GPT-4o pricing, context window, and cost calculator
An OpenAI model with tracked standard text pricing plus text and image input support.
Verified fields
Quick facts
gpt-4oSupported capabilities
- Streaming
- Function calling
- Structured outputs
- Prompt caching
- Batch API
- Fine-tuning
Only capabilities explicitly tracked from provider documentation are shown.
Source-tracked rates
Verified pricing profiles
Amounts are USD per 1M tokens unless the column states an hourly storage unit.
| Profile | Input / 1M | Cached input / 1M | Output / 1M | Notes |
|---|---|---|---|---|
| standardDefault | $2.50 USD | $1.25 USD | $10.00 USD | Used for default estimates. |
Workload estimate
GPT-4o cost calculator
Change the workload assumptions. The calculator uses the same shared pricing resolver as StackLens Compare.
Estimated monthly total$75.00
- Monthly input cost
- $25.00
- Monthly output cost
- $50.00
- Per 1,000 requests
- $7.50
- Active profile
- standard
Estimate excludes untracked provider-specific charges.
StackLens cost guidance
What a GPT-4o request costs
Two single-request examples use GPT-4o's tracked standard input and output rates. They isolate token charges before retries, tool calls, storage, or other API features.
Short interactive request
- Input
- 10,000 tokens · $0.025
- Output
- 1,000 tokens · $0.01
- Estimated token cost
- $0.035
Useful as a small prompt-and-response budgeting reference, not a prediction of response quality or length.
Document-heavy request
- Input
- 100,000 tokens · $0.25
- Output
- 5,000 tokens · $0.05
- Estimated token cost
- $0.30
This stays within the tracked 128,000-token context window when input and output are considered together.
Boundary: These examples compare API token charges only. Actual cost changes with cached input, retries, output length, and any separately billed features.
Explicit assumptions
Common workload examples
1M input tokens
$2.50 under the standard profile, excluding output and other charges.
1M output tokens
$10.00 under the standard profile, excluding input and other charges.
10,000 monthly requests
At 1,000 input and 500 output tokens per request: $75.00 under standard.
50% cached input
The same default workload with 50% cached input is estimated at $68.75. Cache savings apply only to the tracked cached-input rate.
Tracked relationships
Related models
StackLens relationship map based on model families and published decision comparisons. Find a workload match → Open relationship map → Open price map →
Featured comparisons
- GPT-4o vs Gemini 2.5 Pro cost
- GPT-4o vs Claude Sonnet 4.6 cost
- GPT-4o vs GPT-4o mini cost
- GPT-4o vs Kimi K2.6 cost
- GPT-4o vs GPT-5.6 Terra cost
- GPT-4o vs GPT-5.6 Sol cost
Continue your research
Verification
Sources and methodology
Pricing and limits are source-tracked and may change. Verify current values with the provider before making production purchasing decisions.
Calculator profile rule: standard is the verified default. Standard pricing is $2.50 per 1M input tokens, $1.25 per 1M cached input tokens, and $10.00 per 1M output tokens.