One transparent rate card
Language-model prices are USD per 1 million tokens and include XinoAPI gateway service. Cache-hit input is shown separately where configured. Prices marked pending need account-level confirmation.
| Model | Input / cache hit (per 1M) | Output (per 1M) | Context |
|---|---|---|---|
DeepSeek V4-Flash deepseek-v4-flash-0731 | Pending verification | Pending verification | Confirm in console |
DeepSeek V4-Pro deepseek-v4-pro-0813 | Pending verification | Pending verification | Confirm in console |
Qwen 3.7 Flash qwen3.7-flash | $0.0301 | $0.1205 | Confirm in console |
Qwen 3.7 Plus qwen3.7-plus | $0.3011 Cache hit $0.0602 | $1.2045 | Confirm in console |
Qwen 3.8 Max qwen3.8-max | $1.8068 Cache hit $0.2259 | $5.4205 | Confirm in console |
GLM-5.3 glm-5.3 | Pending verification | Pending verification | Confirm in console |
GLM-5.3-Flash glm-5.3-flash | Pending verification | Pending verification | Confirm in console |
GLM-5.2 glm-5.2 | $1.2045 Cache hit $0.3011 | $4.2159 | Confirm in console |
Kimi K2.7 Code kimi-k2.7-code | $0.9787 Cache hit $0.1957 | $4.0653 | Confirm in console |
MiniMax M3 MiniMax-M3 | $0.3162 Cache hit $0.0632 | $1.2648 | Confirm in console |
Doubao Seed 2.1 Turbo doubao-seed-2-1-turbo-260628 | $0.4517 Cache hit $0.0903 | $2.2585 | Confirm in console |
On mobile, swipe the table horizontally to view all input, output, and context rates.
Public pricing snapshot: 2026-10-14. Pending prices require account quote confirmation. Context, output limits, and parameter support must be confirmed for the selected route. Full pricing.
Video generation · limited availability
Video generation is billed by successful output seconds or generation tokens, depending on the provider. Failed generations are not billed where the upstream provider reports no billable output.
| Model | Meter | Account quote | Output |
|---|---|---|---|
MiniMax H3 MiniMax-H3 | Confirm task meter | Confirm account quote | Limited availability |
Seedance 2.0 doubao-seedance-2-0-260128 | Confirm task meter | Confirm account quote | Limited availability |
Seedance 2.5 doubao-seedance-2-5-260628 | Confirm task meter | Confirm account quote | Limited availability |
On mobile, swipe the table horizontally to compare meters, rates, and output limits.
Limited availability: these IDs appear in the public pricing snapshot, which does not verify task API access or billing units. Confirm access, task endpoints, meter, output limits, and account quote before purchasing credits or submitting a job.
What real workloads cost
Monthly volumes assume 30 days and uncached input. Cost = input millions × input rate + output millions × output rate; confirm pending prices before estimating.
Chat Assistant · 500 requests/day
Code Assistant · 10 devs
Document Summary · bulk
Reasoning Workflow
Free account, pay as you go
Create an account without a monthly fee. Add at least $20 in credits when you are ready to make API calls; credits do not expire.
Scale without hidden cuts
The API Console displays each model's current rate. Enterprise pricing is reviewed against actual monthly usage, model mix, capacity, and support needs.
For enterprise volumes (>$5K/month), invoicing, or dedicated routing, contact sales.
Pricing is not the whole decision
XinoAPI is designed for users outside mainland China and routes requests to third-party model providers with different data policies.
| Control | Current policy | Why it matters |
|---|---|---|
| Mainland China access | Not permitted for registration, purchase, dashboard access, or API use. | Maintains a clear cross-border service boundary for Chinese LLM inference export. |
| Prompt/response storage | No plaintext content retention by default; billing uses metadata such as model, tokens, status, and timestamps. | Reduces data exposure for production agent and application workloads. |
| Provider terms | Users must comply with each upstream provider's terms, data policy, and regional restrictions. | XinoAPI is a gateway, not the developer or operator of upstream models. |
| Sensitive data | Use the Privacy SDK for local PII and secret redaction before sending prompts. | Provider-side policies vary, especially for models operated in mainland China. |
See the Compliance Center and Security Whitepaper for the full policy.
Pricing questions, answered
pip install xinoapi-privacy.deepseek-v4-flash-0731 for general tasks and deepseek-v4-pro-0813 for planning and code review. These are the active API model IDs.