OpenAI vs Google Vertex AI Pricing
Per-million-token pricing for OpenAI and Google Vertex AI, with side-by-side flagship models, cheapest tiers, and context windows. Pricing data syncs weekly from the open-source litellm catalog — last updated May 4, 2026.
Who wins on what
Cheapest input tokens
$0.02/1MGoogle Vertex AI
Gemma 3 4B — $0.02/1M input
Cheapest output tokens
$0.04/1MGoogle Vertex AI
Gemma 3n 4B — $0.04/1M output
Longest context window
2.0MOpenAI
gpt-5.4 (>272K context length) — 2.0M input tokens
Lowest average output cost
$3.98/1MGoogle Vertex AI
Provider-wide average across 48 models
Largest model catalog
153 modelsOpenAI
More options to match cost vs capability
Side-by-side
OpenAI
Cheapest input
$0.030
gpt-oss-20b
Cheapest output
$0.140
gpt-oss-20b
Longest context
2.0M
gpt-5.4 (>272K context length)
Avg output / 1M
$23.87
Across catalog
| Model | In/1M | Out/1M | Ctx |
|---|---|---|---|
| o1-pro | $150.00 | $600.00 | 200K |
| gpt-5.4-pro (>272K context length) | $60.00 | $270.00 | 2.0M |
| gpt-5.5-pro (>272K context length) | $60.00 | $270.00 | 2.0M |
| gpt-5.4-pro (<272K context length) | $30.00 | $180.00 | 272K |
| gpt-5.5-pro (<272K context length) | $30.00 | $180.00 | 272K |
| gpt-oss-20b | $0.030 | $0.140 | 131K |
Google Vertex AI
Cheapest input
$0.017
Gemma 3 4B
Cheapest output
$0.040
Gemma 3n 4B
Longest context
2.0M
Gemini 3/3.1 (> 200k context)
Avg output / 1M
$3.98
Across catalog
| Model | In/1M | Out/1M | Ctx |
|---|---|---|---|
| Gemini 3/3.1 (> 200k context) | $4.00 | $18.00 | 2.0M |
| Gemini 3 Pro Preview | $2.00 | $12.00 | 1.0M |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1.0M |
| Gemini 3.1 Pro Preview Customtools | $2.00 | $12.00 | 1.0M |
| Gemini 3/3.1 (≤ 200k context) | $2.00 | $12.00 | 200K |
| Gemma 3n 4B | $0.020 | $0.040 | 33K |
All prices in USD per 1 million tokens. Showing top 6 models per provider, sorted by output cost.
Run the numbers for your workload
Calcaas multiplies per-token costs by your real usage patterns — inputs, outputs, retries, and conversation history — across both providers in one model.