Inference provider

DeepInfra

Headquarters: US

107

models

110

endpoints

DeepInfra website preview
DeepInfra website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
CSM 1Bdeepinfra/us4K$7.00$0.00——100.00%
Clefdeepinfra/bf1666K$0.12$0.00——100.00%
Clef Flashdeepinfra/bf1666K$0.02$0.00——100.00%
DeepSeek V3deepinfra/fp4164K$0.32$0.89——87.64%
DeepSeek V3.1deepinfra/fp4164K$0.25$0.95$0.13—100.00%
DeepSeek V3.2deepinfra/fp4164K$0.26$0.38$0.13—95.83%
DeepSeek V4 Flash 0423deepinfra/fp81.0M$0.09$0.18$0.02—99.25%
DeepSeek V4 Flash 0731deepinfra/fp81.0M$0.06$0.18$0.02—100.00%
DeepSeek V4 Flash Vision Expdeepinfra/fp81.0M$0.22$0.65$0.00686—100.00%
DeepSeek V4 Pro 0423deepinfra/fp81.0M$1.30$2.60$0.10—100.00%
DeepSeek V4 Pro 0813deepinfra/fp81.0M$1.30$2.60$0.10—99.64%
DeepSeek V4.1 Flashdeepinfra/fp81.0M$0.14$0.42$0.0042—100.00%
Drex v1.5deepinfra131K$0.04$0.00——100.00%
Drex v2.0deepinfra131K$0.06$0.00——100.00%
E5-Base-v2deepinfra/us512$0.005$0.00——100.00%
E5-Large-v2deepinfra/us512$0.01$0.00——100.00%
GLM 4.6deepinfra/fp4203K$0.50$2.00$0.10—99.86%
GLM 4.7deepinfra/fp4203K$0.40$1.75$0.08—59.58%
GLM 5.2deepinfra/fp41.0M$0.56$1.80$0.11—99.43%
GLM 5.3deepinfra/fp41.0M$0.56$2.50$0.13—98.89%
GLM 5.3 Flashdeepinfra/fp41.0M$0.08$0.25$0.02—99.11%
GTE-Basedeepinfra/us512$0.005$0.00——100.00%
GTE-Largedeepinfra/us512$0.01$0.00——100.00%
Gemma 3 12Bdeepinfra/bf16131K$0.05$0.15——99.93%
Gemma 3 27Bdeepinfra/fp8131K$0.08$0.16——99.79%
Gemma 3 4Bdeepinfra/bf16131K$0.05$0.10——100.00%
Gemma 4 26B A4Bdeepinfra/fp8262K$0.07$0.34——100.00%
Gemma 4 31Bdeepinfra/fp8262K$0.20$0.40——100.00%
Gemma 4 31Bdeepinfra/turbo262K$0.09$0.34$0.05—100.00%
Granite 4.2 8Bdeepinfra/bf16131K$0.06$0.25$0.02—100.00%
Hermes 3 405B Instructdeepinfra/fp8131K$1.00$1.00——99.84%
Hermes 3 70B Instructdeepinfra/fp8131K$0.70$0.70——100.00%
Hy4 previewdeepinfra/fp41.0M$0.83$2.50$0.04—100.00%
Inklingdeepinfra/fp8524K$0.95$4.05$0.16—98.90%
Inkling Smalldeepinfra/fp8524K$0.45$1.20$0.10—100.00%
Kimi K2.6deepinfra/fp4262K$0.75$3.50$0.15—98.34%
Kimi K3deepinfra/mxfp41.0M$2.85$14.25$0.29—99.93%
Kokoro 82Mdeepinfra/us4K$0.62$0.00——100.00%
Ling 3.0 Flashdeepinfra/bf16131K$0.06$0.18$0.01—98.95%
Ling 3.0 Flash VLdeepinfra/fp16131K$0.06$0.18$0.01—99.76%
Ling 3.1 Flashdeepinfra/fp4262K$0.30$0.90$0.06—97.41%
Llama 3 8B Lunarisdeepinfra/turbo8K$0.04$0.05——100.00%
Llama 3.1 70B Instructdeepinfra/turbo131K$0.40$0.40——96.29%
Llama 3.1 8B Instructdeepinfra/fp8131K$0.02$0.04——100.00%
Llama 3.1 Euryale 70B v2.2deepinfra/fp8131K$0.85$0.85——100.00%
Llama 3.3 70B Instructdeepinfra/turbo131K$0.10$0.32——96.81%
Llama 4 Scoutdeepinfra/fp8328K$0.10$0.30——99.90%
Llama Guard 4 12Bdeepinfra/bf16164K$0.18$0.18——99.93%
MiMo-V2.6-Flashdeepinfra/fp81.0M$0.13$0.27$0.00266—88.53%
MiMo-V2.6-Prodeepinfra/fp81.0M$0.43$0.87$0.0036—100.00%
MiniMax M3deepinfra/fp8524K$0.28$1.10$0.06—99.91%
Mistral Nemodeepinfra/fp8131K$0.03$0.03——100.00%
Mistral Small 3deepinfra/fp833K$0.05$0.08——100.00%
Mistral Small 3.2 24Bdeepinfra/fp8128K$0.08$0.20——99.71%
Multilingual-E5-Largedeepinfra/fp32512$0.01$0.00——100.00%
Muse Glimmer 30Bdeepinfra/bf16131K$0.30$1.20$0.04—100.00%
MythoMax 13Bdeepinfra/fp164K$0.40$0.40——100.00%
Nemotron 3 Superdeepinfra/bf16262K$0.08$0.40——100.00%
Nemotron 3 Ultradeepinfra/fp4262K$0.50$2.20$0.10—100.00%
Nemotron 3.5 ASR Streaming Multilingual 0.6Bdeepinfra/us—$3.33$0.00——99.71%
Nemotron 3.5 Content Safetydeepinfra/bf16131K$0.20$0.20——100.00%
Nemotron 3.5 Lightningdeepinfra/bf16262K$0.06$0.16$0.03—100.00%
Orpheus 3Bdeepinfra/us4K$7.00$0.00——77.78%
Phi 4deepinfra/bf1616K$0.07$0.14——100.00%
Qwen2.5 72B Instructdeepinfra/fp833K$0.36$0.40——99.72%
Qwen3 14Bdeepinfra/fp841K$0.12$0.24——98.00%
Qwen3 235B A22B Instruct 2507deepinfra/fp8262K$0.09$0.55——99.79%
Qwen3 30B A3Bdeepinfra/fp841K$0.12$0.50——100.00%
Qwen3 32Bdeepinfra/fp841K$0.08$0.28——98.96%
Qwen3 ASR 0.6Bdeepinfra/us—$3.33$0.00——100.00%
Qwen3 ASR 1.7Bdeepinfra/us—$7.50$0.00——99.27%
Qwen3 Coder 480B A35Bdeepinfra/turbo262K$0.30$1.00$0.10—86.64%
Qwen3 Embedding 4Bdeepinfra/us33K$0.02$0.00——100.00%
Qwen3 Embedding 8Bdeepinfra/us33K$0.01$0.00——100.00%
Qwen3 Next 80B A3B Instructdeepinfra/fp8262K$0.09$1.10——96.94%
Qwen3 VL 235B A22B Instructdeepinfra/fp8262K$0.20$0.88$0.11—99.79%
Qwen3 VL 30B A3B Instructdeepinfra/fp8262K$0.15$0.60——99.10%
Qwen3.5 397B A17Bdeepinfra/fp8262K$0.45$3.00$0.22—100.00%
Qwen3.5-27Bdeepinfra/fp8262K$0.26$2.60——100.00%
Qwen3.5-35B-A3Bdeepinfra/fp8262K$0.14$1.00$0.05—99.60%
Qwen3.5-9Bdeepinfra/bf16262K$0.10$0.15——99.70%
Qwen3.6 27Bdeepinfra/fp8262K$0.32$3.20——100.00%
Qwen3.6 35B A3Bdeepinfra/fp8262K$0.10$0.95$0.10—77.17%
Qwen3.8 27Bdeepinfra/bf16262K$0.15$1.88$0.04—75.69%
R1 0528deepinfra/fp4164K$0.50$2.15$0.35—99.93%
Step 5 Previewdeepinfra/fp81.0M$1.00$2.70$0.05—88.74%
Voxtral Mini 3B 2507deepinfra/bf16—$16.67$0.00——100.00%
Voxtral Small 24B 2507 STTdeepinfra/bf16—$50.00$0.00——96.20%
Whisper Large V3deepinfra/us—$7.50$0.00——100.00%
Whisper Large V3 Turbodeepinfra/us—$3.33$0.00——100.00%
all-MiniLM-L12-v2deepinfra/us512$0.005$0.00——100.00%
all-MiniLM-L6-v2deepinfra/us512$0.005$0.00——99.93%
all-mpnet-base-v2deepinfra/us512$0.005$0.00——99.28%
bge-base-en-v1.5deepinfra/us512$0.005$0.00——100.00%
bge-large-en-v1.5deepinfra/us512$0.01$0.00——100.00%
bge-m3deepinfra/fp328K$0.01$0.00——100.00%
gpt-oss-120bdeepinfra/bf16131K$0.04$0.17——99.93%
gpt-oss-120bdeepinfra/turbo131K$0.15$0.60——100.00%
gpt-oss-20bdeepinfra/bf16131K$0.03$0.14——99.70%
multi-qa-mpnet-base-dot-v1deepinfra/us512$0.005$0.00——100.00%
paraphrase-MiniLM-L6-v2deepinfra/us512$0.005$0.00——100.00%