AI API Cost Matrix
Compare input/output pricing, context windows, and tiers across all 143 models from 22 providers. Sort, filter, and find the cheapest option for your workload.
💰 Monthly Cost Estimator
| Model ↕ | Provider ↕ | Tier ↕ | Input $/M ↕ | Output $/M ↕ | Est. Monthly* ↕ | Context ↕ | Link |
|---|
* Estimated monthly cost based on 1,000 input tokens, 500 output tokens, 1,000 requests/day, 30 days. Adjust in the estimator above.
Get personalized cost optimization
APIpulse's free tools cover cost calculators, model comparisons and migration guides, with every price checked against the provider's own pricing page.
Free Tools →Related Tools
Frequently Asked Questions
What is the cheapest AI API in 2026?
GPT-oss 20B is the cheapest at $0.08/$0.35 per million input/output tokens. For production use, DeepSeek V4 Flash ($0.22/$0.66) offers the best value with 1M context window.
Which AI model has the best price-to-performance ratio?
DeepSeek V4 Pro ($0.66/$1.98) offers the best price-to-performance for most tasks. For premium quality, Claude Sonnet 4.6 ($3/$15) provides excellent capability at a mid-range price with 1M context.
How much does GPT-5 cost per million tokens?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens. GPT-5.5 costs $5.00/$30.00. GPT-5 mini is the budget option at $0.25/$2.00.
What is the cheapest AI API for high-volume applications?
For high-volume use, GPT-oss 20B ($0.08/$0.35), Llama 3.1 8B ($0.10/$0.10), and Mistral Small 4 ($0.15/$0.60) are the cheapest options. DeepSeek V4 Flash ($0.22/$0.66) offers the best quality-to-cost ratio at scale.