impulse

Gemini 2.5 Flash

Frontier labRetiring 1 Dec 2026

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.

API id gemini-2.5-flashReleased 17 Jun 2025 (Jun 2025)
A newer model in this line is out: Gemini 3.8 Flash, released 2 Sep 2026.
Google AI Studio retires it on 1 Dec 2026 (in 12 days). 8 hosts keep serving it.
Input / 1M
$0.30
at Google AI Studio
Output / 1M
$2.50
at Google AI Studio
Context window
1M
tokens
Max output
66K
tokens per reply
Hosts
9
9 listings
Released
Jun 2025
17 Jun 2025

Pricing

List prices at Google AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.30$2.50
Cached input
90% off input
$0.03
Batch
50% off
$0.15$1.25
Flex
50% off
$0.15$1.25
Priority
80% more
$0.54$4.50
Web search
$35.00 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$253
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$169
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$283
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$660
Use your own numbers

Where to run it

9 hosts serve Gemini 2.5 Flash. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gemini-2.5-flash
$0.30 / $2.50
Retires 1 Dec 2026
gemini-2.5-flash
$0.30 / $2.50
google.gemini-2.5-flash
$0.15 / $0.60
−69% vs headline
DeepInfraInference
gemini-2.5-flash
$0.30 / $2.50
ReplicateInference
gemini-2.5-flash
$0.30 / $2.50
gemini-2.5-flash
$0.30 / $2.50
databricks-gemini-2-5-flash
$0.30 / $2.50
gemini_2.5_flash
-
PerplexityGateway
gemini-2.5-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 inputParallel tool callsPDF inputPrompt cachingURL contextBuilt-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

  • Oracle OCI
    google.gemini-2.5-flash
    $0.15 / $0.60
    69% less

Smaller Google models

No cheaper Google model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    46% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    76% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    76% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    69% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    19% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    25% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    38% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    43% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026Gemini 3.8 FlashLatest$0.75 / $3.75
  2. Aug 2026Gemini 3.7 Flash$0.75 / $3.75
  3. Jul 2026Gemini 3.6 Flash$0.75 / $3.75
  4. May 2026Gemini 3.5 Flash$1.50 / $9.00
  5. UndatedGemini 3 Flash$0.50 / $3.00
  6. Jun 2025Gemini 2.5 FlashThis page$0.30 / $2.50
  7. UndatedGemini 2.0 Flash$0.15 / $0.60

Call it

Using Google AI Studio's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-2.5-flash", contents="Hello")
print(response.text)

Quick answers

How much does Gemini 2.5 Flash cost?

On Google AI Studio, Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens. Cached input costs $0.03 per million tokens. The cheapest host is Oracle OCI, at $0.15 per million input tokens and $0.60 per million output tokens.

Which APIs offer Gemini 2.5 Flash?

Gemini 2.5 Flash runs on 9 APIs: Google AI Studio, Vertex AI, Oracle OCI, DeepInfra, Replicate, Vercel AI Gateway, Databricks, RunwayML and Perplexity.

What is Gemini 2.5 Flash's context window?

1M tokens, with up to 66K tokens in one reply.

Is Gemini 2.5 Flash being retired?

Google AI Studio retires it on 1 Dec 2026. 8 hosts keep serving it.

Is there a newer version of Gemini 2.5 Flash?

Yes. Gemini 3.8 Flash is the newest model in this line, released on 2 Sep 2026.

What are cheaper alternatives to Gemini 2.5 Flash?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (46% less), Claude Haiku 5.5 on Anthropic (76% less) and Kimi K2.7 Code on CLF AI Gateway (19% less). Gemini 2.5 Flash itself costs 69% less on Oracle OCI. Savings are on a mix of 3 input tokens to 1 output token.

When was Gemini 2.5 Flash released?

Google released it on 17 Jun 2025.

What is Gemini 2.5 Flash's API model id?

Use gemini-2.5-flash with Google AI Studio. Other hosts use their own ids: google.gemini-2.5-flash on Oracle OCI, databricks-gemini-2-5-flash on Databricks, gemini_2.5_flash on RunwayML.

Sources

Raw catalog entry for gemini-2.5-flash on Google AI Studio
{
  "cache_read_input_audio_token_cost": 1e-7,
  "cache_read_input_audio_token_cost_batches": 1e-7,
  "cache_read_input_audio_token_cost_flex": 1e-7,
  "cache_read_input_audio_token_cost_priority": 1.8e-7,
  "cache_read_input_token_cost": 3e-8,
  "cache_read_input_token_cost_batches": 3e-8,
  "cache_read_input_token_cost_flex": 3e-8,
  "cache_read_input_token_cost_priority": 5.4e-8,
  "deprecation_date": "2026-12-01",
  "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations",
  "successor_model": "gemini/gemini-3.5-flash-lite",
  "input_cost_per_audio_token": 0.000001,
  "input_cost_per_audio_token_flex": 5e-7,
  "input_cost_per_token": 3e-7,
  "litellm_provider": "gemini",
  "max_input_tokens": 1048576,
  "max_output_tokens": 65536,
  "mode": "chat",
  "output_cost_per_reasoning_token": 0.0000025,
  "output_cost_per_token": 0.0000025,
  "rpm": 100000,
  "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_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_url_context": true,
  "supports_vision": true,
  "supports_web_search": true,
  "tpm": 8000000,
  "search_context_cost_per_query": {
    "search_context_size_low": 0.035,
    "search_context_size_medium": 0.035,
    "search_context_size_high": 0.035
  },
  "search_free_requests": {
    "count": 1500,
    "period": "day",
    "shared_group": "gemini-2-flash"
  },
  "google_maps_grounding_cost_per_query": 0.025,
  "input_cost_per_audio_token_batches": 5e-7,
  "input_cost_per_audio_token_priority": 0.0000018,
  "input_cost_per_token_batches": 1.5e-7,
  "input_cost_per_token_flex": 1.5e-7,
  "input_cost_per_token_priority": 5.4e-7,
  "output_cost_per_token_batches": 0.00000125,
  "output_cost_per_token_flex": 0.00000125,
  "output_cost_per_token_priority": 0.0000045,
  "supports_audio_input": true,
  "supports_image_size": false
}