Pricing
Models and prices
Every model on sale, in US dollars per million tokens. You pay per token used, from prepaid credit bought under an offline contract.
- US dollarsEvery price on this page
- Per 1M tokensInput and output priced apart
- Pay per token usedSettled when each request ends
- Prepaid creditAdded by an administrator under your contract
| Model | Context | Input / 1M tokens | Output / 1M tokens | Prompt cache and service tiers |
|---|---|---|---|---|
DeepSeek-V4-Prodeepseek-ai/deepseek-v4-pro | 1M tokens | $1.7876296 | $3.57525921 |
|
DeepSeek-V4-Pro 0813 正式版deepseek-ai/deepseek-v4-pro-0813 | 1.02M tokens | $0.66 | $1.98 |
|
DeepSeek-V4.1-Flashdeepseek-ai/deepseek-v4.1-flash | 1M tokens | $0.15 | $0.60 |
|
DeepSeek-V4.1-Flash-1017deepseek-ai/deepseek-v4.1-flash-1017 | 1.02M tokens | $0.14896913 | $0.59587653 |
|
MiniMax-M2.5minimax/minimax-m2.5 | 200K tokens | $0.31283518 | $1.25134072 |
|
MiniMax-M3minimax/minimax-m3Long prompts cost more: over 512K prompt tokens, $0.62567036 in / $2.50268144 out, per 1M tokens. | 1M tokens | from $0.31283518 | from $1.25134072 |
|
MiniMax-M3.1-Flashminimax/minimax-m3.1-flash | 1.02M tokens | $0.14896913 | $0.59587653 |
|
Kimi K2.6moonshotai/kimi-k2.6 | 256K tokens | $0.96829937 | $4.02216661 |
|
Kimi K2.7 Codemoonshotai/kimi-k2.7-code | 256K tokens | $0.96829937 | $4.02216661 |
|
Kimi K2.7 Code HighSpeedmoonshotai/kimi-k2.7-code-highspeed | 256K tokens | $1.93659874 | $8.04433321 |
|
Kimi K2.8 Previewmoonshotai/kimi-k2.8-preview | 1.02M tokens | $0.96829937 | $4.02216661 |
|
Kimi K3moonshotai/kimi-k3 | 1M tokens | $2.97938267 | $14.89691336 |
|
Kimi K3.1 Promoonshotai/kimi-k3.1-pro | 1M tokens | $1.93659874 | $10.12990108 |
|
Kimi K3.1 Pro HighSpeedmoonshotai/kimi-k3.1-pro-highspeed | 1.02M tokens | $3.87319747 | $20.25980217 |
|
GUI-Plusqwen/gui-plus | 256K tokens | $0.2234537 | $0.6703611 | — |
Qwen-Flash-Characterqwen/qwen-flash-character | 8K tokens | $0.03724228 | $0.2234537 |
|
Qwen-MT-Flashqwen/qwen-mt-flash | 16K tokens | $0.10427839 | $0.29048981 | — |
Qwen-MT-liteqwen/qwen-mt-lite | 16K tokens | $0.08938148 | $0.23835061 | — |
Qwen-MT-Plusqwen/qwen-mt-plus | 16K tokens | $0.26814444 | $0.80443332 | — |
Qwen-Plus-Characterqwen/qwen-plus-character | 32K tokens | $0.11917531 | $0.29793827 |
|
Qwen-VL-OCRqwen/qwen-vl-ocr | 38.19K tokens | $0.04469074 | $0.07448457 | — |
Qwen3-VL-Plusqwen/qwen3-vl-plusLong prompts cost more: over 32K prompt tokens, $0.2234537 in / $2.234537 out; over 128K prompt tokens, $0.4469074 in / $4.46907401 out, per 1M tokens. | 256K tokens | from $0.14896913 | from $1.48969134 |
|
Qwen3.5-OCRqwen/qwen3.5-ocr | 64K tokens | $0.07448457 | $0.29793827 | — |
Qwen3.5-Omni-Plusqwen/qwen3.5-omni-plus | 256K tokens | $1.04278394 | $5.95876534 | — |
Qwen3.7-Flashqwen/qwen3.7-flashLong prompts cost more: over 32K prompt tokens, $0.08938148 in / $0.35752592 out; over 256K prompt tokens, $0.17876296 in / $0.71505184 out, per 1M tokens. | 1M tokens | from $0.02979383 | from $0.11917531 |
|
Qwen3.7-Maxqwen/qwen3.7-max | 1M tokens | $1.7876296 | $5.36288881 |
|
Qwen3.7-Plusqwen/qwen3.7-plusLong prompts cost more: over 256K prompt tokens, $0.71505184 in / $2.86020737 out, per 1M tokens. | 1M tokens | from $0.23835061 | from $0.95340246 |
|
Qwen3.7-Text-Embedding-Flashqwen/qwen3.7-text-embedding-flashEmbeddings | 128K tokens | $0.01862114 | $0.00 | — |
Qwen3.8-2.4T-A95Bqwen/qwen3.8-2.4t-a95b | 1M tokens | $1.7876296 | $5.36288881 |
|
Qwen3.8-Flashqwen/qwen3.8-flash | 1M tokens | $0.11917531 | $0.40221666 |
|
Qwen3.8-Maxqwen/qwen3.8-max | 1M tokens | $1.7876296 | $5.36288881 |
|
Qwen3.8-Omni-Flashqwen/qwen3.8-omni-flash | 1M tokens | $0.11917531 | $0.40221666 |
|
Qwen4-Maxqwen/qwen4-max | 1M tokens | $1.48969134 | $4.46907401 |
|
伶鹊-对话分析-Flashqwen/tongyi-xiaomi-analysis-flash | 32K tokens | $0.02979383 | $0.05958765 |
|
伶鹊-对话分析-Proqwen/tongyi-xiaomi-analysis-pro | 32K tokens | $0.14896913 | $0.40221666 |
|
Step 5 Previewstepfun/step-5-preview | 1M tokens | $1.04278394 | $2.97938267 |
|
Hy-MT2-Litetencent/hy-mt2-lite | 8K tokens | $0.04469074 | $0.17876296 | — |
Hy-MT2-Plustencent/hy-mt2-plus | 8K tokens | $0.07448457 | $0.29793827 | — |
Hy-MT2-Protencent/hy-mt2-pro | 8K tokens | $0.07448457 | $0.29793827 | — |
Hy-Roletencent/hy-role | 32K tokens | $0.35752592 | $1.43010368 | — |
Hy-Role-Latesttencent/hy-role-latest | 32K tokens | $0.35752592 | $1.43010368 | — |
Hy3tencent/hy3 | 256K tokens | $0.14896913 | $0.59587653 |
|
Hy4tencent/hy4 | 1.02M tokens | $0.4469074 | $1.3407222 |
|
Hy4 flashtencent/hy4-flash | 1.02M tokens | $0.03724228 | $0.14896913 |
|
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | 1.02M tokens | $0.14896913 | $0.29793827 |
|
MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | 1.02M tokens | $0.4469074 | $0.8938148 |
|
GLM-4-Flash-250414zai-org/glm-4-flash-250414 | 128K tokens | $0.00 | $0.00 | — |
GLM-5zai-org/glm-5Long prompts cost more: from 32K prompt tokens, $0.8938148 in / $3.27732094 out, per 1M tokens. | 200K tokens | from $0.59587653 | from $2.6814444 |
|
GLM-5-Turbozai-org/glm-5-turboLong prompts cost more: from 32K prompt tokens, $1.04278394 in / $3.87319747 out, per 1M tokens. | 200K tokens | from $0.74484567 | from $3.27732094 |
|
GLM-5.1zai-org/glm-5.1Long prompts cost more: from 32K prompt tokens, $1.19175307 in / $4.17113574 out, per 1M tokens. | 200K tokens | from $0.8938148 | from $3.57525921 |
|
GLM-5.2zai-org/glm-5.2 | 1M tokens | $1.19175307 | $4.17113574 |
|
GLM-5.3zai-org/glm-5.3 | 1.02M tokens | $1.19175307 | $4.17113574 |
|
GLM-5.3-Flashzai-org/glm-5.3-flash | 800K tokens | $0.11917531 | $0.41711357 |
|
GLM-5.3-FlashXzai-org/glm-5.3-flashx | 1.02M tokens | $0.29793827 | $1.04278394 |
|
GLM-5.3-FlashX-Legalzai-org/glm-5.3-flashx-legal | 1M tokens | $0.29793827 | $1.04278394 |
|
No model matches your search.
About these prices
- You pay for the tokens you send at the input price, and the tokens the model writes at the output price — a reasoning model’s reasoning included.
- These are Token Gear’s prices, the ones in effect now. Signed in, the console’s Models page shows the prices your account pays.
- A price marked “from” is the lowest: a long prompt costs more, as its row says. Where the prompt cache is priced apart, its row says what the part of a prompt read from or written to the cache costs. Your account’s data constraints keep requests away from providers that do not meet them (Privacy Policy §4).
- Prices exclude taxes unless your contract says otherwise (Terms §4). Credit is added by an administrator under an offline contract: there is no self-service top-up or card payment (contact sales). How retries and streams cut short are billed is in the API docs.