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%

claude-haiku-4.5Anthropic

Input: $1.00/M$0.65/M
Output: $5.00/M$3.25/M
Discount: 35.00% off
Context: 200K
TTFT p50: 2.9 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-haiku-5.5NewAnthropic

Input: $0.10/M$0.065/M
Output: $0.50/M$0.325/M
Discount: 35.00% off
Context: 100K
TTFT p50: 5.7 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-opus-4.5Anthropic

Input: $5.00/M$3.25/M
Output: $25.00/M$16.25/M
Discount: 35.00% off
Context: 198K
TTFT p50: 3.9 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-opus-4.6Anthropic

Input: $5.00/M$3.25/M
Output: $25.00/M$16.25/M
Discount: 35.00% off
Context: 1M
TTFT p50: 4.5 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-opus-4.8-fastNewAnthropic

Input: $10.00/M$6.50/M
Output: $50.00/M$32.50/M
Discount: 35.00% off
Context: 1M
TTFT p50: 2.5 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-opus-5.5NewAnthropic

Input: $4.00/M$2.60/M
Output: $20.00/M$13.00/M
Discount: 35.00% off
Context: 1M
TTFT p50: 6.5 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-sonnet-4.5Anthropic

Input: $3.00/M$1.95/M
Output: $15.00/M$9.75/M
Discount: 35.00% off
Context: 198K
TTFT p50: 24.3 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

claude-sonnet-4.6Anthropic

Input: $3.00/M$1.95/M
Output: $15.00/M$9.75/M
Discount: 35.00% off
Context: 1M
TTFT p50: 3.2 s

TextImage inputFile inputReasoningTool useStructured outputWeb searchExplicit caching

codestral-embedNewMistral AI

Input: $0.15/M$0.098/M
Output: –
Discount: 35.00% off
Context: –
TTFT p50: –

Retrieval

deepseek-r1DeepSeek

Input: $1.35/M$0.878/M
Output: $5.40/M$3.51/M
Discount: 35.00% off
Context: 160K
TTFT p50: 3.1 s

TextReasoningTool useImplicit caching

deepseek-v3.1NewDeepSeek

Input: $0.25/M$0.163/M
Output: $0.95/M$0.618/M
Discount: 35.00% off
Context: 128K
TTFT p50: 2.5 s

TextReasoningTool useStructured outputImplicit caching

deepseek-v3.2DeepSeek

Input: $0.62/M$0.403/M
Output: $1.85/M$1.20/M
Discount: 35.00% off
Context: 160K
TTFT p50: 3.6 s

TextReasoningTool useStructured outputImplicit caching

deepseek-v4-flash-vision-expNewDeepSeek

Input: $0.30/M$0.195/M
Output: $1.20/M$0.78/M
Discount: 35.00% off
Context: 1M
TTFT p50: 4.1 s

TextImage inputReasoningTool useStructured outputImplicit caching

devstral-2-123bNewMistral AI

Input: $0.40/M$0.26/M
Output: $2.00/M$1.30/M
Discount: 35.00% off
Context: 256K
TTFT p50: 3 s

TextTool useStructured output

e2ee-gemma-4-26b-a4b-uncensored-pNewGoogle

Input: $0.35/M$0.228/M
Output: $1.10/M$0.715/M
Discount: 35.00% off
Context: 262.1K
TTFT p50: –

TextTool useStructured output

e2ee-glm-5.1NewZ.ai

Input: $1.10/M$0.715/M
Output: $4.15/M$2.70/M
Discount: 35.00% off
Context: 200K
TTFT p50: –

TextReasoningTool useStructured output

e2ee-gpt-oss-120b-pNewOpenAI

Input: $0.13/M$0.085/M
Output: $0.65/M$0.423/M
Discount: 35.00% off
Context: 128K
TTFT p50: –

TextReasoning

e2ee-gpt-oss-20b-pNewOpenAI

Input: $0.05/M$0.033/M
Output: $0.19/M$0.124/M
Discount: 35.00% off
Context: 128K
TTFT p50: –

TextReasoning

e2ee-qwen-2.5-7b-pNewAlibaba

Input: $0.05/M$0.033/M
Output: $0.13/M$0.085/M
Discount: 35.00% off
Context: 32K
TTFT p50: 3.6 s

Text

embed-v4.0NewCohere

Input: $0.12/M$0.078/M
Output: –
Discount: 35.00% off
Context: 128K
TTFT p50: –

RetrievalImage input

Model				Context		Capabilities
claude-haiku-4.5Anthropic	$1.00/M$0.65/M	$5.00/M$3.25/M	35.00% off	200K	2.9 s	+1
claude-haiku-5.5NewAnthropic	$0.10/M$0.065/M	$0.50/M$0.325/M	35.00% off	100K	5.7 s	+1
claude-opus-4.5Anthropic	$5.00/M$3.25/M	$25.00/M$16.25/M	35.00% off	198K	3.9 s	+1
claude-opus-4.6Anthropic	$5.00/M$3.25/M	$25.00/M$16.25/M	35.00% off	1M	4.5 s	+1
claude-opus-4.8-fastNewAnthropic	$10.00/M$6.50/M	$50.00/M$32.50/M	35.00% off	1M	2.5 s	+1
claude-opus-5.5NewAnthropic	$4.00/M$2.60/M	$20.00/M$13.00/M	35.00% off	1M	6.5 s	+1
claude-sonnet-4.5Anthropic	$3.00/M$1.95/M	$15.00/M$9.75/M	35.00% off	198K	24.3 s	+1
claude-sonnet-4.6Anthropic	$3.00/M$1.95/M	$15.00/M$9.75/M	35.00% off	1M	3.2 s	+1
codestral-embedNewMistral AI	$0.15/M$0.098/M	–	35.00% off	–	–
deepseek-r1DeepSeek	$1.35/M$0.878/M	$5.40/M$3.51/M	35.00% off	160K	3.1 s
deepseek-v3.1NewDeepSeek	$0.25/M$0.163/M	$0.95/M$0.618/M	35.00% off	128K	2.5 s
deepseek-v3.2DeepSeek	$0.62/M$0.403/M	$1.85/M$1.20/M	35.00% off	160K	3.6 s
deepseek-v4-flash-vision-expNewDeepSeek	$0.30/M$0.195/M	$1.20/M$0.78/M	35.00% off	1M	4.1 s
devstral-2-123bNewMistral AI	$0.40/M$0.26/M	$2.00/M$1.30/M	35.00% off	256K	3 s
e2ee-gemma-4-26b-a4b-uncensored-pNewGoogle	$0.35/M$0.228/M	$1.10/M$0.715/M	35.00% off	262.1K	–
e2ee-glm-5.1NewZ.ai	$1.10/M$0.715/M	$4.15/M$2.70/M	35.00% off	200K	–
e2ee-gpt-oss-120b-pNewOpenAI	$0.13/M$0.085/M	$0.65/M$0.423/M	35.00% off	128K	–
e2ee-gpt-oss-20b-pNewOpenAI	$0.05/M$0.033/M	$0.19/M$0.124/M	35.00% off	128K	–
e2ee-qwen-2.5-7b-pNewAlibaba	$0.05/M$0.033/M	$0.13/M$0.085/M	35.00% off	32K	3.6 s
embed-v4.0NewCohere	$0.12/M$0.078/M	–	35.00% off	128K	–

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.