Code review assistant cost drivers
Large diffs and repository instructions make reviews input-heavy, while retries and follow-up reviews can increase calls per pull request.
Workload cost scenario
AI Code Review API Cost Calculator
Estimate LLM API costs for code review prompts containing diffs, repository context, and structured review output.
Developer tooling teams evaluating an automated review workflow.
Lowest tracked estimate
$20.85
Gemini 2.5 Flash-Lite for the current assumptions
Lowest cost does not mean best model. Test output quality, latency, retries, and reliability on your own workload.
Cost comparison
Estimated monthly cost by model
Comparing 22 models that fit the initial input length.
| Model | Provider | Input cost | Output cost | Monthly estimate | Context usage |
|---|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $13.65 | $7.20 | $20.85 | 1.4% | |
| DeepSeek V4 Flash non-thinking | DeepSeek | $18.94 | $5.04 | $23.98 | 1.5% |
| GPT-4o mini | OpenAI | $21.38 | $10.80 | $32.18 | 11.7% |
| gpt-5.4-nano | OpenAI | $27.30 | $22.50 | $49.80 | 3.8% |
| Gemini 3.5 Live Translate Preview | $34.13 | $27.00 | $61.13 | 11.4% | |
| Gemini 3.1 Flash-Lite | $34.13 | $27.00 | $61.13 | 1.4% | |
| deepseek-v4-pro | DeepSeek | $58.78 | $15.66 | $74.44 | 1.5% |
| Gemini 2.5 Flash | $40.95 | $45.00 | $85.95 | 1.4% | |
| Gemini 3 Flash Preview | $68.25 | $54.00 | $122.25 | 1.4% | |
| gpt-5.4-mini | OpenAI | $102.38 | $81.00 | $183.38 | 3.8% |
| Claude Haiku 4.5 | Anthropic | $136.50 | $90.00 | $226.50 | 7.5% |
| gpt-5.6-luna | OpenAI | $136.50 | $108.00 | $244.50 | 1.4% |
| Gemini 2.5 Pro | $170.63 | $180.00 | $350.63 | 1.4% | |
| Gemini 3.5 Flash | $204.75 | $162.00 | $366.75 | 1.4% | |
| Claude Sonnet 5 | Anthropic | $273.00 | $180.00 | $453.00 | 1.5% |
| Gemini 3.1 Pro Preview | $273.00 | $216.00 | $489.00 | 1.4% | |
| GPT-4o | OpenAI | $356.25 | $180.00 | $536.25 | 11.7% |
| gpt-5.6-terra | OpenAI | $341.25 | $270.00 | $611.25 | 1.4% |
| Claude Sonnet 4.6 | Anthropic | $409.50 | $270.00 | $679.50 | 1.5% |
| Claude Opus 4.8 | Anthropic | $682.50 | $450.00 | $1,132.50 | 1.5% |
| gpt-5.6-sol | OpenAI | $682.50 | $540.00 | $1,222.50 | 1.4% |
| Claude Fable 5 | Anthropic | $1,500.00 | $900.00 | $2,400.00 | 1.5% |
What to measure
- Measure tokens by diff-size band.
- Avoid resending unchanged repository context.
- Separate initial review calls from follow-up validation.
Estimate boundary: This scenario does not claim equal review quality and excludes code indexing, sandbox, and repository-hosting costs.
View pricing sources
OpenAI model pricingHigh confidenceChecked 2026-07-13
Tracked prices for included OpenAI models are checked against official provider documentation.
Anthropic model pricingHigh confidenceChecked 2026-07-12
Tracked prices for included Anthropic models are checked against official provider documentation.
Google model pricingHigh confidenceChecked 2026-07-14
Tracked prices for included Google models are checked against official provider documentation.
DeepSeek model pricingHigh confidenceChecked 2026-07-12
Tracked prices for included DeepSeek models are checked against official provider documentation.
Anthropic model pricingHigh confidenceChecked 2026-07-14
Tracked prices for included Anthropic models are checked against official provider documentation.