Skip to main content

Deepinfra LLM API Pricing

deepinfra.com
214
Models
$0.0015
Cheapest/1M
$0.790
Avg Price/1M
0
Free Models

What is Deepinfra's cheapest model?

Deepinfra's cheapest LLM is Embeddinggemma 300M at $0.0015 per million tokens (blended). They offer 214 models total.

All Deepinfra Models by Price

118 models
#ModelInputOutput
44OpenAI: gpt-oss-20b
20B
$0.030$0.140
49OpenAI: gpt-oss-120b
120B
$0.039$0.190
11Qwen3 Embedding 0 6B Batch
$0.0050Free
18Qwen3 Reranker 0 6B
$0.010Free
23Qwen3 Embedding 0 6B
$0.010Free
24Qwen3 Embedding 4B Batch
$0.010Free
25Qwen3 Embedding 4B
$0.020Free
26Qwen3 Reranker 4B
$0.025Free
31Qwen3 Embedding 8B Batch
$0.040Free
35Qwen3 Reranker 8B
$0.050Free
37Qwen3 Embedding 8B
$0.050Free
50Qwen3 235B A22b Instruct 2507
$0.071$0.100
40Google: Gemma 3 4B
4B
$0.040$0.080
46Google: Gemma 3 12B
12B
$0.040$0.130
47Phi 4 Multimodal Instruct
$0.050$0.100
14Meta: Llama 3.2 1B Instruct
1BOpen
$0.0050$0.010
27Meta: Llama 3.2 3B Instruct
3BOpen
$0.020$0.020
39Meta: Llama 3.2 11B Vision Instruct
11BOpen
$0.049$0.049
45Mistral: Mistral Small 3
24BOpen
$0.050$0.080
38Sao10k L3 8B Lunaris V1 Turbo
$0.040$0.050
29Meta Llama 3.1 8B Instruct Turbo
$0.020$0.030
30Mistralai Mistral Nemo Instruct 2407
$0.020$0.040
1Embeddinggemma 300M
$0.0020Free
36Google: Gemma 2 9B
9B
$0.030$0.060
48Nvidia Nemotron Nano 9B V2
9B
$0.040$0.160
41Qwen2 7B Instruct
$0.055$0.055
32Meta: Llama 3 8B Instruct
8BOpen
$0.030$0.040
33Meta Llama 3 8B Instruct
$0.030$0.040
2Intfloat E5 Base V2
$0.0050Free
17Intfloat Multilingual E5 Large
$0.010Free
21Intfloat E5 Large V2
$0.010Free
13Thenlper Gte Base
$0.0050Free
20Thenlper Gte Large
$0.010Free
34Mistral: Mistral 7B Instruct v0.3
7BOpen
$0.028$0.054
42Mistral: Mistral 7B Instruct v0.1
7BOpen
$0.055$0.055
43Mistral: Mistral 7B Instruct v0.2
7BOpen
$0.055$0.055
4Baai Bge Base EN V1 5
$0.0050Free
15Baai Bge M3
$0.010Free
16Baai Bge Large EN V1 5
$0.010Free
19Baai Bge M3 Multi
$0.010Free
22Baai Bge EN Icl
$0.010Free
3Sentence Transformers Clip Vit B 32
$0.0050Free
5Sentence Transformers Clip Vit B 32 Multilingual V1
$0.0050Free
6Sentence Transformers All Minilm L6 V2
$0.0050Free
7Sentence Transformers All Minilm L12 V2
$0.0050Free
8Sentence Transformers All Mpnet Base V2
$0.0050Free
9Sentence Transformers Paraphrase Minilm L6 V2
$0.0050Free
12Sentence Transformers Multi QA Mpnet Base Dot V1
$0.0050Free
10Shibing624 Text2vec Base Chinese
$0.0050Free
28meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
$0.020$0.030

Other Providers

Frequently Asked Questions

Deepinfra offers 214 models tracked on Sector HQ. The cheapest model starts at $0.0015 per million tokens (blended rate).