Cost optimization
Batch API Pricing: OpenAI, Claude & Gemini Costs
Compare standard and Batch API costs with a calculator using official model prices. Understand turnaround time, caching, retries, and budget assumptions.
Read articleOpenAI bills the API per token, with separate prices for input, cached input, output, long context, and the Batch API. The table lists selected text models from the official pricing page.
| Model | Input | Cached input | Cache writes | Output | Long-context input | Long-context output | Batch input | Batch output |
|---|---|---|---|---|---|---|---|---|
| gpt-6-astra | $10.00 | $1.00 | $12.50 | $50.00 | $20.00 | $75.00 | $5.00 | $25.00 |
| gpt-6.1-sol | $2.00 | $0.10 | $2.50 | $10.00 | $4.00 | $15.00 | $1.00 | $5.00 |
| gpt-6-sol | $2.00 | $0.20 | $2.50 | $10.00 | $4.00 | $15.00 | $1.00 | $5.00 |
| gpt-6-luna | $0.10 | $0.01 | $0.125 | $0.50 | $0.20 | $0.75 | $0.05 | $0.25 |
| gpt-5.6-sol | $4.00 | $0.40 | $5.00 | $20.00 | $8.00 | $30.00 | $2.00 | $10.00 |
| gpt-5.6-terra | $2.00 | $0.20 | $2.50 | $12.00 | $4.00 | $18.00 | $1.00 | $6.00 |
| gpt-5.6-luna | $0.20 | $0.02 | $0.25 | $1.20 | $0.40 | $1.80 | $0.10 | $0.60 |
| gpt-5.5 | $5.00 | $0.50 | Not listed | $30.00 | $10.00 | $45.00 | $2.50 | $15.00 |
| gpt-5.5-pro | $30.00 | Not listed | Not listed | $180.00 | $60.00 | $270.00 | $15.00 | $90.00 |
| gpt-5.4 | $2.50 | $0.25 | Not listed | $15.00 | $5.00 | $22.50 | $1.25 | $7.50 |
| gpt-5.4-mini | $0.75 | $0.075 | Not listed | $4.50 | Not listed | Not listed | $0.375 | $2.25 |
| gpt-5.4-nano | $0.20 | $0.02 | Not listed | $1.25 | Not listed | Not listed | $0.10 | $0.625 |
| gpt-5.4-pro | $30.00 | Not listed | Not listed | $180.00 | $60.00 | $270.00 | $15.00 | $90.00 |
| gpt-5.2 | $1.75 | $0.175 | Not listed | $14.00 | Not listed | Not listed | $0.875 | $7.00 |
| gpt-5.1 | $1.25 | $0.125 | Not listed | $10.00 | Not listed | Not listed | $0.625 | $5.00 |
| gpt-5 | $1.25 | $0.125 | Not listed | $10.00 | Not listed | Not listed | $0.625 | $5.00 |
| gpt-5-mini | $0.25 | $0.025 | Not listed | $2.00 | Not listed | Not listed | $0.125 | $1.00 |
| gpt-5-nano | $0.05 | $0.005 | Not listed | $0.40 | Not listed | Not listed | $0.025 | $0.20 |
| gpt-4.1 | $2.00 | $0.50 | Not listed | $8.00 | Not listed | Not listed | $1.00 | $4.00 |
| gpt-4.1-mini | $0.40 | $0.10 | Not listed | $1.60 | Not listed | Not listed | $0.20 | $0.80 |
| gpt-4.1-nano | $0.10 | $0.025 | Not listed | $0.40 | Not listed | Not listed | $0.05 | $0.20 |
| gpt-4o | $2.50 | $1.25 | Not listed | $10.00 | Not listed | Not listed | $1.25 | $5.00 |
| gpt-4o-mini | $0.15 | $0.075 | Not listed | $0.60 | Not listed | Not listed | $0.075 | $0.30 |
| o3 | $2.00 | $0.50 | Not listed | $8.00 | Not listed | Not listed | $1.00 | $4.00 |
| o4-mini | $1.10 | $0.275 | Not listed | $4.40 | Not listed | Not listed | $0.55 | $2.20 |
Uses official list prices for input and output tokens only. Cache, long context, tools, regional uplifts, taxes, and discounts are excluded.
Quota Monitor reads OpenAI API costs and official monthly spend limits through an Admin API key. It does not read prepaid credit balances.
Read the OpenAI API monitoring guideCost optimization
Compare standard and Batch API costs with a calculator using official model prices. Understand turnaround time, caching, retries, and budget assumptions.
Read articleCost optimization
Calculate cache reads, writes, and break-even reuse. A worked Claude example and a checklist for comparing prompt caching costs across providers.
Read articleUsage and billing
Separate Claude Code subscription limits, API charges, and local ccusage estimates. Learn what to measure and how to reconcile a real bill.
Read articleModel comparison
Compare Haiku 5.5 and Sonnet 5.5 token costs for short prompts, long prompts, output-heavy tasks, and cache reuse using shared pricing data.
Read article