Google Vertex AI vs DeepSeek Pricing
Google Vertex AI is cheaper than DeepSeek at the entry level: Gemma 3n 4B costs $0.040 per 1M output tokens against $0.100 for DeepSeek R1 0528 Qwen3 8B — 2.5× the price. On current flagships, Google Vertex AI's Nano Banana 2 Lite costs $30.00/1M output against $2.19/1M for DeepSeek's DeepSeek R1. Prices are USD, current as of August 11, 2026.
Per-million-token pricing for Google Vertex AI and DeepSeek, with side-by-side flagship models, cheapest tiers, and context windows. Pricing data syncs weekly from a continuously-updated model catalog — last updated August 11, 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
2.0MGoogle Vertex AI
Gemini 3/3.1 (> 200k context) — 2.0M input tokens
Lowest average output cost
$0.79/1MDeepSeek
Provider-wide average across 21 models
Largest model catalog
59 modelsGoogle Vertex AI
More options to match cost vs capability
Cheapest cached input
$0.00/1MDeepSeek
DeepSeek Chat — $0.00/1M cached read
Most reasoning models
18 modelsGoogle Vertex AI
Models with dedicated reasoning / thinking support
Most vision models
18 modelsGoogle Vertex AI
Models that accept image input
Open-weights available
YesDeepSeek
Offers open-weight models you can self-host
Side-by-side
Google Vertex AI
Full Google Vertex AI pricing →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
$9.45
Across catalog
Cheapest cached input
$0.025
Gemini 3.1 Flash Lite
| Model | In/1M | Out/1M | Ctx |
|---|---|---|---|
| Gemini 3.6 Flash VisionReasoningToolsCache | $1.50 | $7.50 | 1.0M |
| Gemini 3.5 Flash Lite VisionReasoningToolsCache | $0.300 | $2.50 | 1.0M |
| Nano Banana 2 Lite VisionReasoningTools | $0.250 | $30.00 | 66K |
| Gemini 3.5 Live Translate Preview | $3.50 | $21.00 | 16K |
| Gemini 3.5 Flash VisionReasoningToolsCache | $1.50 | $9.00 | 1.0M |
| Gemma 3n 4B | $0.020 | $0.040 | 33K |
DeepSeek
Full DeepSeek pricing →Cheapest input
$0.020
DeepSeek R1 0528 Qwen3 8B
Cheapest output
$0.100
DeepSeek R1 0528 Qwen3 8B
Longest context
1.0M
DeepSeek Chat
Avg output / 1M
$0.790
Across catalog
Cheapest cached input
$0.0028
DeepSeek Chat
| Model | In/1M | Out/1M | Ctx |
|---|---|---|---|
| DeepSeek V4 Flash ReasoningToolsCache | $0.140 | $0.280 | 1.0M |
| DeepSeek V4 Pro ReasoningToolsCache | $0.435 | $0.870 | 1.0M |
| DeepSeek Chat ToolsCache | $0.140 | $0.280 | 1.0M |
| DeepSeek Reasoner ReasoningToolsCache | $0.140 | $0.280 | 1.0M |
| DeepSeek R1 | $0.550 | $2.19 | 66K |
| DeepSeek R1 0528 Qwen3 8B | $0.020 | $0.100 | 33K |
All prices in USD per 1 million tokens. Showing top 6 models per provider, sorted by output cost.
Frequently asked questions
Is Google Vertex AI or DeepSeek cheaper?
Google Vertex AI has the cheaper entry point at $0.04/1M output (Gemma 3n 4B — $0.04/1M output). Provider-wide, Google Vertex AI averages $9.45/1M output against $0.790/1M for DeepSeek. Which is cheaper for you depends on which model tier your workload actually needs.
How much do Google Vertex AI and DeepSeek cost per 1M tokens?
Google Vertex AI starts at $0.040 per 1M output tokens (Gemma 3n 4B), with its current flagship Nano Banana 2 Lite at $30.00. DeepSeek starts at $0.100 (DeepSeek R1 0528 Qwen3 8B), with DeepSeek R1 at $2.19. Input tokens cost less than output on both.
Which has the larger context window, Google Vertex AI or DeepSeek?
Google Vertex AI — Gemini 3/3.1 (> 200k context) — 2.0M input tokens. For comparison, Google Vertex AI's largest is 2.0M tokens (Gemini 3/3.1 (> 200k context)) and DeepSeek's is 1.0M tokens (DeepSeek Chat).
Which has more reasoning models, Google Vertex AI or DeepSeek?
Google Vertex AI lists 18 reasoning models and DeepSeek lists 3. Reasoning models bill their internal thinking as output tokens, so a reasoning call costs several times a standard completion of the same visible length — compare them on total tokens billed, not headline rate.
Can I self-host Google Vertex AI or DeepSeek models?
DeepSeek publishes open-weight models you can run on your own hardware; Google Vertex AI does not. Self-hosting swaps per-token pricing for GPU-hour cost, which usually only wins above sustained high utilisation — below that, hosted inference is cheaper.
Should I switch from Google Vertex AI to DeepSeek to save money?
Only if the cheaper model still meets your quality bar. Token price is one input; the ones that decide your bill are prompt size, response length, retries and how much conversation history you resend each turn. Model the switch against your real traffic before committing. Prices here are current as of August 11, 2026.
Related comparisons
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.