ToolPicker
DeepInfra

DeepInfra

39/100

Serverless open embedding models (BGE, E5, GTE), per-token.

deepinfra.com

// scorecard · 39/100

verified 1mo ago
methodology →
Agent-readiness11/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server0/9
llms.txt0/3
Reliability & performance0/15
Actively maintained
Production-ready0/4
Updated recently
Pricing6/13
Itemized public pricing6/6
Free tier / trial0/4
Free-tier generosity0/3
Docs & DX10/12
Docs quality6/8
Public API2/2
Quickstart / examples2/2
Security & compliance8/12
SOC 26/6
ISO 270012/2
GDPR0/2
Security / trust page0/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size
Years operating

// rankings · cost per standard workload

#2 in Embeddings$1/ 100M tokens

bge-large-en-v1.5 $0.010/1M x100 = $1/mo

deepinfra.com/pricing

// overview

DeepInfra is an AI inference cloud providing OpenAI-compatible APIs to run 100+ models at scale including LLMs, vision, embeddings, image/video generation, and speech. It offers per-token pricing for language models, private deployments, GPU rental/clusters, zero data retention, and runs on its own optimized infrastructure. The company raised $107M Series B and is SOC 2 and ISO 27001 certified.

Best for: Developers and enterprises needing scalable, low-cost AI inference via simple APIs

// pricing

Pay-as-you-goper token or inference time
  • no long-term contracts
  • no minimums
  • scale up/down as needed

// security & compliance

SOC 2 ISO 27001 GDPR HIPAA

// features

  • OpenAI-compatible API for 100+ models
  • Per-token and pay-per-use pricing with no contracts
  • Private model deployments and GPU clusters
  • Zero retention policy
  • SOC 2 and ISO 27001 certified
  • Own cutting-edge inference-optimized infrastructure