Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
gemini-3.8-flashReleased 2 Sep 2026 (Sep 2026)Pricing
List prices at Google AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.75 | $3.75 | |
| Cached input 90% off input | $0.075 | 90% off input | |
| Batch 50% off | $0.375 | $1.88 | 50% off |
| Flex 50% off | $0.375 | $1.88 | 50% off |
| Priority 80% more | $1.35 | $6.75 | 80% more |
| Web search $14.00 per 1,000 searches | $14.00 per 1,000 searches |
What it costs a month
At Google AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$446
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$333
- Coding agent1,000 requests a day, 40K in / 2K out, cached$558
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$1,350
Where to run it
6 hosts serve Gemini 3.8 Flash. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Google AI StudioLab API gemini-3.8-flash | $0.75 / $3.75 | gemini-3.8-flash | |
Vertex AICloud gemini-3.8-flash | $0.75 / $3.75 | gemini-3.8-flash | |
DatabricksCloud databricks-gemini-3-8-flash | $0.75 / $3.75 | databricks-gemini-3-8-flash | |
GMI CloudInference gemini-3.8-flash | $0.75 / $3.75 | gemini-3.8-flash | |
PerplexityGateway gemini-3.8-flash | $0.75 / $3.75 | gemini-3.8-flash | |
Kyma APICloud gemini-3.8-flash | $2.03 / $10.13 +170% vs headline | gemini-3.8-flash | |
GitHub CopilotSubscription gemini-3.8-flash | In the subscription Retires 14 Dec 2026 | gemini-3.8-flash | Retires 14 Dec 2026 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Vertex AI | |||||||
| Alias gemini-3.8-flash | $0.75 / $3.75 | gemini-3.8-flash | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- AudioImagesTextVideoPDFs
- Produces
- Text
- Features
- Audio inputComputer useParallel tool callsPDF inputPrompt cachingURL contextVideo inputBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Google AI Studio.
Smaller Google models
- 43% less
Other frontier labs
- 17% less
- 69% less
- 87% less
- 87% less
Open-weight picks
- 54% less
- 57% less
- 65% less
- 68% less
Model line
Newer and older versions, at each lab's own price.
- Sep 2026Gemini 3.8 FlashLatest$0.75 / $3.75
- Aug 2026Gemini 3.7 Flash$0.75 / $3.75
- Jul 2026Gemini 3.6 Flash$0.75 / $3.75
- May 2026Gemini 3.5 Flash$1.50 / $9.00
- UndatedGemini 3 Flash$0.50 / $3.00
- Jun 2025Gemini 2.5 Flash$0.30 / $2.50
- UndatedGemini 2.0 Flash$0.15 / $0.60
Call it
Using Google AI Studio's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="gemini-3.8-flash", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="gemini/gemini-3.8-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemini 3.8 Flash cost?
On Google AI Studio, Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens. Cached input costs $0.075 per million tokens.
Which APIs offer Gemini 3.8 Flash?
Gemini 3.8 Flash runs on 6 APIs: Google AI Studio, Vertex AI, Databricks, GMI Cloud, Perplexity and Kyma API.
What is Gemini 3.8 Flash's context window?
1M tokens, with up to 66K tokens in one reply.
Is Gemini 3.8 Flash being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Gemini 3.8 Flash?
No. Gemini 3.8 Flash is the newest model in its line.
What are cheaper alternatives to Gemini 3.8 Flash?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (43% less), Grok Build 0.1 on xAI (17% less), GPT-5.4 Nano on OpenAI (69% less) and Kimi K2.7 Code on CLF AI Gateway (54% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Gemini 3.8 Flash released?
Google released it on 2 Sep 2026.
What is Gemini 3.8 Flash's API model id?
Use gemini-3.8-flash with Google AI Studio. Other hosts use their own ids: databricks-gemini-3-8-flash on Databricks.
Sources
- Databricks pricing
- Google AI Studio pricing
- GitHub Copilot pricing
- GMI Cloud pricing
- Perplexity pricing
- Vertex AI pricing
- LiteLLM model map
Raw catalog entry for gemini-3.8-flash on Google AI Studio
{
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-8,
"cache_read_input_token_cost_batches": 3.75e-8,
"cache_read_input_token_cost_flex": 3.75e-8,
"input_cost_per_token": 7.5e-7,
"input_cost_per_token_batches": 3.75e-7,
"input_cost_per_token_flex": 3.75e-7,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 0.00000375,
"output_cost_per_token": 0.00000375,
"output_cost_per_token_batches": 0.000001875,
"output_cost_per_token_flex": 0.000001875,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_logprobs": false,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_minimal_reasoning_effort": false,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 800000,
"input_cost_per_token_priority": 0.00000135,
"output_cost_per_token_priority": 0.00000675,
"cache_read_input_token_cost_priority": 1.35e-7,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"search_free_requests": {
"count": 5000,
"period": "month",
"shared_group": "gemini-3"
},
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014,
"supports_computer_use": true
}