Cheaper Inference
Model record / Google
gemini-2.5-flash
Access gemini-2.5-flash from Google through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationVision inputStandard generationStreaming35% below list
What you pay
Current catalog rates.
Input / 1M tokens$0.30 list$0.195
Output / 1M tokens$2.50 list$1.625
Cached input / 1M tokens$0.03 list$0.0195
Current discount35%
Observed reliability
99.74
Successful provider-reaching requests
Output speed
214.1
Median tokens per second over sustained generations
TTFT
4.3 s
p50 · p90 17.4 s · n 247
Latency
8.5 s
p50 · p90 22.5 s · n 7,393
Evidence strength
—
At a glance
- Provider
- Model ID
- gemini-2.5-flash
- Type
- Text generation
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
- Input
- image, pdf, text
- Output
- text
- Vision input
- Supported
- Image editing
- Not supported
- Video input
- Not supported
- Reasoning
- Not supported
- Streaming
- Supported
- Context window
- 1,048,576 tokens
Parameters by endpoint
The request field of each parameter on each endpoint, and the values it takes.
POST /v1/chat/completions
| Field | Values |
|---|---|
| reasoning.exclude | |
| max_tokens | |
| reasoning | effort: none, low, medium, high; max_tokens: 1024 to max output tokens; enabled: true or false |
| response_format | |
| stop | |
| temperature | |
| tool_choice | |
| tools |
POST /v1/messages
| Field | Values |
|---|---|
| max_tokens | |
| thinking |
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
gemini-2.5-flash
High confidenceThis model averaged 33.9% below comparable direct provider prices across the selected range. Its strongest observed window was 7:00 PM–8:00 AM in UTC.
Last 7 days
Average saved
33.9%
Last 7 days
Cheapest time
7:00 PM–8:00 AM
34.8% average savings
Hourly coverage
24/24
166 total observations
Signal quality
High
Ready for planning
Typical unit savings$0.10 / 1M input tokens$0.85 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#67
of 408 ranked models
Last 7 days
#80
of 417 ranked models
Last 30 days
#60
of 417 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.