Pricing
Pay per request. No subscription, no minimum spend, no charge for a failed request. Prices below are read from the gateway’s live price list.
排序
显示 77 / 77 个模型
按 token 计费
对话、embedding、语音转写 —— 每百万 tokens 的价格。
Other8
bge-m3输入$0.0125text-embedding-3-small输入$0.025mimo-v2.6-flash输入$0.175输出$0.35缓存命中$0.0035mimo-v2.5输入$0.175输出$0.35缓存命中$0.0035codex-auto-review输入$0.4657输出$2.79缓存命中$0.0466mimo-v2.6-pro输入$0.5438输出$1.09缓存命中$0.0045mimo-v2.5-pro输入$0.5438输出$1.09缓存命中$0.0045MiniMax-M3$1.5/ 百万 tokens
智谱4
glm-5.2输入$0.0563输出$0.1768缓存命中$0.0104glm-5.3-flash输入$0.0926输出$0.3087缓存命中$0.0185glm-5.3-flashx输入$0.4017输出$1.36缓存命中$0.0814glm-5.3输入$0.9692输出$3.05缓存命中$0.18
阿里巴巴4
qwen3.8-flash输入$0.0926输出$0.2779缓存命中$0.009263qwen3.7-plus输入$0.2792输出$1.12缓存命中$0.0558qwen3.8-max输入$1.24输出$3.71缓存命中$0.1544qwen3.7-max输入$1.54输出$4.63缓存命中$0.3088
DeepSeek5
deepseek-v4-flash输入$0.099输出$0.198缓存命中$0.00198deepseek-flash输入$0.1125输出$0.0281缓存命中$0.000563deepseek-v4-flash-vision-exp输入$0.2475输出$0.7425缓存命中$0.007875deepseek-v3.2输入$0.252输出$0.378缓存命中$0.1215deepseek-v4-pro输入$0.297输出$0.594缓存命中$0.002458
讯飞2
muse-spark-1.3-contributor输入$0.1245输出$0.249缓存命中$0.00249muse-spark-1.3输入$1.56输出$5.31缓存命中$0.1875
Anthropic10
claude-haiku-4-5输入$0.1406输出$0.7031缓存命中$0.0141claude-sonnet-5输入$0.2232输出$1.12缓存命中$0.0223claude-opus-4-7输入$0.5581输出$2.79缓存命中$0.0558claude-sonnet-4-6输入$0.6输出$3缓存命中$0.06claude-sonnet-5-5输入$0.838输出$4.19缓存命中$0.0838claude-opus-4-8输入$1.12输出$5.59缓存命中$0.1118claude-opus-5输入$1.48输出$7.42缓存命中$0.1485claude-opus-5-5输入$1.68输出$8.38缓存命中$0.0838claude-fable-5-1输入$3.63输出$18.16缓存命中$0.0908claude-fable-5输入$8.18输出$40.89缓存命中$0.8178
xAI3
grok-4.5输入$0.1489输出$0.4467缓存命中$0.0372grok-4.6输入$0.1489输出$0.4467缓存命中$0.0372grok-4.7输入$0.1489输出$0.4467缓存命中$0.0372
OpenAI9
gpt-6-luna$0.25/ 百万 tokensgpt-5.6-luna$0.5/ 百万 tokensgpt-6.1-sol$5/ 百万 tokensgpt-5.6-terra$5/ 百万 tokensgpt-6-sol$5/ 百万 tokensgpt-5.5$12.5/ 百万 tokensgpt-5.6-sol$12.5/ 百万 tokensgpt-6-astra$25/ 百万 tokensgpt-transcribe输入$93.75输出$187.5
Google4
gemini-3.8-flash输入$0.3748输出$1.87缓存命中$0.0375gemini-3.7-flash输入$0.3748输出$1.87缓存命中$0.0375gemini-3.6-flash输入$0.45输出$2.25缓存命中$0.045gemini-3.1-pro-preview输入$0.4998输出$3缓存命中$0.05
字节跳动2
doubao-seed-2-1-turbo-260628输入$0.525输出$2.6缓存命中$0.105doubao-seed-2-1-pro-260628输入$1.04输出$5.21缓存命中$0.2075
Moonshot4
kimi-k2.7-code输入$0.8906输出$3.75缓存命中$0.1781kimi-k2.6输入$1.19输出$5缓存命中$0.2kimi-k2.8-preview输入$1.25输出$5缓存命中$0.3125kimi-k3输入$2.42输出$12.11缓存命中$0.2423
按次计费
图片与视频 —— 每次生成的价格。与上面的按 token 表不可直接比较。
字节跳动1
doubao-seedream-5-0-pro-260628- Image Input (after first)$0.00375
- Image Output$0.0563
- Layer Image Output$0.0281
- High-Resolution Image Output$0.1125
- +1
Other7
seedance-2.0-mini- 480P$0.0132
- 480P-input$0.007909
- 720P$0.0284
- 720P-input$0.017
seedance-2.0-fast- 480P$0.0352
- 480P-input$0.0207
- 720P$0.0756
- 720P-input$0.0446
seedance-2.0- 4K$0.9233
- 4K-input$0.554
- 1080P$0.4443
- 1080P-input$0.2712
- +4
MiniMax-H3- 2K$0.0975
- 768P$0.06
seedance-2.5- 1080P$0.6752
- 1080P-input$0.4039
- 480P$0.1221
- 480P-input$0.073
- +2
midjourney-v8.2- fast$0.2064
- relax$0.1689
- turbo$0.375
midjourney-niji-7- fast$0.2064
- relax$0.1689
- turbo$0.375
OpenAI6
gpt-image-2.5-sunburst$0.009375/ 次gpt-image-2$0.009375/ 次gpt-image-2.5-flare$0.009375/ 次gpt-image-2.5-flare-fd- 1K$0.0234
- 2K$0.0281
- 4K$0.0563
gpt-image-2.5-sunburst-fd- 1K$0.0234
- 2K$0.0281
- 4K$0.0563
gpt-image-2-fd- 1K$0.0234
- 2K$0.0281
- 4K$0.0563
Google4
gemini-3.1-flash-image- 0.5K$0.0113
- 1K$0.0168
- 2K$0.0253
- 4K$0.0378
gemini-nano-banana-2.1- 1K$0.02
- 2K$0.03
- 4K$0.045
gemini-3-pro-image- 1K$0.0251
- 2K$0.0251
- 4K$0.045
gemini-2.5-flash-image$0.0468/ 次
xAI2
grok-imagine-image-2.0- 1K low$0.048
- 1K medium$0.072
- 2K low$0.072
- 2K medium$0.096
- +1
grok-imagine-video-1.5$0.08/ 次
快手2
kling-v3-omni- 4k$0.5893
- 4k-sound$0.5893
- base$0.0924
- pro$0.1232
- +4
kling-v3-motion-control$0.1286/ 次
This table is generated from https://api.tokwork.com/api/pricing and refreshes every five minutes. The console shows the same numbers with a per-model breakdown; text and chat models appear here as they are enabled. Switch currency in the header to see converted prices — your balance is still charged in USD, at the live rate shown in the currency menu.
How billing works
- Prepaid balance. Top up once; every request deducts its price. When the balance reaches zero, requests stop instead of running up a bill.
- Per-request receipts. Every call is logged with the model, the size, and the amount deducted, so you can reconcile it against your own usage.
- Image sizes differ. For image models the price depends on the output resolution (and, for some models, the quality) — the breakdown above is the authoritative list, and it is also shown in the console before you generate.
- Failed requests are free. A request that returns an error from a provider is not charged.
Ready to call it? Sign in to create a key, or read the quickstart first.