/M$0.128/M	$0.60/M$0.51/M	15.00% off	16.4K	1.7 s
qwen3.5-122b-a10bNewAlibaba	$0.40/M$0.34/M	$3.20/M$2.72/M	15.00% off	262.1K	2.6 s
qwen3.5-27bNewAlibaba	$0.30/M$0.255/M	$2.40/M$2.04/M	15.00% off	262.1K	1.4 s
qwen3.5-flashNewAlibaba	$0.10/M$0.085/M	$0.40/M$0.34/M	15.00% off	1M	4.3 s
seed-1.8NewByteDance	$0.25/M$0.213/M	$2.00/M$1.70/M	15.00% off	256K	4.9 s
seed-2.0-codeNewByteDance Seed	$0.50/M$0.425/M	$3.00/M$2.55/M	15.00% off	262.1K	3.4 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