Gemini 2.5 Flash
Google's previous-generation Flash model for high-volume, low-latency multimodal tasks.
Model ID
google/gemini-2.5-flash- Context window
- 1M
- tokens
- Max output
- 66K
- tokens
- Input
- $0.195
- per 1M tokens
- Output
- $1.63
- per 1M tokens
Cache read $0.0195 · Cache write $0.0541
Quickstart
Call Gemini 2.5 Flash in one request.
Point the SDK you already use at xKiro and pass the model ID. The same key works for every model in the catalog.
SDK guidesimport osfrom openai import OpenAI client = OpenAI( api_key=os.environ["XKIRO_API_KEY"], base_url="https://api.xkiro.com/v1",) res = client.chat.completions.create( model="", messages=[ {"role": "user", "content": "Explain HTTP caching in two sentences."}, ],) print(res.choices[0].message.content)✓ 200 OK
"model": "google/gemini-2.5-flash"
HTTP caching stores copies of responses so later requests can be served without contacting the origin server. Headers such as Cache-Control and ETag decide how long a copy stays fresh and how it is revalidated.
14 input · 42 output tokens · $0.000071 at this model’s rates
Create an API key in the dashboard and export it as XKIRO_API_KEY.
Pricing
What Gemini 2.5 Flash costs.
Billed per million tokens from your wallet balance, outside plan budgets.
$0.195
$0.3−35%Input
per 1M tokens
$1.63
$2.50−35%Output
per 1M tokens
$0.0195
Cache read
per 1M tokens
$0.0541
Cache write
per 1M tokens
Google's own API lists Gemini 2.5 Flash at $0.3 / $2.50 per 1M tokens.
Pay as you go here: 35% less than the official API.
Google pricing page (lowest tier), checked Oct 21, 2026Billed fairly
- A request that fails before any output is generated is never billed
- An identical blocking request retried within two minutes replays the first result — no double charge
- If a stream breaks off or you cancel it, you pay only up to that point
Specifications
Limits and capabilities.
- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- Input
- Text · Image · Video
- Output
- Text
- Provider
- Model ID
- google/gemini-2.5-flash
- Good for
- Long context
Capabilities
- Tool useSupported
- VisionSupported
- Video inputSupported
- ReasoningSupported
Reasoning effort
- low
- high
Set it with reasoning_effort in the OpenAI format, or thinking in the Anthropic format.
Supported parameters
- max_tokens
- temperature
- top_p
- stop
- frequency_penalty
- presence_penalty
- seed
- stream
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
Compare
Similar models.
Closest in price and context window — same provider first, then alternatives from other providers.
Browse all 69 models| Model | Input / 1M | Output / 1M | ||
|---|---|---|---|---|
| 1M | $0.195 | $1.63 | $0.0195 | |
| 1M | $0.4875 | $2.44 | $0.0488 | |
| 1M | $0.4875 | $2.44 | $0.0488 | |
| 1M | $0.4875 | $2.44 | $0.0488 | |
| 1M | $0.15 | $0.5 | $0.02 | |
| 1.05M | $0.2828 | $0.5655 | $0.0023 | |
| 1M | $0.1 | $0.5 | $0.01 |
Start building with Gemini 2.5 Flash.
Create a key, point your SDK at xKiro and call google/gemini-2.5-flash.
No credit card · No auto-renewal · 26 free models, free forever