Google Gemini 3.8 Flash API Pricing and Speed
Google Gemini 3.8 Flash API pricing: $0.75 per 1M tokens for input and $3.75 per 1M tokens for output, from the official API price list of Google Gemini API. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.83 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · no price change seen since 16 Oct 2026.
Quality on your task: not measured by Measured Lab yet. On our data, Gemini 3.8 Flash fits 6 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $15.94 for 5,000 customer messages a month
- Calculated Pull data from invoices and documents with strict JSON and page images: $6.00 for 2,000 documents a month
- Calculated Summarize documents and meetings: $7.35 for 1,000 documents or meetings a month
- Calculated Translate content: $12.38 for 3,000 pages a month
- Calculated Chat assistant on your website: $156.38 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $44.06 for 500 coding tasks a month
What our data confirms
- Observed Strict JSON output: accepted in our test call on 17 Oct 2026
- Published Calls your tools, in Google documentation, read 17 Oct 2026
- Published Reads images; OpenRouter listing, 9 Nov 2026
Example to try
“Review this pull request and list bugs and missing tests, with the file and line of each.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 7.0 s, 200 tokens/s (median of 95 test requests on 19 dates, short request)
- Observed Hidden reasoning: 976 tokens on that request, billed as output
Stated by the provider
- Stated by the provider Google for this model: DeepSWE v1.1 73.7%, Terminal-Bench 2.1 89.4%, Terminal-Bench 4.0 19.1%; quotes and test conditions in Quality signals
Before you choose
- Published Training on your data, per Google Gemini API Additional Terms of Service: depends on plan — Unpaid Services: used to improve products, with human review; Paid Services: not used, read 2 Nov 2026
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $0.75Input per 1M tokens, from Google Gemini API Published
- $3.75Output per 1M tokens, from Google Gemini API Published
- $0.075Cached input per 1M tokens, from Google Gemini API Published
All prices by channel
| Price per 1M tokens | Google Gemini API direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.75 Published | $0.825 Published | — |
| Output | $3.75 Published | $4.125 Published | — |
| Cached input · read | $0.075 Published | $0.0825 Published | — |
| Cache write | UnknownUnknown | $0.041667 Published | — |
| Cache storage · per hour | $0.50 Published | — | — |
| Batch · input / output | — | $0.375 / $1.875 Published | — |
Input price from Google Gemini API, 16 Oct 2026 – 2 Nov 2026
16 Oct 2026$0.75 throughout2 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.825 throughout9 Nov 2026
Context window1,048,576tokens Published
Max output65,536tokens Published
OpenRouter providers who serves this model through OpenRouter, at what price
OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.
Pinned min: $0.375 / $1.875 · Google AI Studio (google-ai-studio/flex)
Unpinned range: input $0.375–$1.35, output $1.875–$6.75 across 7 endpoints of 2 providers.
Models with the widest provider price spread on OpenRouter
Request fragment that pins Google AI Studio (google-ai-studio/flex):
{"provider": {"order": ["google-ai-studio/flex"], "allow_fallbacks": false}}With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).
All endpoints (7), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
google-vertex/global/flex | Not stated | $0.375 | $1.875 | 1,048,576 | |
| Google AI Studio | google-ai-studio/flex | Not stated | $0.375 | $1.875 | 1,048,576 |
google-vertex/global | Not stated | $0.75 | $3.75 | 1,048,576 | |
| Google AI Studio | google-ai-studio | Not stated | $0.75 | $3.75 | 1,048,576 |
google-vertex/us | Not stated | $0.825 | $4.125 | 1,048,576 | |
google-vertex/global/priority | Not stated | $1.35 | $6.75 | 1,048,576 | |
| Google AI Studio | google-ai-studio/priority | Not stated | $1.35 | $6.75 | 1,048,576 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Googlereasoning: low95 answers on 19 dates · 100 % answered | 6.96 srange 1.02–10.51 s · slow 10 %: 9.21 s Observed | 200 tokens/srange 103–365 · slowest 10 %: 126 tokens/s | $0.0036range $0.000535–$0.0041 Calculated | 976for 72 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Googlereasoning: low85 answers on 17 dates · 100 % answered | 6.95 srange 1.08–11.47 s · slow 10 %: 9.15 s Observed | 205 tokens/srange 107–369 · slowest 10 %: 134 tokens/s | $0.00324range $0.000535–$0.0041 Calculated | 814for 74 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Googlereasoning: low85 answers on 17 dates · 100 % answered | 8.09 srange 1.36–10.93 s · slow 10 %: 9.42 s Observed | 206 tokens/srange 87.0–366 · slowest 10 %: 122 tokens/s | $0.00394range $0.000546–$0.0041 Calculated | 979for 70 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Googlereasoning: low85 answers on 17 dates · 100 % answered | 7.93 srange 1.43–12.28 s · slow 10 %: 9.36 s Observed | 200 tokens/srange 114–368 · slowest 10 %: 131 tokens/s | $0.00385range $0.000545–$0.0041 Calculated | 961for 72 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · Googlereasoning: low85 answers on 17 dates · 100 % answered | 7.63 srange 1.66–10.71 s · slow 10 %: 9.38 s Observed | 150 tokens/srange 95.9–275 · slowest 10 %: 111 tokens/s | $0.00338range $0.000548–$0.0041 Calculated | 847for 74 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
| Signal | Result | Source |
|---|---|---|
| Instruction followingIFEval, 50 prompts · reasoning: low | 98 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code98 % on 22 Oct 2026 · 98 % on 17 Oct 2026 · instruction level 99 % |
Figures the provider publishes (6)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| DeepSWE v1.1 | 73.7% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
| Terminal-Bench 2.1 | 89.4% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
| Terminal-Bench 4.0 | 19.1% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
| Humanity's Last Exam (HLE-Verified) | 54.9% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
| OSWorld 2.0 | 59.0% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
| CharXiv Reasoning | 86.2% Stated by the provider | Results table in Gemini 3.8 Flash - Model Card — Google DeepMindread 17 Oct 2026 |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
What typical tasks cost with this model
| Task | At Google Gemini API's price (Unknown) | Through OpenRouter ($0.825 / $4.125) |
|---|---|---|
| 1,000 chat replies | Unknown | $2.06 |
| Summarizing 100 documents | Unknown | $0.50 |
| A day of coding assistant use | Unknown | $1.65 |
Calculated Prices per 1M tokens (input / output) in brackets; token counts and what is not included: our assumptions and the same tasks on other models.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 16 Oct 2026
- Shown in: the United States
- Checks so far: 25 checks since 16 Oct 2026
- What changed: no price change since 16 Oct 2026
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does Gemini 3.8 Flash cost per 1M cache-read tokens (cache hits) directly from Google Gemini API (official API price)? | Unknown | Unknown | |
| How much does Gemini 3.8 Flash cost per 1M input tokens directly from Google Gemini API (official API price)? | Unknown | Unknown | |
| How much does Gemini 3.8 Flash cost per 1M output tokens directly from Google Gemini API (official API price)? | Unknown | Unknown | |
| How much does Gemini 3.8 Flash cost to keep 1M tokens in its cache for one hour directly from Google Gemini API (official API price)? | Unknown | Unknown | |
| How much does Google Gemini 3.8 Flash cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.08 per 1M tokens | Published | |
| How much does Google Gemini 3.8 Flash cost per 1M cache-write tokens on OpenRouter? | $0.04 per 1M tokens | Published | |
| How much does Google Gemini 3.8 Flash cost per 1M output tokens on OpenRouter? | $4.13 per 1M tokens | Published | |
| What is the context window of Google Gemini 3.8 Flash on OpenRouter, in tokens? | 1,048,576 tokens | Published | |
| What is the maximum output length of Google Gemini 3.8 Flash on OpenRouter, in tokens? | 65,536 tokens | Published |
History
Same price in all 25 checks since 16 Oct 2026.
- — First check: $0.83 per 1M tokens
The source record lists $0.00000083 per token ($0.83 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.000000825"
Latest briefings each price change recalculated as a task cost
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Record history — 224 records for 10 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.83 per 1M tokens | Published |
| 8 Nov 2026 | $0.83 per 1M tokens | Published |
| 7 Nov 2026 | $0.83 per 1M tokens | Published |
| 6 Nov 2026 | $0.83 per 1M tokens | Published |
| 5 Nov 2026 | $0.83 per 1M tokens | Published |
| 4 Nov 2026 | $0.83 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | Unknown | Unknown |
| 4 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | Unknown | Unknown |
| 4 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | Unknown | Unknown |
| 4 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | Unknown | Unknown |
| 4 Nov 2026 | Unknown | Unknown |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.08 per 1M tokens | Published |
| 8 Nov 2026 | $0.08 per 1M tokens | Published |
| 7 Nov 2026 | $0.08 per 1M tokens | Published |
| 6 Nov 2026 | $0.08 per 1M tokens | Published |
| 5 Nov 2026 | $0.08 per 1M tokens | Published |
| 4 Nov 2026 | $0.08 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.04 per 1M tokens | Published |
| 8 Nov 2026 | $0.04 per 1M tokens | Published |
| 7 Nov 2026 | $0.04 per 1M tokens | Published |
| 6 Nov 2026 | $0.04 per 1M tokens | Published |
| 5 Nov 2026 | $0.04 per 1M tokens | Published |
| 4 Nov 2026 | $0.04 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $4.13 per 1M tokens | Published |
| 8 Nov 2026 | $4.13 per 1M tokens | Published |
| 7 Nov 2026 | $4.13 per 1M tokens | Published |
| 6 Nov 2026 | $4.13 per 1M tokens | Published |
| 5 Nov 2026 | $4.13 per 1M tokens | Published |
| 4 Nov 2026 | $4.13 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 1,048,576 tokens | Published |
| 8 Nov 2026 | 1,048,576 tokens | Published |
| 7 Nov 2026 | 1,048,576 tokens | Published |
| 6 Nov 2026 | 1,048,576 tokens | Published |
| 5 Nov 2026 | 1,048,576 tokens | Published |
| 4 Nov 2026 | 1,048,576 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 65,536 tokens | Published |
| 8 Nov 2026 | 65,536 tokens | Published |
| 7 Nov 2026 | 65,536 tokens | Published |
| 6 Nov 2026 | 65,536 tokens | Published |
| 5 Nov 2026 | 65,536 tokens | Published |
| 4 Nov 2026 | 65,536 tokens | Published |
Showing the latest 60 of 224 records; the full history is in data.json and data.csv.