Pricing and Billing
What you are charged for, how caching lowers your cost, and how to check any single call against your bill.
1. What you pay for
Pricing is per token, quoted per 1 million tokens, and charged in CNY (¥). There is no subscription and no monthly minimum — you buy credits, and each call deducts what it actually used. Credits never expire.
Every call is billed across up to four separate token types, each with its own rate. This matters more than it sounds: output is typically 5–6× the input rate on the same model, so a rough estimate based on input alone will understate your bill.
| Token type | Typical rate | What it is |
|---|---|---|
| Input | Baseline | The prompt you send, minus anything served from cache. |
| Output | 5–6× input on most models | What the model generates. Usually the largest line on your bill — cap it with max_tokens if cost matters more than length. A few models price output far lower, so check the model you actually use. |
| Cache read | ~10% of input on most models | Prompt content the provider already had cached from an earlier call. Heavily discounted — but not on every model: on a few, cached input costs the same as or more than regular input, so caching is not automatically a saving. |
| Cache write | Varies by model | Content being placed into the cache so later calls can reuse it. On Claude models this runs above the input rate; on several others it is below. Per-model rates are on the pricing page. |
One API key reaches every model in your key's scope — you do not need a separate key per model. All of your keys draw on the same account balance.
2. All model prices
Every rate below is what your account is actually charged — these come from the same price records the billing system reads, so nothing here can drift out of sync with your bill. Prices are shown in USD, converted from CNY at 6.71 CNY/USD.
Models available
53
Providers
14
Lowest input price
$0.0387 / 1M
Exchange rate
6.71 CNY/USD
Showing 53 of 53 models
| Model | Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Context | Images | Copy model ID |
|---|---|---|---|---|---|---|---|---|
| JZS Token1 model | ||||||||
| jzs-max-3.0Exclusive | JZS Token | $0.0620 | $0.3100 | $0.0062 | $0.0620 | 1M | Understands | |
| Alibaba / Qwen7 models | ||||||||
| qwen3.6-flash | Alibaba / Qwen | $0.155038% below official | $0.7750 | $0.0155 | $0.1550 | — | Unknown | |
| qwen3.8-flash | Alibaba / Qwen | $0.1550 | $0.7750 | $0.0155 | $0.1550 | — | Unknown | |
| qwen3.6-plus | Alibaba / Qwen | $0.232553% below official | $1.16 | $0.0232 | $0.2325 | 1M | Understands | |
| qwen3.7-plus | Alibaba / Qwen | $0.3100 | $1.55 | $0.0310 | $0.3100 | 1M | Understands | |
| qwen3.8-omni-flash | Alibaba / Qwen | $0.3875 | $1.94 | $0.0387 | $0.3875 | — | Unknown | |
| qwen3.7-max | Alibaba / Qwen | $0.775069% below official | $2.32 | $0.0969 | $0.9687 | 1M | — | |
| qwen3.8-max | Alibaba / Qwen | $1.5522% below official | $4.65 | $0.1937 | $1.94 | 1M | Understands | |
| Anthropic7 models | ||||||||
| claude-haiku-4-5-20251001 | Anthropic | $0.077592% below official | $0.3875 | $0.0077 | $0.1162 | 256K | Understands | |
| claude-sonnet-5 | Anthropic | $0.775061% below official | $3.87 | $0.0775 | $0.9687 | 1M | Understands | |
| claude-opus-4-6 | Anthropic | $1.16 | $5.81 | $0.1162 | $1.45 | 1M | Understands | |
| claude-opus-4-7 | Anthropic | $1.16 | $5.81 | $0.1162 | $1.45 | 1M | Understands | |
| claude-opus-4-8 | Anthropic | $1.16 | $5.81 | $0.1162 | $1.45 | 1M | Understands | |
| claude-opus-5 | Anthropic | $1.1676% below official | $5.81 | $0.1162 | $1.45 | 1M | Understands | |
| claude-opus-4-5-20251101 | Anthropic | $1.5569% below official | $7.75 | $0.0155 | $1.94 | — | Unknown | |
| ByteDance / Doubao4 models | ||||||||
| doubao-seed-2.0-lite | ByteDance / Doubao | $0.07758% below official | $0.3875 | $0.0077 | $0.0387 | — | Unknown | |
| doubao-seed-2.0-code | ByteDance / Doubao | $0.232548% below official | $1.16 | $0.0232 | $0.2325 | 200K | Understands | |
| doubao-seed-2.0-pro | ByteDance / Doubao | $0.232548% below official | $1.16 | $0.0232 | $0.2325 | 128K | Understands | |
| doubao-seed-2.1-turbo | ByteDance / Doubao | $0.232544% below official | $1.16 | $0.0232 | $0.2325 | — | Unknown | |
| DeepSeek3 models | ||||||||
| deepseek-v4-flash⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai) | DeepSeek | $0.1490 | $0.7452 | $0.0149 | $0.1490 | 1M | — | |
| deepseek-v4.1-flash⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai) | DeepSeek | $0.1490 | $0.7452 | $0.0149 | $0.1490 | — | Unknown | |
| deepseek-v4-pro⏱ Off-peak rate · peak 09:00–12:00 ×2, 14:00–18:00 ×2 (Asia/Shanghai) | DeepSeek | $0.4471 | $2.24 | $0.0447 | $0.4471 | 1M | — | |
| Google / Gemini3 models | ||||||||
| gemini-3-flash | Google / Gemini | $0.2325 | $1.16 | $0.0232 | $0.1162 | — | Unknown | |
| gemini-3.5-flash | Google / Gemini | $0.4650 | $2.32 | $0.0465 | $0.2325 | — | Unknown | |
| gemini-3.1-pro | Google / Gemini | $0.7750 | $3.87 | $0.0775 | $0.3875 | — | Unknown | |
| Meituan / LongCat1 model | ||||||||
| LongCat-2.0 | Meituan / LongCat | $0.077574% below official | $0.3100 | $0.0077 | $0.0775 | 1M | — | |
| MiniMax4 models | ||||||||
| MiniMax-M2.7 | MiniMax | $0.038783% below official | $0.1937 | $0.0039 | $0.0194 | — | Unknown | |
| MiniMax-M2.7-highspeed | MiniMax | $0.077583% below official | $0.3875 | $0.0077 | $0.0387 | — | Unknown | |
| MiniMax-M3 | MiniMax | $0.077567% below official | $0.3875 | $0.0077 | $0.0194 | 1M | Understands | |
| MiniMax-M3-highspeed | MiniMax | $0.1550 | $0.7750 | $0.0155 | $0.0775 | — | Unknown | |
| Moonshot / Kimi3 models | ||||||||
| kimi-k2.6 | Moonshot / Kimi | $0.155080% below official | $0.7750 | $0.0155 | $0.1550 | — | Unknown | |
| kimi-k2.7 | Moonshot / Kimi | $0.4650 | $2.32 | $0.0465 | $0.4650 | — | Unknown | |
| kimi-k3 | Moonshot / Kimi | $1.9435% below official | $9.69 | $0.1937 | $1.94 | 1M | Understands | |
| OpenAI9 models | ||||||||
| gpt-6-luna | OpenAI | $0.0387 | $0.2325 | $0.0039 | $0.0485 | — | Unknown | |
| gpt-5.6-luna | OpenAI | $0.0775 | $0.0465 | $0.0077 | $0.1162 | 258K | Understands | |
| gpt-5.6-terra | OpenAI | $0.2325 | $1.39 | $0.0232 | $0.3487 | 258K | Understands | |
| gpt-6-sol | OpenAI | $0.2325 | $1.39 | $0.0232 | $0.2906 | — | Unknown | |
| gpt-5.5 | OpenAI | $0.3875 | $2.32 | $0.0387 | $0.3875 | 258K | Understands | |
| gpt-5.6-sol | OpenAI | $0.4650 | $2.79 | $0.0465 | $0.5812 | 258K | Understands | |
| gpt-6-astra | OpenAI | $1.16 | $6.97 | $0.1162 | $1.74 | — | Unknown | |
| gpt-image-2-4k | OpenAI | $0.1937 per image | 4K output | Generates | ||||
| gpt-image-2 | OpenAI | $0.0194 per image | 1–2K output | Generates | ||||
| StepFun1 model | ||||||||
| step-3.7-flash | StepFun | $0.077559% below official | $0.3875 | $0.0077 | $0.0387 | 256K | Understands | |
| xAI / Grok3 models | ||||||||
| grok-4.5 | xAI / Grok | $0.3875 | $1.94 | $0.4844 | $0.3875 | 500K | Understands | |
| grok-4.6 | xAI / Grok | $0.3875 | $1.94 | $0.4844 | $0.3875 | — | Unknown | |
| grok-4.7 | xAI / Grok | $0.3875 | $1.94 | $0.0387 | $0.4844 | — | Unknown | |
| Xiaomi / MiMo4 models | ||||||||
| mimo-v2.5 | Xiaomi / MiMo | $0.1550 | $0.7750 | $0.0155 | $0.1550 | 1M | Understands | |
| mimo-v2.6-flash | Xiaomi / MiMo | $0.1550 | $0.7750 | $0.0155 | $0.1550 | — | Unknown | |
| mimo-v2.5-pro | Xiaomi / MiMo | $0.3100 | $1.55 | $0.0310 | $0.3100 | 1M | — | |
| mimo-v2.6-pro | Xiaomi / MiMo | $0.3100 | $1.55 | $0.0310 | $0.3100 | — | Unknown | |
| Zhipu / Z.ai3 models | ||||||||
| glm-5.3-flash | Zhipu / Z.ai | $0.1550 | $0.7750 | $0.0155 | $0.1550 | — | Unknown | |
| glm-5.2 | Zhipu / Z.ai | $0.620029% below official | $3.10 | $0.0620 | $0.6200 | 1M | Understands | |
| glm-5.3 | Zhipu / Z.ai | $0.620029% below official | $3.10 | $0.0620 | $0.6200 | — | Unknown | |
JZS Token1 model
JZS Token
- Input / 1M
- $0.0620
- Output / 1M
- $0.3100
- Cache read
- $0.0062
- Cache write
- $0.0620
Alibaba / Qwen7 models
Alibaba / Qwen
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
38% below the vendor's list price
Alibaba / Qwen
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
Alibaba / Qwen
- Input / 1M
- $0.2325
- Output / 1M
- $1.16
- Cache read
- $0.0232
- Cache write
- $0.2325
53% below the vendor's list price
Alibaba / Qwen
- Input / 1M
- $0.3100
- Output / 1M
- $1.55
- Cache read
- $0.0310
- Cache write
- $0.3100
Alibaba / Qwen
- Input / 1M
- $0.3875
- Output / 1M
- $1.94
- Cache read
- $0.0387
- Cache write
- $0.3875
Alibaba / Qwen
- Input / 1M
- $0.7750
- Output / 1M
- $2.32
- Cache read
- $0.0969
- Cache write
- $0.9687
69% below the vendor's list price
Alibaba / Qwen
- Input / 1M
- $1.55
- Output / 1M
- $4.65
- Cache read
- $0.1937
- Cache write
- $1.94
22% below the vendor's list price
Anthropic7 models
Anthropic
- Input / 1M
- $0.0775
- Output / 1M
- $0.3875
- Cache read
- $0.0077
- Cache write
- $0.1162
92% below the vendor's list price
Anthropic
- Input / 1M
- $0.7750
- Output / 1M
- $3.87
- Cache read
- $0.0775
- Cache write
- $0.9687
61% below the vendor's list price
Anthropic
- Input / 1M
- $1.16
- Output / 1M
- $5.81
- Cache read
- $0.1162
- Cache write
- $1.45
Anthropic
- Input / 1M
- $1.16
- Output / 1M
- $5.81
- Cache read
- $0.1162
- Cache write
- $1.45
Anthropic
- Input / 1M
- $1.16
- Output / 1M
- $5.81
- Cache read
- $0.1162
- Cache write
- $1.45
Anthropic
- Input / 1M
- $1.16
- Output / 1M
- $5.81
- Cache read
- $0.1162
- Cache write
- $1.45
76% below the vendor's list price
Anthropic
- Input / 1M
- $1.55
- Output / 1M
- $7.75
- Cache read
- $0.0155
- Cache write
- $1.94
69% below the vendor's list price
ByteDance / Doubao4 models
ByteDance / Doubao
- Input / 1M
- $0.0775
- Output / 1M
- $0.3875
- Cache read
- $0.0077
- Cache write
- $0.0387
8% below the vendor's list price
ByteDance / Doubao
- Input / 1M
- $0.2325
- Output / 1M
- $1.16
- Cache read
- $0.0232
- Cache write
- $0.2325
48% below the vendor's list price
ByteDance / Doubao
- Input / 1M
- $0.2325
- Output / 1M
- $1.16
- Cache read
- $0.0232
- Cache write
- $0.2325
48% below the vendor's list price
ByteDance / Doubao
- Input / 1M
- $0.2325
- Output / 1M
- $1.16
- Cache read
- $0.0232
- Cache write
- $0.2325
44% below the vendor's list price
DeepSeek3 models
DeepSeek
- Input / 1M
- $0.1490
- Output / 1M
- $0.7452
- Cache read
- $0.0149
- Cache write
- $0.1490
DeepSeek
- Input / 1M
- $0.1490
- Output / 1M
- $0.7452
- Cache read
- $0.0149
- Cache write
- $0.1490
DeepSeek
- Input / 1M
- $0.4471
- Output / 1M
- $2.24
- Cache read
- $0.0447
- Cache write
- $0.4471
Google / Gemini3 models
Google / Gemini
- Input / 1M
- $0.2325
- Output / 1M
- $1.16
- Cache read
- $0.0232
- Cache write
- $0.1162
Google / Gemini
- Input / 1M
- $0.4650
- Output / 1M
- $2.32
- Cache read
- $0.0465
- Cache write
- $0.2325
Google / Gemini
- Input / 1M
- $0.7750
- Output / 1M
- $3.87
- Cache read
- $0.0775
- Cache write
- $0.3875
Meituan / LongCat1 model
Meituan / LongCat
- Input / 1M
- $0.0775
- Output / 1M
- $0.3100
- Cache read
- $0.0077
- Cache write
- $0.0775
74% below the vendor's list price
MiniMax4 models
MiniMax
- Input / 1M
- $0.0387
- Output / 1M
- $0.1937
- Cache read
- $0.0039
- Cache write
- $0.0194
83% below the vendor's list price
MiniMax
- Input / 1M
- $0.0775
- Output / 1M
- $0.3875
- Cache read
- $0.0077
- Cache write
- $0.0387
83% below the vendor's list price
MiniMax
- Input / 1M
- $0.0775
- Output / 1M
- $0.3875
- Cache read
- $0.0077
- Cache write
- $0.0194
67% below the vendor's list price
MiniMax
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.0775
Moonshot / Kimi3 models
Moonshot / Kimi
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
80% below the vendor's list price
Moonshot / Kimi
- Input / 1M
- $0.4650
- Output / 1M
- $2.32
- Cache read
- $0.0465
- Cache write
- $0.4650
Moonshot / Kimi
- Input / 1M
- $1.94
- Output / 1M
- $9.69
- Cache read
- $0.1937
- Cache write
- $1.94
35% below the vendor's list price
OpenAI9 models
OpenAI
- Input / 1M
- $0.0387
- Output / 1M
- $0.2325
- Cache read
- $0.0039
- Cache write
- $0.0485
OpenAI
- Input / 1M
- $0.0775
- Output / 1M
- $0.0465
- Cache read
- $0.0077
- Cache write
- $0.1162
OpenAI
- Input / 1M
- $0.2325
- Output / 1M
- $1.39
- Cache read
- $0.0232
- Cache write
- $0.3487
OpenAI
- Input / 1M
- $0.2325
- Output / 1M
- $1.39
- Cache read
- $0.0232
- Cache write
- $0.2906
OpenAI
- Input / 1M
- $0.3875
- Output / 1M
- $2.32
- Cache read
- $0.0387
- Cache write
- $0.3875
OpenAI
- Input / 1M
- $0.4650
- Output / 1M
- $2.79
- Cache read
- $0.0465
- Cache write
- $0.5812
OpenAI
- Input / 1M
- $1.16
- Output / 1M
- $6.97
- Cache read
- $0.1162
- Cache write
- $1.74
StepFun1 model
StepFun
- Input / 1M
- $0.0775
- Output / 1M
- $0.3875
- Cache read
- $0.0077
- Cache write
- $0.0387
59% below the vendor's list price
xAI / Grok3 models
xAI / Grok
- Input / 1M
- $0.3875
- Output / 1M
- $1.94
- Cache read
- $0.4844
- Cache write
- $0.3875
xAI / Grok
- Input / 1M
- $0.3875
- Output / 1M
- $1.94
- Cache read
- $0.4844
- Cache write
- $0.3875
xAI / Grok
- Input / 1M
- $0.3875
- Output / 1M
- $1.94
- Cache read
- $0.0387
- Cache write
- $0.4844
Xiaomi / MiMo4 models
Xiaomi / MiMo
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
Xiaomi / MiMo
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
Xiaomi / MiMo
- Input / 1M
- $0.3100
- Output / 1M
- $1.55
- Cache read
- $0.0310
- Cache write
- $0.3100
Xiaomi / MiMo
- Input / 1M
- $0.3100
- Output / 1M
- $1.55
- Cache read
- $0.0310
- Cache write
- $0.3100
Zhipu / Z.ai3 models
Zhipu / Z.ai
- Input / 1M
- $0.1550
- Output / 1M
- $0.7750
- Cache read
- $0.0155
- Cache write
- $0.1550
Zhipu / Z.ai
- Input / 1M
- $0.6200
- Output / 1M
- $3.10
- Cache read
- $0.0620
- Cache write
- $0.6200
29% below the vendor's list price
Zhipu / Z.ai
- Input / 1M
- $0.6200
- Output / 1M
- $3.10
- Cache read
- $0.0620
- Cache write
- $0.6200
29% below the vendor's list price
Last updated Sep 23, 2026, 6:17 AM UTC. The pricing page shows the same catalogue with model comparisons and copyable model IDs.
3. Caching, and how to actually benefit from it
When consecutive requests share a long identical prefix, the provider can reuse the work it already did on that prefix instead of reprocessing it. You are charged the discounted cache-read rate for that portion. Long conversations, follow-up questions on the same document, code completion, and agent loops all hit this case naturally.
The practical rule: keep the unchanging part of your prompt at the front, and put what varies at the end. Caching matches on a shared prefix, so a system prompt or document that sits before your question stays cacheable across turns. Move a timestamp or a request ID to the top and you invalidate the prefix on every single call — you then pay full input rate for the whole thing, plus a cache write.
Cache writes are not free, so a one-off call that will never be followed up gains nothing from caching. The benefit shows up from the second call onward, which is exactly the pattern agents and multi-turn chat produce.
4. Image models are billed per image
Image generation is not billed per token. Each image is a fixed price regardless of prompt length, and the rate depends on the output resolution. Current per-image prices are on the pricing page.
Image calls go to POST /v1/images/generations, not the chat endpoint. In your usage records they show a cost with zero tokens — that is expected, since tokens play no part in what you were charged.
5. Checking a call against your bill
The usage lookup page takes an API key and shows your balance, per-model totals, and recent calls. The four token types appear as separate columns, so you can multiply each one by its rate on the pricing page and land on the exact figure that was deducted.
The token counts come from the provider's usage block on the response — the same numbers your own client receives, so you can verify them against your logs without asking us.
Failed calls are listed too, with the reason in the Details column and a cost of zero. A call that errored is never billed. If the failure came from the upstream provider rather than your request, that column says so — you do not need to go debugging your own code first.
6. When prices change
Model prices track what the providers charge, and those move occasionally. Our price records sync automatically and the pricing page shows when they were last updated. Each call is billed at the rate in effect at that moment, and your usage records keep the resulting cost, so a later price change never restates what you already paid.
A few models are priced by time of day, meaning a call during the provider's peak window costs more than the same call off-peak. Where that applies, the pricing page notes it on the model. If your workload is flexible, shifting it out of the peak window is the simplest saving available.
Questions about a specific charge
Send us the call's timestamp and the model, plus the masked form of your API key — never a full working key. See the contact page for how to reach us.