LLM Cost Calculator

OpenAI API Pricing 2026

OpenAI offers GPT-6.1 Sol and Terra for complex work, alongside GPT-6 Luna for cost-sensitive workloads. Compare input and output rates across its model tiers.

Pricing data updated 2026-11-02. Provider rate card: platform.openai.com/docs/pricing.

Get OpenAI API access →

OpenAI Model Pricing

Prices in USD per 1M tokens

ModelInput / 1MOutput / 1MContext
GPT-6.1 Terra
Auto-added 2026-11; set isCurrent: true after review
$1$51,050,000
GPT-6.1 Terra Pro
Auto-added 2026-11; set isCurrent: true after review
$1$51,050,000
GPT-6 Astra
Auto-added 2026-11; set isCurrent: true after review
$10$501,050,000
GPT-6 Astra Pro
Auto-added 2026-11; set isCurrent: true after review
$10$501,050,000
GPT-6 Luna
Auto-added 2026-11; set isCurrent: true after review
$0.1$0.51,050,000
GPT-6 Luna Pro
Auto-added 2026-11; set isCurrent: true after review
$0.1$0.51,050,000
GPT-6 Sol
Auto-added 2026-11; set isCurrent: true after review
$2$101,050,000
GPT-6 Sol Pro
Auto-added 2026-11; set isCurrent: true after review
$2$101,050,000
GPT-6.1 Sol
Auto-added 2026-11; set isCurrent: true after review
$2$101,050,000
GPT-6.1 Sol Pro
Auto-added 2026-11; set isCurrent: true after review
$2$101,050,000
GPT-5.6 Luna
OpenAI cost-sensitive GPT-5.6 tier; 1.05M context
$0.2$1.21,050,000
GPT-5.6 Luna Pro
Auto-added 2026-08; set isCurrent: true after review
$0.2$1.21,050,000
GPT-5.6 Sol
OpenAI flagship for complex professional work; 1.05M context
$5$301,050,000
GPT-5.6 Sol Pro
Auto-added 2026-08; set isCurrent: true after review
$4$201,050,000
GPT-5.6 Terra
OpenAI balanced GPT-5.6 tier; 1.05M context
$2$121,050,000
GPT-5.6 Terra Pro
Auto-added 2026-08; set isCurrent: true after review
$2$121,050,000
GPT-5.4 Image 2
Auto-added 2026-08; set isCurrent: true after review
$8$15272,000
GPT-5.5
Latest OpenAI frontier model; 272K context standard tier
$5$301,050,000
GPT-5.5 Pro
GPT-5.5 Pro; 1M context; max capability tier
$30$1801,050,000
GPT-5.3 Chat
Auto-added 2026-08; set isCurrent: true after review
$1.75$14128,000
GPT-5.4
Strong coding & professional workloads; 272K context standard tier
$2.5$151,050,000
GPT-5.4 Mini
Best mini model for coding, computer use, and subagents
$0.75$4.5400,000
GPT-5.4 Nano
Ultra-low-cost GPT-5.4 tier for classification and routing
$0.2$1.25400,000
GPT-5.4 Pro
GPT-5.4 Pro; 1M context; enterprise workloads
$30$1801,050,000
GPT-5.3-Codex
Auto-added 2026-08; set isCurrent: true after review
$1.75$14400,000
GPT Audio
Auto-added 2026-08; set isCurrent: true after review
$2.5$10128,000
GPT Audio Mini
Auto-added 2026-08; set isCurrent: true after review
$0.6$2.4128,000
GPT-5.2-Codex
Auto-added 2026-08; set isCurrent: true after review
$1.75$14400,000
GPT-5.1-Codex-Max
Auto-added 2026-08; set isCurrent: true after review
$1.25$10400,000
GPT-5.2
Auto-added 2026-08; set isCurrent: true after review
$1.75$14400,000
GPT-5.2 Chat
Auto-added 2026-08; set isCurrent: true after review
$1.75$14128,000
GPT-5.2 Pro
Auto-added 2026-08; set isCurrent: true after review
$21$168400,000
GPT-5.1
Auto-added 2026-08; set isCurrent: true after review
$1.25$10400,000
GPT-5.1-Codex
Auto-added 2026-08; set isCurrent: true after review
$1.25$10400,000
GPT-5.1-Codex-Mini
Auto-added 2026-08; set isCurrent: true after review
$0.25$2400,000
GPT-5 Image
Auto-added 2026-08; set isCurrent: true after review
$10$10400,000
GPT-5 Image Mini
Auto-added 2026-08; set isCurrent: true after review
$2.5$2400,000
GPT-5 Pro
GPT-5 Pro; 400K context; heavy inference
$15$120400,000
gpt-oss-safeguard-20b
Auto-added 2026-08; set isCurrent: true after review
$0.08$0.3131,072
o3 Deep Research
o3 with deep-research mode; extended reasoning budget
$10$40200,000
o4 Mini Deep Research
o4-mini deep-research; cost-effective research tasks
$2$8200,000
GPT-5 Codex
GPT-5 Codex; 400K context; coding-optimized
$1.25$10400,000
GPT-5 Mini
Previous-gen budget model; GPT-5.4 Mini is the current mini tier
$0.25$2400,000
GPT-5
Previous flagship; use GPT-5.5 for new projects
$1.25$10400,000
GPT-5 Nano
GPT-5 Nano; 400K context; ultra-cheap classification & routing
$0.05$0.4400,000
gpt-oss-120b
OpenAI open-source 120B; runs on Groq/Together at low cost
$0.15$0.6131,072
gpt-oss-20b
Auto-added 2026-08; set isCurrent: true after review
$0.02$0.09131,072
o3 Pro
o3 Pro; extended thinking compute; top-tier reasoning
$20$80200,000
GPT-4.1
Previous production tier with 1M context; superseded by GPT-5.4
$2$81,047,576
GPT-4.1 Mini
Previous mid-tier; 1M context window
$0.4$1.61,047,576
GPT-4.1 Nano
Previous budget tier; GPT-5.4 Nano is cheaper for new workloads
$0.1$0.41,047,576
o3
Flagship reasoning; use when o4-mini accuracy is insufficient
$2$8200,000
o4 Mini High
Auto-added 2026-08; set isCurrent: true after review
$1.1$4.4200,000
o4-mini
Best-value reasoning model; chain-of-thought built in
$1.1$4.4200,000
o1-pro
OpenAI reasoning model; verify current availability in the official rate card
$150$600200,000
o3 Mini High
Auto-added 2026-08; set isCurrent: true after review
$1.1$4.4200,000
o3 Mini
OpenAI reasoning mini model; verify current availability in the official rate card
$1.1$4.4200,000
o1
OpenAI reasoning model; verify current availability in the official rate card
$15$60200,000
GPT-4o-mini
OpenAI budget model; verify current availability in the official rate card
$0.15$0.6128,000
GPT-4o
Previous generation; use GPT-4.1 for new projects
$2.5$10128,000

How to read these estimates

The monthly table assumes 70% input tokens and 30% output tokens. It is a consistent comparison baseline, not a prediction of your workload. Actual bills can also include cached-input discounts, batch pricing, tool calls, minimum charges, regional differences, retries, and taxes.

The linked source is the provider's pricing documentation. Catalog rates may include third-party prices. Verify the current rate card and model availability before committing to a budget.

Estimated Monthly Cost (70% input / 30% output split)

Model1M tokens/mo10M tokens/mo100M tokens/mo1B tokens/mo
GPT-6.1 Terra$2.20$22.00$220$2,200
GPT-6.1 Terra Pro$2.20$22.00$220$2,200
GPT-6 Astra$22.00$220$2,200$22,000
GPT-6 Astra Pro$22.00$220$2,200$22,000
GPT-6 Luna$0.220$2.20$22.00$220
GPT-6 Luna Pro$0.220$2.20$22.00$220
GPT-6 Sol$4.40$44.00$440$4,400
GPT-6 Sol Pro$4.40$44.00$440$4,400
GPT-6.1 Sol$4.40$44.00$440$4,400
GPT-6.1 Sol Pro$4.40$44.00$440$4,400
GPT-5.6 Luna$0.500$5.00$50.00$500
GPT-5.6 Luna Pro$0.500$5.00$50.00$500
GPT-5.6 Sol$12.50$125$1,250$12,500
GPT-5.6 Sol Pro$8.80$88.00$880$8,800
GPT-5.6 Terra$5.00$50.00$500$5,000
GPT-5.6 Terra Pro$5.00$50.00$500$5,000
GPT-5.4 Image 2$10.10$101$1,010$10,100
GPT-5.5$12.50$125$1,250$12,500
GPT-5.5 Pro$75.00$750$7,500$75,000
GPT-5.3 Chat$5.42$54.25$543$5,425
GPT-5.4$6.25$62.50$625$6,250
GPT-5.4 Mini$1.87$18.75$188$1,875
GPT-5.4 Nano$0.515$5.15$51.50$515
GPT-5.4 Pro$75.00$750$7,500$75,000
GPT-5.3-Codex$5.42$54.25$543$5,425
GPT Audio$4.75$47.50$475$4,750
GPT Audio Mini$1.14$11.40$114$1,140
GPT-5.2-Codex$5.42$54.25$543$5,425
GPT-5.1-Codex-Max$3.88$38.75$388$3,875
GPT-5.2$5.42$54.25$543$5,425
GPT-5.2 Chat$5.42$54.25$543$5,425
GPT-5.2 Pro$65.10$651$6,510$65,100
GPT-5.1$3.88$38.75$388$3,875
GPT-5.1-Codex$3.88$38.75$388$3,875
GPT-5.1-Codex-Mini$0.775$7.75$77.50$775
GPT-5 Image$10.00$100$1,000$10,000
GPT-5 Image Mini$2.35$23.50$235$2,350
GPT-5 Pro$46.50$465$4,650$46,500
gpt-oss-safeguard-20b$0.146$1.46$14.60$146
o3 Deep Research$19.00$190$1,900$19,000
o4 Mini Deep Research$3.80$38.00$380$3,800
GPT-5 Codex$3.88$38.75$388$3,875
GPT-5 Mini$0.775$7.75$77.50$775
GPT-5$3.88$38.75$388$3,875
GPT-5 Nano$0.155$1.55$15.50$155
gpt-oss-120b$0.285$2.85$28.50$285
gpt-oss-20b$0.041$0.410$4.10$41.00
o3 Pro$38.00$380$3,800$38,000
GPT-4.1$3.80$38.00$380$3,800
GPT-4.1 Mini$0.760$7.60$76.00$760
GPT-4.1 Nano$0.190$1.90$19.00$190
o3$3.80$38.00$380$3,800
o4 Mini High$2.09$20.90$209$2,090
o4-mini$2.09$20.90$209$2,090
o1-pro$285$2,850$28,500$285,000
o3 Mini High$2.09$20.90$209$2,090
o3 Mini$2.09$20.90$209$2,090
o1$28.50$285$2,850$28,500
GPT-4o-mini$0.285$2.85$28.50$285
GPT-4o$4.75$47.50$475$4,750

Frequently Asked Questions

How much does OpenAI LLM API cost?

OpenAI offers 60 models ranging from $0.020/1M to $150.00/1M input tokens. OpenAI offers GPT-6.1 Sol and Terra for complex work, alongside GPT-6 Luna for cost-sensitive workloads. Compare input and output rates across its model tiers.

Is OpenAI cheaper than self-hosting?

For low-volume workloads (under 100M tokens/month), cloud APIs like OpenAI are almost always cheaper than purchasing and maintaining GPU hardware. Use our calculator to find the exact break-even point for your usage.