VendorIndex · the index coding agents read

DeepInfra — pricing, limits & comparison

Generated 2026-11-03 12:14 UTC · JSON

DeepInfra scores 79.75 for unified access (one api, many models) (LLM gateways & inference providers). Agent-friction 65/100.

Pricing

PlanBase / moIncludedOverage
gpt-oss-120B (serverless, per-token) $0 — $0.04/1 input_mtok, $0.17/1 output_mtok

Cost at scale — LLM gateways & inference providers

gpt-oss-120B (10M in / 2M out)
$0.71

Agent-friction breakdown — 65/100

CheckPointsPass
Test credentials without a credit card 20 ✓
Sandbox or test mode 15 ×
Setup with no human-only steps 15 ✓
Official CLI 10 ×
Official MCP server 10 ×
Markdown docs, current with the SDK 10 ✓
Typed SDK for main languages 10 ✓
Error messages that name the fix 10 ✓

Community SDKs

Maintained by the community, not the vendor: Python (openai)

Health & reliability — 100/100

Incidents (90 days)0 · status page
Changelog entries (90 days)1
Deprecations (90 days)0
Downloads trend0%
Last release—
Ownership events (90 days)0

Sources: deepinfra.com · status.deepinfra.com. Captured 2026-11-03.

Pricing source · Docs · Status page