Googleopen weightsGemma 3 12B pricing
$0.05 per 1M input tokens and $0.15 per 1M output tokens. In real work that is 0.02¢ per chat answer and 0.08¢ to summarize a 20-page PDF.
What Gemma 3 12B costs per task
Token counts estimated from a measured model of the same lab (Gemini 3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.02¢$0.25 / 1,000 | 35 in · 788 out · 843 reasoning | 22 of 336 | estimated |
| Reply to a customer email | <0.01¢$0.10 / 1,000 | 271 in · 128 out · 424 reasoning | 20 of 336 | estimated |
| Write a 1,500-word blog post | 0.05¢$0.54 / 1,000 | 52 in · 2,621 out · 964 reasoning | 9 of 336 | estimated |
| Write 10 product descriptions | 0.05¢$0.46 / 1,000 | 293 in · 1,127 out · 1,817 reasoning | 13 of 336 | estimated |
| Translate 1,000 words | 0.07¢$0.73 / 1,000 | 1,308 in · 1,297 out · 3,167 reasoning | 50 of 336 | estimated |
| Proofread one page (500 words) | 0.02¢$0.20 / 1,000 | 706 in · 653 out · 443 reasoning | 10 of 336 | estimated |
| Summarize a 20-page PDF | 0.08¢$0.82 / 1,000 | 12,741 in · 535 out · 713 reasoning | 14 of 336 | estimated |
| Extract data from an invoice | 0.02¢$0.24 / 1,000 | 452 in · 539 out · 943 reasoning | 13 of 336 | estimated |
| Analyze a 200-row spreadsheet | 0.15¢$1.53 / 1,000 | 6,304 in · 1,018 out · 7,100 reasoning | 9 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.05¢$0.51 / 1,000 | 3,608 in · 669 out · 1,499 reasoning | 16 of 336 | estimated |
| Classify 100 support tickets | 0.11¢$1.06 / 1,000 | 1,397 in · 571 out · 6,059 reasoning | 34 of 336 | estimated |
| Review 500 lines of code | 0.06¢$0.57 / 1,000 | 5,207 in · 2,074 out | 6 of 336 | estimated |
| Write a SQL query | 0.02¢$0.25 / 1,000 | 135 in · 546 out · 1,043 reasoning | 12 of 336 | estimated |
| Run a 50-step coding agent | 12¢$119 / 1,000 | 2,194,987 in · 14,715 out · 47,150 reasoning | 69 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Gemma 3 12B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrabf16 | $0.04 / $0.12 | - | 131K | |
| N NextBitint4 | $0.05 / $0.15 | - | 131K | 100% |
DeepInfrabf16 | $0.05 / $0.15 | - | 131K | 100% |
DeepInfrabf16 | $0.075 / $0.23 | - | 131K | 100% |
Price history
First seen in our price history on Apr 3, 2025 at $0.05 input / $0.10 output. Since then the output price moved from $0.10 to $0.15 per 1M tokens (8 changes).
FAQ
How much does Gemma 3 12B cost?
Gemma 3 12B costs $0.05 per 1 million input tokens and $0.15 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.02¢ and summarizing a 20-page PDF about 0.08¢.
Where is Gemma 3 12B cheapest?
Among 4 providers we track, the lowest list price today is at DeepInfra: $0.04 input and $0.12 output per 1M tokens.
Is the Gemma 3 12B cost per task measured or estimated?
Estimated: Gemma 3 12B was not run directly. Tokens come from Gemini 3.8 Flash and are rescaled by the tokenizer of Google. Real usage can differ.