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%

bge-m3NewBAAI

Input: $0.011/M
Output: $0.011/M
Discount: –
Context: 8.2K
TTFT p50: –

Retrieval

bge-m3-multiNewBAAI

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

Retrieval

bge-m3-multi-8kNewBAAI

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

Retrieval

claude-haiku-4.5-20251001-rNewAnthropic

Input: $1.14/M
Output: $5.72/M
Discount: –
Context: 200K
TTFT p50: –

TextImage inputReasoningTool useStructured output

claude-opus-5.5-fastNewAnthropic

Input: $8.00/M
Output: $40.00/M
Discount: At market
Context: 1M
TTFT p50: 3.7 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

clip-vit-b-32NewSentence Transformers

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

Retrieval

clip-vit-b-32-multilingual-v1NewSentence Transformers

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

Retrieval

codestralNewMistral AI

Input: $0.30/M
Output: $0.90/M
Discount: At market
Context: 128K
TTFT p50: 3.9 s

TextTool useStructured output

codestral-embedNewMistral AI

Input: $0.15/M
Output: –
Discount: At market
Context: –
TTFT p50: –

Retrieval

command-aNewCohere

Input: $2.50/M
Output: $10.00/M
Discount: At market
Context: 256K
TTFT p50: 2 s

TextTool useStructured output

cosmos-predictNewNVIDIA

Input: –
Output: –
Discount: –
Context: –
TTFT p50: –

VideoImage inputVideo input

d1NewLiquid AI

Input: $0.02/M
Output: –
Discount: At market
Context: 65.5K
TTFT p50: –

DecisionImage input

d1-ultraNewLiquid AI

Input: $0.042/M
Output: –
Discount: At market
Context: 32.8K
TTFT p50: –

DecisionImage input

deepseek-ocr-2NewDeepSeek

Input: $0.034/M
Output: $0.034/M
Discount: –
Context: 8.2K
TTFT p50: 1.6 s

TextImage input

deepseek-r1-communityNewDeepSeek

Input: $4.58/M
Output: $4.58/M
Discount: –
Context: 64K
TTFT p50: 4.1 s

TextReasoningTool use

deepseek-r1-turboNewDeepSeek

Input: $0.801/M
Output: $2.86/M
Discount: –
Context: 64K
TTFT p50: 3.2 s

TextReasoningTool useStructured output

deepseek-v4.1-flash-1017-fastNewDeepSeek

Input: $0.686/M
Output: $2.75/M
Discount: –
Context: 1M
TTFT p50: 3.1 s

TextImage inputReasoningTool useStructured outputImplicit caching

deepseek-v4.1-flash-fastNewDeepSeek

Input: $0.60/M
Output: $2.40/M
Discount: At market
Context: 1M
TTFT p50: 1.9 s

TextImage inputReasoningTool useStructured outputImplicit caching

drama-3NewFish Audio

Input: $10.00/M chars
Output: –
Discount: At market
Context: –
TTFT p50: –

Audio

e2ee-qwen3.6-35b-a3b-uncensored-pNewAlibaba

Input: $0.242/M
Output: $0.726/M
Discount: –
Context: 128K
TTFT p50: 11.5 s

TextTool useStructured output

Model				Context		Capabilities
bge-m3NewBAAI	$0.011/M	$0.011/M	–	8.2K	–
bge-m3-multiNewBAAI	$0.011/M	–	–	–	–
bge-m3-multi-8kNewBAAI	$0.011/M	–	–	–	–
claude-haiku-4.5-20251001-rNewAnthropic	$1.14/M	$5.72/M	–	200K	–
claude-opus-5.5-fastNewAnthropic	$8.00/M	$40.00/M	At market	1M	3.7 s	+1
clip-vit-b-32NewSentence Transformers	$0.006/M	–	–	–	–
clip-vit-b-32-multilingual-v1NewSentence Transformers	$0.006/M	–	–	–	–
codestralNewMistral AI	$0.30/M	$0.90/M	At market	128K	3.9 s
codestral-embedNewMistral AI	$0.15/M	–	At market	–	–
command-aNewCohere	$2.50/M	$10.00/M	At market	256K	2 s
cosmos-predictNewNVIDIA	–	–	–	–	–
d1NewLiquid AI	$0.02/M	–	At market	65.5K	–
d1-ultraNewLiquid AI	$0.042/M	–	At market	32.8K	–
deepseek-ocr-2NewDeepSeek	$0.034/M	$0.034/M	–	8.2K	1.6 s
deepseek-r1-communityNewDeepSeek	$4.58/M	$4.58/M	–	64K	4.1 s
deepseek-r1-turboNewDeepSeek	$0.801/M	$2.86/M	–	64K	3.2 s
deepseek-v4.1-flash-1017-fastNewDeepSeek	$0.686/M	$2.75/M	–	1M	3.1 s
deepseek-v4.1-flash-fastNewDeepSeek	$0.60/M	$2.40/M	At market	1M	1.9 s
drama-3NewFish Audio	$10.00/M chars	–	At market	–	–
e2ee-qwen3.6-35b-a3b-uncensored-pNewAlibaba	$0.242/M	$0.726/M	–	128K	11.5 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