Skip to content

DeepInfra

Inference host · 57 models · 61 priced routes · deepinfra.com

Models on DeepInfra

ModelIn / out per 1M
Qwen3 Embedding 8B
DeepInfra, us
$0.01 / FreeSame vs headline
Qwen3 Embedding 4B
DeepInfra, us
$0.02 / FreeSame vs headline
Mistral Nemo
DeepInfra, fp8, fp8
$0.019 / $0.03+4% vs headline
Llama 3.1 8B Instruct
DeepInfra, fp8, fp8
$0.02 / $0.04Same vs headline
gpt-oss-20b
DeepInfra, bf16, bf16
$0.03 / $0.14+60% vs headline
Mistral Small 3
DeepInfra, fp8, fp8
$0.05 / $0.08Same vs headline
Gemma 3 4B
DeepInfra, bf16, bf16
$0.05 / $0.1Same vs headline
gpt-oss-120b
DeepInfra, bf16, bf16
$0.037 / $0.17+8% vs headline
Gemma 3 12B
DeepInfra, bf16, bf16
$0.05 / $0.15Same vs headline
DeepSeek V4 Flash 0731
DeepInfra, fp8, fp8
$0.06 / $0.18+14% vs headline
Gemma 3 27B
DeepInfra, fp8, fp8
$0.08 / $0.16Same vs headline
Mistral Small 3.2 24B
DeepInfra, fp8, fp8
$0.075 / $0.2Same vs headline
DeepSeek V4 Flash 0423
DeepInfra, fp8, fp8
$0.09 / $0.18+84% vs headline
Qwen3.5-9B
DeepInfra, bf16, bf16
$0.1 / $0.15+22% vs headline
GLM 5.3 Flash
DeepInfra, fp4, fp4
$0.075 / $0.25+73% vs headline
Qwen3 32B
DeepInfra, fp8, fp8
$0.08 / $0.28Same vs headline
Gemma 4 26B A4B
DeepInfra, fp8, fp8
$0.07 / $0.34+59% vs headline
Qwen3 14B
DeepInfra, fp8, fp8
$0.12 / $0.24-62% vs headline
Llama 4 Scout
DeepInfra, fp8, fp8
$0.1 / $0.3Same vs headline
Gemma 4 31B
DeepInfra, turbo, fp4
$0.09 / $0.34Same vs headline

About DeepInfra

Caching: Cached input prices listed per model (e.g. $0.06 / $0.015 cached)

Across fru.devCompany profile

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.