Prices are in US dollars and are for 1 million tokens. The discount is relative to the model's official list price; the struck-through amount is that official price. To see cache prices, hover over the input price. Status is calculated from the last hour of requests. Only the names on this page are accepted; any other model name returns a 400.
Combo & Smart 1 models Deal
Price change From November 28, 2026, wiozen-coder will cost $0.065 input and $0.26 output per 1M tokens; cache prices rise by the same rate. If you don't accept the change, tell us before it takes effect and you can ask for a refund of your unused paid balance (Refund and Balance Policy).
| Model name | Status | Context | Input | Output | ||
|---|---|---|---|---|---|---|
wiozen-coderWiozen Coder |
live | 200K | $0.05 | $0.20 | output $0.20 · context 200K |
Gemini 1 models
| Model name | Status | Discount | Context | Input | Output | ||
|---|---|---|---|---|---|---|---|
gemini-3.8-flash-highGemini 3.8 Flash |
live | −%60 | 1M | output |
DeepSeek 1 models
Time-based pricing Half the official price every hour · input / output, 1M tokens · Turkey time
Off-peak hours nowAll other hours and weekends
$0.075 / $0.30Peak hoursWeekdays 04:00–07:00 and 09:00–13:00
$0.15 / $0.60Next switch: today 04:00 AM · peak-hour pricing starts.
| Model name | Status | Discount | Context | Input | Output | ||
|---|---|---|---|---|---|---|---|
deepseek-v4.1-flashDeepSeek V4.1 Flash |
working | −%50 | 1M | output |
Image generation 5 models
Reference image Text-to-image and generation from a reference image (image-to-image: editing, background replacement) are supported; FLUX.2 Klein does not take a reference image. Pricing is per image; the amount is in the model description. Endpoint
/v1/images/generations · examples| Model name | Status | Discount | Context | Input | Output | ||
|---|---|---|---|---|---|---|---|
gemini-3.1-flash-imageGemini 3.1 Flash Image |
live | −%30 | 32K | output |
|||
gpt-image-2.5GPT Image 2.5 |
live | −%30 | 32K | output |
|||
flux-2-klein-4bFLUX.2 Klein 4B |
live | −%30 | — | output |
|||
gpt-image-2.6-flareGPT Image 2.6 Flare |
live | −%30 | 32K | output |
|||
gpt-image-2.6-sunburstGPT Image 2.6 Sunburst |
live | −%30 | 32K | output |
Transcription 1 models
Per minute Turns speech into text. You pay for the length of the audio, not for tokens: the duration is rounded up to the second and multiplied by the per-minute price. Supported files are wav, mp3, m4a, mp4, ogg, flac and webm. Endpoint
/v1/audio/transcriptions · endpoints| Model name | Status | Context | Input | Output | ||
|---|---|---|---|---|---|---|
whisper-large-v3Whisper Large v3 |
live | — | $0.003 / min | — | Whisper Large v3 |
Not sure which to pick? Which AI model to choose, Claude Haiku vs Sonnet: API price and how to calculate AI API cost.