OpenAI compatible API. Attested gateway. Public status.

DeepInfra

DeepInfra models on TrustedRouter with prices, routes, policy notes, and source links.

Verify gateway

1 URLbase_url migration

100smodels and routes

0prompt logs by default

`deepinfra`

No logs

All providers

Provider	DeepInfra
Models	8 public models
Prepaid routes	8
BYOK routes	8
Zero data retention	yes
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	Tracked as provider ZDR — DeepInfra documents memory-only handling with no storage of API content and no training on submitted API data. (Exception: requests to Google/Anthropic-backed models inherit those vendors' policies.) Policy source

Measured performance

308 samples

Continuously sampled across DeepInfra's routed models — p50 TTFT, throughput, and success rate. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	846 ms
Throughput	12 tok/s
Uptime	65.58%

Model	p50 TTFT	p50 TTFB	Throughput	Uptime	Config excluded	Samples
qwen/qwen3.5-27b	728 ms	671 ms	—	52.08%	—	48
google/gemma-4-26b-a4b-it	792 ms	724 ms	—	69.23%	—	52
google/gemma-3-12b-it	841 ms	737 ms	—	64.10%	—	39
meta-llama/llama-3.1-70b-instruct	846 ms	743 ms	—	63.16%	—	38
google/gemma-4-31b-it	886 ms	854 ms	12 tok/s	78.43%	—	51
google/gemma-3-27b-it	891 ms	787 ms	—	68.29%	—	41
google/gemma-3-4b-it	892 ms	789 ms	—	61.54%	—	39

Full provider & model leaderboard.

Provider models

Models served by DeepInfra.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	Context	Endpoints	Prompt	Completion	Routes
`Qwen/Qwen3-Embedding-8B` Qwen3 Embedding 8B benchmarks performance api	32,000	2	$0.011/1M	selected route	prepaid BYOK
`google/gemma-3-12b-it` Google: Gemma 3 12B benchmarks performance api	131,072	2	$0.055/1M	$0.165/1M	prepaid BYOK
`google/gemma-3-27b-it` Google: Gemma 3 27B benchmarks performance api	131,072	2	$0.088/1M	$0.176/1M	prepaid BYOK
`google/gemma-3-4b-it` Google: Gemma 3 4B benchmarks performance api	131,072	2	$0.055/1M	$0.11/1M	prepaid BYOK
`google/gemma-4-26b-a4b-it` Google: Gemma 4 26B A4B benchmarks performance api	262,144	2	$0.077/1M	$0.374/1M	prepaid BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B benchmarks performance api	262,144	2	$0.143/1M	$0.418/1M	prepaid BYOK
`meta-llama/llama-3.1-70b-instruct` Meta: Llama 3.1 70B Instruct benchmarks performance api	131,072	2	$0.44/1M	$0.44/1M	prepaid BYOK
`qwen/qwen3.5-27b` Qwen: Qwen3.5-27B benchmarks performance api	262,144	2	$0.286/1M	$2.86/1M	prepaid BYOK