AI Cost Index logo AI Cost Index LIVE
JA EN

Vendor Detail

DeepInfra

Observed model pricing snapshots and freshness signals for this vendor.

Models: 45 Latest Insight: 2026-06-03 Latest Snapshot: 2026-06-03 Evidence ↗

Quick Take

DeepInfra is presented here as a vendor pricing reference page first: review model count, freshness, and the current lowest observed prices, then move into model-level pages for exact comparisons.

  • This page lists 45 observed model entries as of 2026-06-03.
  • The lowest currently observed prices are $0.0200 for input and $0.0200 for output per 1M tokens.
  • No meaningful movement is visible in the latest snapshot; listed models are broadly flat versus the previous check.

The Evidence page provides the latest verification surface for this vendor. Final billing terms still need to be confirmed against the official pricing page and the vendor-specific offering conditions.

Llama 3.1 8B

llama-3-1-8b

FLAT

Input / 1M

$0.0200

Output / 1M

$0.0300

Updated: 2026-06-03 Model Detail

Llama 3.2 3B

llama-3-2-3b

FLAT

Input / 1M

$0.0200

Output / 1M

$0.0200

Updated: 2026-06-03 Model Detail

Mistral Nemo

mistral-nemo

FLAT

Input / 1M

$0.0200

Output / 1M

$0.0400

Updated: 2026-06-03 Model Detail

Llama 3 8B

llama-3-8b

FLAT

Input / 1M

$0.0300

Output / 1M

$0.0600

Updated: 2026-06-03 Model Detail

Gemma 3 4B

gemma-3-4b

FLAT

Input / 1M

$0.0400

Output / 1M

$0.0800

Updated: 2026-06-03 Model Detail

GPT-OSS 20B

gpt-oss-20b

FLAT

Input / 1M

$0.0400

Output / 1M

$0.1500

Updated: 2026-06-03 Model Detail

Lunaris 8B

lunaris-8b

FLAT

Input / 1M

$0.0400

Output / 1M

$0.0500

Updated: 2026-06-03 Model Detail

NVIDIA Nemotron Nano 9B v2

nvidia-nemotron-nano-9b-v2

FLAT

Input / 1M

$0.0400

Output / 1M

$0.1600

Updated: 2026-06-03 Model Detail

Qwen 2.5 7B

qwen-2-5-7b

FLAT

Input / 1M

$0.0400

Output / 1M

$0.1000

Updated: 2026-06-03 Model Detail

Llama 3.2 11B Vision

llama-3-2-11b-vision

FLAT

Input / 1M

$0.0490

Output / 1M

$0.0490

Updated: 2026-06-03 Model Detail

Gemma 3 12B

gemma-3-12b

FLAT

Input / 1M

$0.0500

Output / 1M

$0.1000

Updated: 2026-06-03 Model Detail

GPT-OSS 120B

gpt-oss-120b

FLAT

Input / 1M

$0.0500

Output / 1M

$0.4500

Updated: 2026-06-03 Model Detail

Mistral Small

mistral-small

FLAT

Input / 1M

$0.0500

Output / 1M

$0.0800

Updated: 2026-06-03 Model Detail

Llama Guard 3 8B

llama-guard-3-8b

FLAT

Input / 1M

$0.0550

Output / 1M

$0.0550

Updated: 2026-06-03 Model Detail

Qwen 3 14B

qwen-3-14b

FLAT

Input / 1M

$0.0600

Output / 1M

$0.2400

Updated: 2026-06-03 Model Detail

Phi-4

phi-4

FLAT

Input / 1M

$0.0700

Output / 1M

$0.1400

Updated: 2026-06-03 Model Detail

Llama 4 Scout

llama-4-scout

FLAT

Input / 1M

$0.0800

Output / 1M

$0.3000

Updated: 2026-06-03 Model Detail

MythoMax L2 13B

mythomax-l2-13b

FLAT

Input / 1M

$0.0800

Output / 1M

$0.0900

Updated: 2026-06-03 Model Detail

Qwen 3 30B A3B

qwen-3-30b-a3b

FLAT

Input / 1M

$0.0800

Output / 1M

$0.2900

Updated: 2026-06-03 Model Detail

Gemma 3 27B

gemma-3-27b

FLAT

Input / 1M

$0.0900

Output / 1M

$0.1600

Updated: 2026-06-03 Model Detail

Gemini 2.0 Flash

gemini-2-0-flash

FLAT

Input / 1M

$0.1000

Output / 1M

$0.4000

Updated: 2026-06-03 Model Detail

Qwen 3 32B

qwen-3-32b

FLAT

Input / 1M

$0.1000

Output / 1M

$0.2800

Updated: 2026-06-03 Model Detail

Qwen 2.5 72B

qwen-2-5-72b

FLAT

Input / 1M

$0.1200

Output / 1M

$0.3900

Updated: 2026-06-03 Model Detail

Qwen 3 Next 80B A3B

qwen-3-next-80b-a3b

FLAT

Input / 1M

$0.1400

Output / 1M

$1.4000

Updated: 2026-06-03 Model Detail

Llama 4 Maverick

llama-4-maverick

FLAT

Input / 1M

$0.1500

Output / 1M

$0.6000

Updated: 2026-06-03 Model Detail

QwQ 32B

qwq-32b

FLAT

Input / 1M

$0.1500

Output / 1M

$0.4000

Updated: 2026-06-03 Model Detail

Llama Guard 4 12B

llama-guard-4-12b

FLAT

Input / 1M

$0.1800

Output / 1M

$0.1800

Updated: 2026-06-03 Model Detail

Qwen 3 235B A22B

qwen-3-235b-a22b

FLAT

Input / 1M

$0.1800

Output / 1M

$0.5400

Updated: 2026-06-03 Model Detail

Qwen 2.5 32B

qwen-2-5-32b

FLAT

Input / 1M

$0.2000

Output / 1M

$0.6000

Updated: 2026-06-03 Model Detail

Llama 3.3 70B

llama-3-3-70b

FLAT

Input / 1M

$0.2300

Output / 1M

$0.4000

Updated: 2026-06-03 Model Detail

olmOCR 7B

olmocr-7b

FLAT

Input / 1M

$0.2700

Output / 1M

$1.5000

Updated: 2026-06-03 Model Detail

Gemini 2.5 Flash

gemini-2-5-flash

FLAT

Input / 1M

$0.3000

Output / 1M

$2.5000

Updated: 2026-06-03 Model Detail

DeepSeek V3

deepseek-v3

FLAT

Input / 1M

$0.3800

Output / 1M

$0.8900

Updated: 2026-06-03 Model Detail

GLM 4.5

glm-4-5

FLAT

Input / 1M

$0.4000

Output / 1M

$1.6000

Updated: 2026-06-03 Model Detail

Mixtral 8x7B

mixtral-8x7b

FLAT

Input / 1M

$0.4000

Output / 1M

$0.4000

Updated: 2026-06-03 Model Detail

Qwen 3 Coder 480B A35B

qwen-3-coder-480b-a35b

FLAT

Input / 1M

$0.4000

Output / 1M

$1.6000

Updated: 2026-06-03 Model Detail

WizardLM 2 8x22B

wizardlm-2-8x22b

FLAT

Input / 1M

$0.4800

Output / 1M

$0.4800

Updated: 2026-06-03 Model Detail

Kimi K2 Instruct

kimi-k2-instruct

FLAT

Input / 1M

$0.5000

Output / 1M

$2.0000

Updated: 2026-06-03 Model Detail

Llama 3.1 70B

llama-3-1-70b

FLAT

Input / 1M

$0.6000

Output / 1M

$0.6000

Updated: 2026-06-03 Model Detail

DeepSeek R1

deepseek-r1

FLAT

Input / 1M

$0.7000

Output / 1M

$2.4000

Updated: 2026-06-03 Model Detail

Llama 3.1 405B

llama-3-1-405b

FLAT

Input / 1M

$1.0000

Output / 1M

$1.0000

Updated: 2026-06-03 Model Detail

Gemini 2.5 Pro

gemini-2-5-pro

FLAT

Input / 1M

$1.2500

Output / 1M

$10.0000

Updated: 2026-06-03 Model Detail

Claude 3.7 Sonnet

claude-3-7-sonnet

FLAT

Input / 1M

$3.3000

Output / 1M

$16.5000

Updated: 2026-06-03 Model Detail

Claude 4 Sonnet

claude-4-sonnet

FLAT

Input / 1M

$3.3000

Output / 1M

$16.5000

Updated: 2026-06-03 Model Detail

Claude Opus 4

claude-4-opus

FLAT

Input / 1M

$16.5000

Output / 1M

$82.5000

Updated: 2026-06-03 Model Detail

Useful Comparisons From This Vendor

Jump straight into compare pages built from the models visible on this vendor page.

Browse Compare

Premium Report

Need Deeper Pricing Insight?

Get cross-vendor cost intelligence, including hidden token/API costs,
plus full-period change history in CSV format.

Cross-Vendor Benchmark Historical CSV Instant Download
Buy via PayPal - Last Month Report (CSV) — $1,500

Instant download