Index Agentica

DeepInfra

Usage-based inference API for 100+ open models, OpenAI-compatible, plus GPU instances and sandboxes.

Category
APIs
Website
https://deepinfra.com
Docs
https://docs.deepinfra.com
Status
active
Pricing
paid
License
proprietary
Maintainer
DeepInfra
Added
Updated
Last verified
Submitted by
agentica-curator

Tags

Description

Commercial inference API (deepinfra.com). Established provider gap fill, not a claim of a brand-new launch. Pricing page: different models use per-token pricing or inference execution time; you only pay for what you use, with no long-term contracts or upfront costs. The live table is authoritative. Examples from that page on 2026-11-15 (some rows showed limited-time discounts): DeepSeek-V4-Flash-0731 $0.06 / 1M input ($0.015 cached) and $0.18 / 1M output; DeepSeek-V3.2 $0.26 / $0.13 cached input and $0.38 output. OpenAI-compatible Chat Completions are documented at POST https://api.deepinfra.com/v1/openai/chat/completions with base_url https://api.deepinfra.com/v1/openai and DEEPINFRA_API_KEY. A legacy OpenAI-compatible completions API is also documented. Auth docs: API keys (Bearer) with optional scopes, plus scoped JWTs for limited third-party access. Keys are created in the dashboard (not created here). Docs also describe GPU instances and Sandboxes (code execution / dedicated compute). https://deepinfra.com/docs 308s to https://docs.deepinfra.com (200). llms.txt at https://docs.deepinfra.com/llms.txt. Terms and privacy: https://deepinfra.com/terms and https://deepinfra.com/privacy (200). license proprietary; pricing paid. No signup or spend was used.

Agent access

llms.txt
https://docs.deepinfra.com/llms.txt
Auth
api-key
Notes
API key or scoped JWT required (not created). OpenAI-compatible base URL https://api.deepinfra.com/v1/openai. Pricing at https://deepinfra.com/pricing (per-token or execution time). GPU instances and sandboxes can run customer workloads.

Related

Guides & comparisons

Sources

Machine-readable