AI Rate Card

deepinfra

Provider · 375 offers · 359 models

This is my company Prove the domain and manage this card: the look, analytics, a recheck of your prices.

Found 375

Simple Full

Download

The offers of the current filter, current prices in USD.

Free for everyone, no sign-in needed: the whole catalog in one file, up to 20 downloads an hour (60 with a free account).

JSONCSVYAMLExcel

The same as an API for bots (format=json|csv|yaml, limit, offset):

https://airatecard.com/export?format=json&provider=deepinfra

API parameters and a form

ModelVariantIconProviderInput, $Output, $Your cost/mo, $Subscription, $/moRegionContextMax outputAcceptsLast checkedRecommendActions
Provider 1
×
Pricing
Region
Input
Status
BGE Base EN v1.5BGE Base EN v1.5deepinfra ↗$0.005——512—text4 Nov
12:00
Qwen3-Embedding-0.6B-batchQwen3-Embedding-0.6B-batchdeepinfra ↗$0.005——33K—4 Nov
12:00
E5 Base v2E5 Base v2deepinfra ↗$0.005——512—text4 Nov
12:00
Llama 3.2 1B InstructLlama 3.2 1B Instructdeepinfra ↗$0.005$0.01—131K32Ktext4 Nov
12:00
all-MiniLM-L12-v2all-MiniLM-L12-v2deepinfra ↗$0.005——512—text4 Nov
12:00
all-MiniLM-L6-v2all-MiniLM-L6-v2deepinfra ↗$0.005——512—text4 Nov
12:00
all-mpnet-base-v2all-mpnet-base-v2deepinfra ↗$0.005——512—text4 Nov
12:00
clip-ViT-B-32clip-ViT-B-32deepinfra ↗$0.005——77—4 Nov
12:00
clip-ViT-B-32-multilingual-v1clip-ViT-B-32-multilingual-v1deepinfra ↗$0.005——512—4 Nov
12:00
Multi-QA-mpnet-base-dot-v1multi-qa-mpnet-base-dot-v1deepinfra ↗$0.005——512—text4 Nov
12:00
paraphrase-MiniLM-L6-v2paraphrase-MiniLM-L6-v2deepinfra ↗$0.005——512—text4 Nov
12:00
text2vec-base-chinesetext2vec-base-chinesedeepinfra ↗$0.005——512—4 Nov
12:00
GTE BaseGTE Basedeepinfra ↗$0.005——512—text4 Nov
12:00
bge-en-iclbge-en-icldeepinfra ↗$0.01——8K—4 Nov
12:00
BGE Large EN v1.5BGE Large EN v1.5deepinfra ↗$0.01——512—text4 Nov
12:00
BGE M3BGE M3deepinfra ↗$0.01——8K—text4 Nov
12:00
bge-m3-multibge-m3-multideepinfra ↗$0.01——512—4 Nov
12:00
bge-m3-multi-8kbge-m3-multi-8kdeepinfra ↗$0.01——8K—4 Nov
12:00
Qwen3 Embedding 0.6BQwen3 Embedding 0.6Bdeepinfra ↗$0.01——33K—text4 Nov
12:00
Qwen3-Embedding-4B-batchQwen3-Embedding-4B-batchdeepinfra ↗$0.01——33K—4 Nov
12:00
Qwen3 Embedding 8BQwen3 Embedding 8Bdeepinfra ↗$0.01——33K—text4 Nov
12:00
Qwen3 Reranker 0.6BQwen3 Reranker 0.6Bdeepinfra ↗$0.01——33K—text4 Nov
12:00
Qwen3.5 0.8BQwen3.5 0.8Bdeepinfra ↗$0.01$0.05—262K82Ktext, image/bmp, image/jpeg +104 Nov
12:00
E5 Large v2E5 Large v2deepinfra ↗$0.01——512—text4 Nov
12:00
Multilingual E5 LargeMultilingual E5 Largedeepinfra ↗$0.01——512—text4 Nov
12:00
E5 Multi-Lingual Large Embeddings 0.6BE5 Multi-Lingual Large Embeddings 0.6Bdeepinfra ↗$0.01——512512text4 Nov
12:00
Nemotron 3 Embed 1BNemotron 3 Embed 1Bdeepinfra ↗$0.01——33K—text4 Nov
12:00
Llama Nemotron Embed VL 1B v2Llama Nemotron Embed VL 1B v2deepinfra ↗$0.01——10K2Ktext, image/png, image/jpeg4 Nov
12:00
Llama Nemotron Rerank VL 1B v2Llama Nemotron Rerank VL 1B v2deepinfra ↗$0.01——10K4Ktext, image/png, image/jpeg +44 Nov
12:00
GTE LargeGTE Largedeepinfra ↗$0.01——512—text4 Nov
12:00

Ranges in one field: "from-to" - "0.5-3", "-3" (up to), "128k-" (from); a colon works too. Several ticked values of one column are ORed, columns are ANDed.

Source: AI Rate Card, https://airatecard.com/en/providers/deepinfra, prices checked 2026-11-04