Skip to main content

Deepinfra LLM API Pricing

deepinfra.com
232
Models
$0.0015
Cheapest/1M
$0.768
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 232 models total.

All Deepinfra Models by Price

135 models
#ModelInputOutput
132Zai Org GLM 5
$0.800$2.56
74Bytedance Seed 2.0 Mini
$0.100$0.400
82DeepSeek: DeepSeek V3.2 Exp
Open
$0.210$0.320
88DeepSeek V3.2
$0.260$0.380
63Allenai Olmocr 2 7B 1025
$0.090$0.190
70Zai Org GLM 4.7 Flash
$0.060$0.400
116Zai Org GLM 4 7
$0.400$1.75
64Qwen: Qwen3 Coder 30B A3B Instruct
30BOpen
$0.070$0.260
93Paddlepaddle Paddleocr VL 0 9B
$0.140$0.800
91AllenAI: Olmo 3.1 32B Instruct
32B
$0.200$0.600
106Minimaxai Minimax M2 5
$0.270$0.950
107Minimaxai Minimax M2 1
$0.270$0.950
108Zai Org GLM 4 6v
$0.300$0.900
117Zai Org GLM 4 6
$0.430$1.74
97DeepSeek: DeepSeek V3.1 Terminus
Open
$0.210$0.790
98DeepSeek V3.1
$0.210$0.790
126DeepSeek: R1 0528
Open
$0.500$2.15
51OpenAI: gpt-oss-20b
20B
$0.030$0.140
56OpenAI: gpt-oss-120b
120B
$0.039$0.190
113Bytedance Seed 1 8
$0.250$2.00
118Moonshotai Kimi K2 Instruct 0905
$0.400$2.00
124MoonshotAI: Kimi K2 Thinking
$0.470$2.00
5Qwen3 Embedding 0 6B Batch
$0.0050Free
18Qwen3 Embedding 0 6B
$0.010Free
19Qwen3 Embedding 8B
$0.010Free
23Qwen3 Reranker 0 6B
$0.010Free
26Qwen3 Embedding 4B Batch
$0.010Free
29Qwen3 Embedding 4B
$0.020Free
30Qwen3 Reranker 4B
$0.025Free
37Qwen3 Embedding 8B Batch
$0.040Free
42Qwen3 Reranker 8B
$0.050Free
57Qwen3 235B A22b Instruct 2507
$0.071$0.100
65Qwen: Qwen3 32B
32BOpen
$0.080$0.280
67Qwen: Qwen3 30B A3B
30BOpen
$0.080$0.280
85Qwen: Qwen3 235B A22B
235BOpen
$0.180$0.540
95Qwen: Qwen3 Next 80B A3B Instruct
80BOpen
$0.090$1.10
101Qwen: Qwen3 VL 235B A22B Instruct
235BOpen
$0.200$0.880
123Google: Gemini 2.5 Flash
$0.300$2.50
68Llama 4 Scout 17B 16e Instruct
$0.080$0.300
83Llama 4 Maverick 17B 128e Instruct Fp8
$0.150$0.600
45Google: Gemma 3 4B
4B
$0.040$0.080
53Google: Gemma 3 12B
12B
$0.040$0.130
61Google: Gemma 3 27B
27B
$0.080$0.160
81Qwen: QwQ 32B
32BOpen
$0.150$0.400
125Bytedance Seedance 1.5 Pro
$1.20Free
54Phi 4 Multimodal Instruct
$0.050$0.100
87DeepSeek: R1 Distill Qwen 32B
32BOpen
$0.270$0.270
115DeepSeek: R1 Distill Llama 70B
70BOpen
$0.700$0.800
96DeepSeek V3 0324
$0.200$0.770
109DeepSeek V3
$0.320$0.890

Other Providers

Frequently Asked Questions

Deepinfra offers 232 models tracked on Sector HQ. The cheapest model starts at $0.0015 per million tokens (blended rate).