Models
DeepSeek API: V4 Flash and V4 Pro pricing
Call DeepSeek V4.1 Flash and V4 Pro through an OpenAI-compatible API. Per-token prices, cache-read rates, tools, JSON and streaming from one Tokely key.
tokely.me/deepseek-api
DeepSeek, Kimi, Qwen and MiniMax API
Call DeepSeek V4, Kimi K3 and K2.7 Code, Qwen 3.8 Flash and MiniMax M3 through one OpenAI-compatible API key. Compare per-token prices in one table.
By TokelyReviewed Tokely serves DeepSeek V4.1 Flash and V4 Pro, Kimi K3 and K2.7 Code, Qwen 3.8 Flash and MiniMax M3 through its OpenAI-compatible endpoint, all from one key and USD balance. The table shows current prices.
Price comparison of the models on this page
| 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 |
| Qwen 3.8 FlashQwen | $0.309375 / $0.969375Cache read: $0.033011 | $0.551719 | $0.2085$0.113 / $0.382 per 1M | 164.6% higher |
| DeepSeek V3.1DeepSeek | $0.478335 / $1.435005Cache read: $0.478335 | $0.837086 | Not matched | — |
| MiniMax M2.5MiniMax | $0.515625 / $1.65Cache read: $0.4125 | $0.928125 | $0.6$0.3 / $1.2 per 1M | 54.7% higher |
| Qwen 3.5 35B A3BQwen | $0.33 / $2.64Cache read: $0.234667 | $0.99 | $0.75$0.25 / $2 per 1M | 32.0% higher |
| DeepSeek V4 FlashDeepSeek | $0.605 / $1.815Cache read: $0.01925 | $1.05875 | Not matched | — |
| Qwen 3.6 35B A3BQwen | $0.5 / $3Cache read: $0.333333 | $1.25 | $0.9375$0.375 / $2.25 per 1M | 33.3% higher |
| Qwen 3.5 122B A10BQwen | $0.53 / $4.24Cache read: $0.765556 | $1.59 | $1.2$0.4 / $3.2 per 1M | 32.5% higher |
| MiniMax M3MiniMax | $0.825 / $3.3Cache read: $0.165 | $1.65 | $0.6$0.3 / $1.2 per 1M | 175.0% higher |
| MiniMax M2.7MiniMax | $0.9075 / $3.63Cache read: $0.9075 | $1.815 | $0.6$0.3 / $1.2 per 1M | 202.5% higher |
| Kimi K2.5Moonshot | $0.825 / $4.33125Cache read: $0.825 | $1.907813 | Not matched | — |
| Qwen 3 235B A22BQwen | $0.9625 / $3.85Cache read: $0 | $1.925 | Not matched | — |
| Kimi K2.6Moonshot | $1.30625 / $5.426025Cache read: $0.221058 | $2.662756 | $1.95$0.95 / $4 per 1M | 36.6% higher |
| Kimi K2.7 CodeMoonshot | $1.30625 / $5.426025Cache read: $0.26125 | $2.662756 | $1.95$0.95 / $4 per 1M | 36.6% higher |
| Qwen 3.8 MaxQwen | $1.5345 / $4.60443Cache read: $0.3 | $2.685608 | $2.88775$1.65 / $4.951 per 1M | 7.0% off |
| Qwen 3.6 27BQwen | $1.2375 / $7.425Cache read: $1.2375 | $3.09375 | $1.5$0.6 / $3.6 per 1M | 106.3% higher |
| DeepSeek V4 ProDeepSeek | $1.815 / $5.445Cache read: $0.060494 | $3.17625 | Not matched | — |
| Qwen 3.5 27BQwen | $1.2375 / $9.9Cache read: $0 | $3.7125 | $0.9$0.3 / $2.4 per 1M | 312.5% higher |
| Qwen 3.8 27BQwen | $1.5125 / $9.075Cache read: $0.3025 | $3.78125 | $0.848$0.424 / $1.696 per 1M | 345.9% higher |
| Qwen 3.7 PlusQwen | $2.475 / $9.9Cache read: $0.495 | $4.95 | $0.8$0.4 / $1.6 per 1M | 518.8% higher |
| Qwen 3.5 397B A17BQwen | $2.0625 / $12.375Cache read: $0 | $5.15625 | $1.5$0.6 / $3.6 per 1M | 243.8% higher |
| Qwen 3.7 MaxQwen | $3.4375 / $10.3125Cache read: $0.6875 | $6.015625 | $2.88775$1.65 / $4.951 per 1M | 108.3% higher |
| Kimi K3Moonshot | $2.7 / $13.5Cache read: $0.27 | $6.075 | $6.75$3 / $15 per 1M | 10.0% off |
| Qwen 3.5 PlusQwen | $2.75 / $16.5Cache read: $0 | $6.875 | $1$0.4 / $2.4 per 1M | 587.5% higher |
| Qwen PlusQwen | $1.98 / $23.76Cache read: $0 | $7.92 | $0.7$0.4 / $1.2 per 1M | 1031.4% higher |
| Qwen 3.6 PlusQwen | $4.125 / $24.75Cache read: $0 | $10.3125 | $1.25$0.5 / $3 per 1M | 725.0% higher |
One key instead of four accounts
There is no need for separate DeepSeek, Moonshot, Alibaba Cloud or MiniMax accounts. Use https://api.tokely.me/v1 with the model IDs deepseek-v4.1-flash, deepseek-v4-pro-0813, kimi-k3, kimi-k2.7-code, qwen3.8-flash or MiniMax-M3.
Where they fit
Qwen 3.8 Flash and DeepSeek V4.1 Flash are the low-cost options for high-volume chat and extraction. Kimi K2.7 Code targets coding agents. DeepSeek V4 Pro, Kimi K3 and MiniMax M3 cover harder reasoning at mid-range prices.
Verified parameters
DeepSeek V4.1 Flash and V4 Pro, Kimi K2.7 Code, Qwen 3.8 Flash and MiniMax M3 were tested on 2026-10-15 through api.tokely.me with streaming usage, function tools, JSON mode, sampling controls and reasoning effort; image input worked on all of them except DeepSeek V4 Pro.
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
Are these models OpenAI-compatible on Tokely?
Yes. Use the OpenAI SDK with base URL https://api.tokely.me/v1 and the model IDs above.
Is GLM available?
Not at the moment. The models in the table are the ones currently enabled.
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.