Free tool
Gemini vs GPT API pricing, compared model by model
On 25 September 2026 the cheapest Gemini model costs $0.05 per million input tokens against $0.018 for the cheapest GPT model, and the typical Gemini model is the cheaper of the two.
| Gemini (Google) | GPT (OpenAI) | |
|---|---|---|
| Models listed | 26 | 63 |
| Cheapest model | Gemma 3 4B, $0.05 in, $0.10 out | gpt-oss-20b, $0.018 in, $0.09 out |
| Most expensive model | Nano Banana Pro (Gemini 3 Pro Image), $2.00 in, $12.00 out | o1-pro, $150.00 in, $600.00 out |
| Median input price | $0.50 | $1.75 |
| Median output price | $2.75 | $10.00 |
| Largest context | 1.04858M, Gemini 3.8 Flash | 1.05M, GPT-6 Luna Pro |
| Newest model | Gemini 3.8 Flash, 2026-09-02 | GPT-6 Luna Pro, 2026-09-22 |
| Models with a batch price | 11 | 37 |
Every model, with your monthly cost
| Model | Provider | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|---|
| GPT-6 Luna Pro | OpenAI | $0.10 | $0.50 | $0.01 | $0.05 / $0.25 | 1.05M | $13.50 | 2026-09-22 |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | $0.01 | $0.05 / $0.25 | 1.05M | $13.50 | 2026-09-22 |
| GPT-6 Sol Pro | OpenAI | $2.00 | $10.00 | $0.20 | $1.00 / $5.00 | 1.05M | $270.00 | 2026-09-22 |
| GPT-6 Sol | OpenAI | $2.00 | $10.00 | $0.20 | $1.00 / $5.00 | 1.05M | $270.00 | 2026-09-22 |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | $1.00 | $5.00 / $25.00 | 1.05M | $1,350.00 | 2026-09-04 |
| GPT-6 Astra Pro | OpenAI | $10.00 | $50.00 | $1.00 | $5.00 / $25.00 | 1.05M | $1,350.00 | 2026-09-04 |
| Gemini 3.8 Flash | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-09-02 | |
| Gemini 3.7 Flash | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-08-13 | |
| Gemini 3.6 Flash | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-07-21 | |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | $0.03 | $0.15 / $1.25 | 1.04858M | $55.50 | 2026-07-21 | |
| GPT-5.6 Luna Pro | OpenAI | $0.20 | $1.20 | $0.02 | $0.10 / $0.60 | 1.05M | $30.00 | 2026-07-09 |
| GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | $0.02 | $0.10 / $0.60 | 1.05M | $30.00 | 2026-07-09 |
| GPT-5.6 Terra Pro | OpenAI | $2.00 | $12.00 | $0.20 | $1.00 / $6.00 | 1.05M | $300.00 | 2026-07-09 |
| GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | $0.20 | $1.00 / $6.00 | 1.05M | $300.00 | 2026-07-09 |
| GPT-5.6 Sol Pro | OpenAI | $2.00 | $10.00 | $0.20 | $1.00 / $5.00 | 1.05M | $270.00 | 2026-07-09 |
| GPT-5.6 Sol | OpenAI | $2.00 | $10.00 | $0.20 | $1.00 / $5.00 | 1.05M | $270.00 | 2026-07-09 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.25 | $1.50 | 66K | $37.50 | 2026-06-30 | |||
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.50 | $3.00 | 131K | $75.00 | 2026-06-18 | |||
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $12.00 | $0.20 | 131K | $300.00 | 2026-06-18 | ||
| Gemini 3.5 Flash | $1.50 | $9.00 | $0.15 | $0.75 / $4.50 | 1.04858M | $225.00 | 2026-05-19 | |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | $0.025 | $0.125 / $0.75 | 1.04858M | $37.50 | 2026-05-07 | |
| GPT Chat Latest | OpenAI | $5.00 | $30.00 | $0.50 | 400K | $750.00 | 2026-05-05 | |
| GPT-5.5 Pro | OpenAI | $30.00 | $180.00 | $15.00 / $90.00 | 1.05M | $4,500.00 | 2026-04-24 | |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | $0.50 | $2.50 / $15.00 | 1.05M | $750.00 | 2026-04-24 |
| GPT-5.4 Image 2 | OpenAI | $8.00 | $15.00 | $2.00 | 272K | $705.00 | 2026-04-21 | |
| Gemma 4 26B A4B free tier on OpenRouter | $0.0675 | $0.225 | $0.0375 | 262K | $7.42 | 2026-04-03 | ||
| Gemma 4 31B free tier on OpenRouter | $0.09 | $0.34 | $0.05 | 262K | $10.50 | 2026-04-02 | ||
| GPT-5.4 Nano | OpenAI | $0.20 | $1.25 | $0.02 | $0.10 / $0.625 | 400K | $30.75 | 2026-03-17 |
| GPT-5.4 Mini | OpenAI | $0.75 | $4.50 | $0.075 | $0.375 / $2.25 | 400K | $112.50 | 2026-03-17 |
| GPT-5.4 Pro | OpenAI | $30.00 | $180.00 | $15.00 / $90.00 | 1.05M | $4,500.00 | 2026-03-05 | |
| GPT-5.4 | OpenAI | $2.50 | $15.00 | $0.25 | $1.25 / $7.50 | 1.05M | $375.00 | 2026-03-05 |
| Gemini 3.1 Flash Lite Preview | $0.25 | $1.50 | $0.025 | 1.04858M | $37.50 | 2026-03-03 | ||
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.50 | $3.00 | 66K | $75.00 | 2026-02-26 | |||
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $12.00 | $0.20 | 1.04858M | $300.00 | 2026-02-25 | ||
| GPT-5.3-Codex | OpenAI | $1.75 | $14.00 | $0.175 | 400K | $315.00 | 2026-02-24 | |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | $0.20 | $1.00 / $6.00 | 1.04858M | $300.00 | 2026-02-19 | |
| GPT Audio | OpenAI | $2.50 | $10.00 | 128K | $300.00 | 2026-01-19 | ||
| GPT Audio Mini | OpenAI | $0.60 | $2.40 | 128K | $72.00 | 2026-01-19 | ||
| GPT-5.2-Codex | OpenAI | $1.75 | $14.00 | $0.175 | 400K | $315.00 | 2026-01-14 | |
| Gemini 3 Flash Preview | $0.50 | $3.00 | $0.05 | $0.25 / $1.50 | 1.04858M | $75.00 | 2025-12-17 | |
| GPT-5.2 Chat | OpenAI | $1.75 | $14.00 | $0.175 | 128K | $315.00 | 2025-12-10 | |
| GPT-5.2 Pro | OpenAI | $21.00 | $168.00 | $10.50 / $84.00 | 400K | $3,780.00 | 2025-12-10 | |
| GPT-5.2 | OpenAI | $1.75 | $14.00 | $0.175 | $0.875 / $7.00 | 400K | $315.00 | 2025-12-10 |
| GPT-5.1-Codex-Max | OpenAI | $1.25 | $10.00 | $0.125 | 400K | $225.00 | 2025-12-04 | |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $2.00 | $12.00 | $0.20 | 66K | $300.00 | 2025-11-20 | ||
| GPT-5.1 | OpenAI | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 | 400K | $225.00 | 2025-11-13 |
| GPT-5.1-Codex | OpenAI | $1.25 | $10.00 | $0.13 | 400K | $225.00 | 2025-11-13 | |
| GPT-5.1-Codex-Mini | OpenAI | $0.25 | $2.00 | $0.03 | 400K | $45.00 | 2025-11-13 | |
| gpt-oss-safeguard-20b | OpenAI | $0.075 | $0.30 | $0.0375 | 131K | $9.00 | 2025-10-29 | |
| GPT-5 Image Mini | OpenAI | $2.50 | $2.00 | $0.25 | 400K | $180.00 | 2025-10-16 | |
| GPT-5 Image | OpenAI | $10.00 | $10.00 | $1.25 | 400K | $750.00 | 2025-10-14 | |
| Nano Banana (Gemini 2.5 Flash Image) | $0.30 | $2.50 | $0.03 | 33K | $55.50 | 2025-10-07 | ||
| GPT-5 Pro | OpenAI | $15.00 | $120.00 | $7.50 / $60.00 | 400K | $2,700.00 | 2025-10-06 | |
| GPT-5 | OpenAI | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 | 400K | $225.00 | 2025-08-07 |
| GPT-5 Mini | OpenAI | $0.25 | $2.00 | $0.025 | $0.125 / $1.00 | 400K | $45.00 | 2025-08-07 |
| GPT-5 Nano | OpenAI | $0.05 | $0.40 | $0.005 | $0.025 / $0.20 | 400K | $9.00 | 2025-08-07 |
| gpt-oss-120b | OpenAI | $0.15 | $0.60 | $0.075 | $0.0296 / $0.136 | 131K | $18.00 | 2025-08-05 |
| gpt-oss-20b | OpenAI | $0.018 | $0.09 | $0.024 / $0.112 | 131K | $2.43 | 2025-08-05 | |
| Gemini 2.5 Flash Lite retiring 2026-10-20 | $0.10 | $0.40 | $0.01 | $0.05 / $0.20 | 1.04858M | $12.00 | 2025-07-22 | |
| Gemini 2.5 Flash retiring 2026-10-20 | $0.30 | $2.50 | $0.03 | $0.15 / $1.25 | 1.04858M | $55.50 | 2025-06-17 | |
| Gemini 2.5 Pro retiring 2026-10-20 | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 | 1.04858M | $225.00 | 2025-06-17 | |
| o3 Pro | OpenAI | $20.00 | $80.00 | 200K | $2,400.00 | 2025-06-10 | ||
| Gemini 2.5 Pro Preview 06-05 | $1.25 | $10.00 | $0.125 | 1.04858M | $225.00 | 2025-06-05 | ||
| o4 Mini High | OpenAI | $1.10 | $4.40 | $0.275 | 200K | $132.00 | 2025-04-16 | |
| o3 | OpenAI | $2.00 | $8.00 | $0.50 | $1.00 / $4.00 | 200K | $240.00 | 2025-04-16 |
| o4 Mini | OpenAI | $1.10 | $4.40 | $0.275 | $0.55 / $2.20 | 200K | $132.00 | 2025-04-16 |
| GPT-4.1 | OpenAI | $2.00 | $8.00 | $0.50 | $1.00 / $4.00 | 1.04758M | $240.00 | 2025-04-14 |
| GPT-4.1 Mini | OpenAI | $0.40 | $1.60 | $0.10 | $0.20 / $0.80 | 1.04758M | $48.00 | 2025-04-14 |
| GPT-4.1 Nano | OpenAI | $0.10 | $0.40 | $0.025 | $0.05 / $0.20 | 1.04758M | $12.00 | 2025-04-14 |
| o1-pro | OpenAI | $150.00 | $600.00 | 200K | $18,000.00 | 2025-03-19 | ||
| Gemma 3 4B | $0.05 | $0.10 | 131K | $4.50 | 2025-03-13 | |||
| Gemma 3 12B | $0.05 | $0.15 | 131K | $5.25 | 2025-03-13 | |||
| Gemma 3 27B | $0.08 | $0.45 | $0.04 | 131K | $11.55 | 2025-03-12 | ||
| o3 Mini High | OpenAI | $1.10 | $4.40 | $0.55 | 200K | $132.00 | 2025-02-12 | |
| o3 Mini | OpenAI | $1.10 | $4.40 | $0.55 | $0.55 / $2.20 | 200K | $132.00 | 2025-01-31 |
| o1 | OpenAI | $15.00 | $60.00 | $7.50 | 200K | $1,800.00 | 2024-12-17 | |
| GPT-4o (2024-11-20) | OpenAI | $2.50 | $10.00 | $1.25 | 128K | $300.00 | 2024-11-20 | |
| GPT-4o (2024-08-06) | OpenAI | $2.50 | $10.00 | $1.25 | 128K | $300.00 | 2024-08-06 | |
| GPT-4o-mini | OpenAI | $0.15 | $0.60 | $0.075 | $0.075 / $0.30 | 128K | $18.00 | 2024-07-18 |
| GPT-4o-mini (2024-07-18) | OpenAI | $0.15 | $0.60 | $0.075 | 128K | $18.00 | 2024-07-18 | |
| Gemma 2 27B | $0.65 | $0.65 | 8K | $48.75 | 2024-07-13 | |||
| GPT-4o | OpenAI | $2.50 | $10.00 | $1.25 | $1.25 / $5.00 | 128K | $300.00 | 2024-05-13 |
| GPT-4o (2024-05-13) | OpenAI | $5.00 | $15.00 | 128K | $525.00 | 2024-05-13 | ||
| GPT-4 Turbo | OpenAI | $10.00 | $30.00 | $5.00 / $15.00 | 128K | $1,050.00 | 2024-04-09 | |
| GPT-3.5 Turbo (older v0613) | OpenAI | $1.00 | $2.00 | 4K | $90.00 | 2024-01-25 | ||
| GPT-3.5 Turbo Instruct | OpenAI | $1.50 | $2.00 | 4K | $120.00 | 2023-09-28 | ||
| GPT-3.5 Turbo 16k | OpenAI | $3.00 | $4.00 | 16K | $240.00 | 2023-08-28 | ||
| GPT-3.5 Turbo | OpenAI | $0.50 | $1.50 | $0.25 / $0.75 | 16K | $52.50 | 2023-05-28 | |
| GPT-4 | OpenAI | $30.00 | $60.00 | 8K | $2,700.00 | 2023-05-28 |
All Gemini prices . All GPT prices . Every provider
Common questions
Is Gemini cheaper than GPT?
On 25 September 2026, the median Gemini model on this list costs $0.50 per million input tokens and $2.75 per million output tokens, against $1.75 and $10.00 for GPT. By that measure Gemini is cheaper, but compare the specific models you would use, since both providers sell models at very different price points.
What is the cheapest Gemini model compared with the cheapest GPT model?
The cheapest Gemini model is Gemma 3 4B at $0.05 in and $0.10 out per million tokens. The cheapest GPT model is gpt-oss-20b at $0.018 in and $0.09 out.
Which has the larger context window, Gemini or GPT?
The largest Gemini context on this list is 1.04858M tokens (Gemini 3.8 Flash) and the largest GPT context is 1.05M tokens (GPT-6 Luna Pro).
How should I choose between Gemini and GPT for a production agent?
Price per token is one input. Run both on a set of your own real cases, count how often each needs a retry or a human check, and compare the total cost of a correct answer rather than the cost of a token.
Choosing a model for a production agent
Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.