Models
Nano Banana API: Gemini image generation pricing
Generate images with Google's Nano Banana family (Gemini Flash Image and Gemini 3 Pro Image) through Tokely's API. Per-image prices, one key and balance.
tokely.me/nano-banana-api
DeepSeek API: V4 Flash and V4 Pro pricing
DeepSeek V4.1 Flash: $0.2 input / $0.8 output per 1M tokens. Pay as you go.
By TokelyReviewed DeepSeek V4.1 Flash and DeepSeek V4 Pro are available through Tokely's OpenAI-compatible endpoint with function tools, JSON mode, streaming and reasoning effort. You pay per token from a prepaid balance; the table shows the Tokely rate next to DeepSeek's published price.
DeepSeek API price comparison
| Model | Tokely input / output | Tokely example | model developer example | Discount vs model developer |
|---|---|---|---|---|
| DeepSeek V4.1 FlashDeepSeek | $0.2 / $0.8Cache read: $0.004 | $0.4 | $0.3$0.15 / $0.6 per 1M | 33.3% higher |
| DeepSeek V3.1DeepSeek | $0.478335 / $1.435005Cache read: $0.478335 | $0.837086 | Not matched | — |
| DeepSeek V4 FlashDeepSeek | $0.605 / $1.815Cache read: $0.01925 | $1.05875 | Not matched | — |
| DeepSeek V4 ProDeepSeek | $1.815 / $5.445Cache read: $0.060494 | $3.17625 | Not matched | — |
Flash for volume, Pro for hard tasks
V4.1 Flash is the low-cost option for chat, extraction and agents with many calls. V4 Pro handles harder reasoning and long outputs at a higher rate. Both accept the same request shape, so switching is a model ID change.
Verified parameters
Tokely tested both models with streaming usage, function tools, JSON mode, temperature, top_p, stop sequences and reasoning effort. V4.1 Flash also accepts inline images; V4 Pro is text-only on Tokely.
Caching
Repeated prefixes are billed at the cache-read rate when the supplier reports a cache hit, and cached tokens are not billed again as regular input.
One key for every model
Every model on this page is available through one OpenAI-compatible endpoint and one balance, with routing modes, bounded fallback, spending limits and request logs.
LLM gateway: one API for every model ↗
A hosted LLM gateway with one OpenAI-compatible endpoint, account routing modes, bounded fallback, spending limits and request logs. Text, image, video and audio from one balance.
OpenAI-compatible API for Claude, Gemini, GPT and more ↗
Keep the OpenAI SDK and call Claude, Gemini, GPT, Kimi, GLM and other supported models. Change the base URL, key and model ID.
Questions before you switch
Is the DeepSeek API OpenAI-compatible?
Yes on Tokely: use the OpenAI SDK with base URL https://api.tokely.me/v1 and model deepseek-v4.1-flash or deepseek-v4-pro-0813.
Do I need a DeepSeek account?
No. One Tokely account and key cover DeepSeek and the other supported models.
START WITH YOUR OWN WORKLOADKnow the price.
Know the price.
Then make the call.
Check the model, compare the rate, and connect with a Tokely key.