GooglereasoningGemini 3.8 Flash pricing
$0.82 per 1M input tokens and $4.12 per 1M output tokens. In real work that is 0.68¢ per chat answer and 1.6¢ to summarize a 20-page PDF.
Official price at Google (Gemini API): $0.75 / $3.75 per 1M, cached $0.075 (source, verified Oct 18, 2026). OpenRouter lists $0.82 / $4.12, which is the cheapest route across its hosts - higher than the official price.
What Gemini 3.8 Flash costs per task
Every row below was measured: we ran the task on this model and counted the tokens. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.68¢$6.76 / 1,000 | 35 in · 788 out · 843 reasoning | 251 of 336 | measured |
| Reply to a customer email | 0.25¢$2.50 / 1,000 | 271 in · 128 out · 424 reasoning | 244 of 336 | measured |
| Write a 1,500-word blog post | 1.5¢$14.83 / 1,000 | 52 in · 2,621 out · 964 reasoning | 209 of 336 | measured |
| Write 10 product descriptions | 1.2¢$12.39 / 1,000 | 293 in · 1,127 out · 1,817 reasoning | 228 of 336 | measured |
| Translate 1,000 words | 1.9¢$19.49 / 1,000 | 1,308 in · 1,297 out · 3,167 reasoning | 240 of 336 | measured |
| Proofread one page (500 words) | 0.51¢$5.10 / 1,000 | 706 in · 653 out · 443 reasoning | 224 of 336 | measured |
| Summarize a 20-page PDF | 1.6¢$15.66 / 1,000 | 12,741 in · 535 out · 713 reasoning | 226 of 336 | measured |
| Extract data from an invoice | 0.65¢$6.49 / 1,000 | 452 in · 539 out · 943 reasoning | 253 of 336 | measured |
| Analyze a 200-row spreadsheet | 3.9¢$38.69 / 1,000 | 6,304 in · 1,018 out · 7,100 reasoning | 218 of 336 | measured |
| Answer from 5 retrieved documents (RAG) | 1.2¢$11.92 / 1,000 | 3,608 in · 669 out · 1,499 reasoning | 253 of 336 | measured |
| Classify 100 support tickets | 2.9¢$28.50 / 1,000 | 1,397 in · 571 out · 6,059 reasoning | 285 of 336 | measured |
| Review 500 lines of code | 1.3¢$12.85 / 1,000 | 5,207 in · 2,074 out | 171 of 336 | measured |
| Write a SQL query | 0.67¢$6.67 / 1,000 | 135 in · 546 out · 1,043 reasoning | 251 of 336 | measured |
| Run a 50-step coding agent | 50¢$496 / 1,000 | 2,194,987 in · 14,715 out · 47,150 reasoning | 170 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Gemini 3.8 Flash through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
Google AI Studiounknown | $0.38 / $1.88 | $0.037 | 1M | 100% |
Googleunknown | $0.38 / $1.88 | $0.037 | 1M | 100% |
Google AI Studiounknown | $0.75 / $3.75 | $0.075 | 1M | 100% |
Googleunknown | $0.75 / $3.75 | $0.075 | 1M | 93% |
Googleunknown | $0.82 / $4.12 | $0.083 | 1M | 100% |
Google AI Studiounknown | $1.35 / $6.75 | $0.14 | 1M | 100% |
Googleunknown | $1.35 / $6.75 | $0.14 | 1M | 80% |
Price history
First seen in our price history on Sep 7, 2026 at $0.75 input / $3.75 output. Since then the output price moved from $3.75 to $4.12 per 1M tokens (1 change).
FAQ
How much does Gemini 3.8 Flash cost?
Gemini 3.8 Flash costs $0.82 per 1 million input tokens and $4.12 per 1 million output tokens, with cached input at $0.083 (list price on Oct 18, 2026). In practice one chat answer costs about 0.68¢ and summarizing a 20-page PDF about 1.6¢.
Where is Gemini 3.8 Flash cheapest?
Among 7 providers we track, the lowest list price today is at Google AI Studio: $0.38 input and $1.88 output per 1M tokens.
Does Gemini 3.8 Flash charge for reasoning tokens?
Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.
Is the Gemini 3.8 Flash cost per task measured or estimated?
Measured: we ran all 13 benchmark prompts on Gemini 3.8 Flash through OpenRouter and recorded the tokens it used.