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%

glm-4.7-flashZ.ai

Input: $0.07/M$0.047/M
Output: $0.40/M$0.268/M
Discount: 33.00% off
Context: 198K
TTFT p50: 3.2 s

TextReasoningTool useStructured outputImplicit caching

venice-qwen-image-2NewVenice AI

Input: –
Output: $0.035/image$0.0235/image
Discount: 32.86% off
Context: –
TTFT p50: –

ImageStructured output

grok-imagine-imageNewxAI

Input: –
Output: $0.02/image$0.0136/image
Discount: 32.09% off
Context: –
TTFT p50: –

ImageImage inputStructured outputImage editing

magistral-small-2509NewMistral AI

Input: $0.50/M$0.343/M
Output: $1.50/M$1.03/M
Discount: 31.43% off
Context: 128K
TTFT p50: 2 s

TextImage inputTool useStructured output

minimax-m2.1MiniMax

Input: $0.30/M$0.206/M
Output: $1.20/M$0.823/M
Discount: 31.42% off
Context: 198K
TTFT p50: 2.2 s

TextReasoningTool useStructured outputImplicit cachingExplicit caching

qwen3.8-omni-flashNewAlibaba

Input: $0.15/M$0.103/M
Output: $0.47/M$0.322/M
Discount: 31.39% off
Context: 1M
TTFT p50: 2.8 s

TextImage inputAudio inputVideo inputReasoningTool useStructured outputImplicit caching

glimpseNewElorian

Input: $0.60/M$0.412/M
Output: $3.00/M$2.06/M
Discount: 31.28% off
Context: 262.1K
TTFT p50: –

TextImage inputVideo inputReasoningTool useStructured outputImplicit caching

qwen3.8-max-0902NewAlibaba

Input: $2.00/M$1.38/M
Output: $6.00/M$4.13/M
Discount: 31.21% off
Context: 1M
TTFT p50: 3 s

TextImage inputFile inputVideo inputReasoningTool useStructured outputImplicit cachingExplicit caching

deepseek-v4-flash-0731-fastNewDeepSeek

Input: $0.35/M$0.241/M
Output: $0.70/M$0.482/M
Discount: 31.10% off
Context: 1M
TTFT p50: 4.6 s

TextReasoningTool useStructured outputWeb search

command-a-plusNewCohere

Input: $0.30/M$0.207/M
Output: $1.50/M$1.04/M
Discount: 31.00% off
Context: 192K
TTFT p50: 2 s

TextImage inputReasoningTool useStructured output

lfm2.5-24b-a2bNewLiquid AI

Input: $0.05/M$0.035/M
Output: $0.70/M$0.483/M
Discount: 31.00% off
Context: 128K
TTFT p50: 1.8 s

TextReasoningTool useStructured outputImplicit caching

llama-3.2-3b-instructNewMeta

Input: $0.05/M$0.035/M
Output: $0.33/M$0.228/M
Discount: 31.00% off
Context: 128K
TTFT p50: 4.3 s

TextTool use

moondream3.1-9b-a2bNewMoondream

Input: $0.30/M$0.207/M
Output: $2.50/M$1.73/M
Discount: 31.00% off
Context: 32K
TTFT p50: –

TextImage inputReasoning

text-embedding-3-largeNewOpenAI

Input: $0.13/M$0.09/M
Output: –
Discount: 31.00% off
Context: 8.2K
TTFT p50: –

Retrieval

deepseek-v4.1-flashNewDeepSeek

Input: $0.15/M$0.105/M
Output: $0.60/M$0.418/M
Discount: 30.33% off
Context: 1M
TTFT p50: 4.1 s

TextImage inputFile inputReasoningTool useStructured outputImplicit caching

aion-3.0NewAion Labs

Input: $3.00/M$2.10/M
Output: $6.00/M$4.19/M
Discount: 30.11% off
Context: 128K
TTFT p50: 5.3 s

TextReasoningTool useStructured outputWeb search

qwen3.5-plusNewAlibaba

Input: $0.40/M$0.281/M
Output: $2.40/M$1.69/M
Discount: 29.76% off
Context: 1M
TTFT p50: 3.9 s

TextImage inputFile inputReasoningTool useStructured outputExplicit caching

gpt-5.6-solOpenAI

Input: $4.00/M$2.83/M
Output: $20.00/M$14.14/M
Discount: 29.29% off
Context: 1.1M
TTFT p50: 5.3 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit cachingExplicit caching

kimi-k3-fastNewMoonshot

Input: $4.50/M$3.20/M
Output: $22.50/M$15.98/M
Discount: 28.96% off
Context: 1M
TTFT p50: 4.4 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchImplicit caching

gemini-4-argonNewGoogle

Input: $2.00/M$1.43/M
Output: $10.00/M$7.14/M
Discount: 28.61% off
Context: 1M
TTFT p50: 8.9 s

TextImage inputFile inputAudio inputVideo inputReasoningTool useStructured outputWeb searchImplicit caching

Model				Context		Capabilities
glm-4.7-flashZ.ai	$0.07/M$0.047/M	$0.40/M$0.268/M	33.00% off	198K	3.2 s
venice-qwen-image-2NewVenice AI	–	$0.035/image$0.0235/image	32.86% off	–	–
grok-imagine-imageNewxAI	–	$0.02/image$0.0136/image	32.09% off	–	–
magistral-small-2509NewMistral AI	$0.50/M$0.343/M	$1.50/M$1.03/M	31.43% off	128K	2 s
minimax-m2.1MiniMax	$0.30/M$0.206/M	$1.20/M$0.823/M	31.42% off	198K	2.2 s
qwen3.8-omni-flashNewAlibaba	$0.15/M$0.103/M	$0.47/M$0.322/M	31.39% off	1M	2.8 s	+1
glimpseNewElorian	$0.60/M$0.412/M	$3.00/M$2.06/M	31.28% off	262.1K	–
qwen3.8-max-0902NewAlibaba	$2.00/M$1.38/M	$6.00/M$4.13/M	31.21% off	1M	3 s	+2
deepseek-v4-flash-0731-fastNewDeepSeek	$0.35/M$0.241/M	$0.70/M$0.482/M	31.10% off	1M	4.6 s
command-a-plusNewCohere	$0.30/M$0.207/M	$1.50/M$1.04/M	31.00% off	192K	2 s
lfm2.5-24b-a2bNewLiquid AI	$0.05/M$0.035/M	$0.70/M$0.483/M	31.00% off	128K	1.8 s
llama-3.2-3b-instructNewMeta	$0.05/M$0.035/M	$0.33/M$0.228/M	31.00% off	128K	4.3 s
moondream3.1-9b-a2bNewMoondream	$0.30/M$0.207/M	$2.50/M$1.73/M	31.00% off	32K	–
text-embedding-3-largeNewOpenAI	$0.13/M$0.09/M	–	31.00% off	8.2K	–
deepseek-v4.1-flashNewDeepSeek	$0.15/M$0.105/M	$0.60/M$0.418/M	30.33% off	1M	4.1 s
aion-3.0NewAion Labs	$3.00/M$2.10/M	$6.00/M$4.19/M	30.11% off	128K	5.3 s
qwen3.5-plusNewAlibaba	$0.40/M$0.281/M	$2.40/M$1.69/M	29.76% off	1M	3.9 s
gpt-5.6-solOpenAI	$4.00/M$2.83/M	$20.00/M$14.14/M	29.29% off	1.1M	5.3 s	+2
kimi-k3-fastNewMoonshot	$4.50/M$3.20/M	$22.50/M$15.98/M	28.96% off	1M	4.4 s	+1
gemini-4-argonNewGoogle	$2.00/M$1.43/M	$10.00/M$7.14/M	28.61% off	1M	8.9 s	+3

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