Language rates · 20% off official
Website offer = official price × 0.8 for input, output and displayed cache-hit token rates. Original currencies, regions and tiers apply. A dash means the official rate is unconfirmed; no offer is calculated.
| Model | Our input / cache hit (per 1M) | Our output (per 1M) | Conditions & source |
|---|---|---|---|
DeepSeek V4-Flash deepseek-v4-flash-0731 | — | — | Official price unconfirmedDeepSeek direct APIThe current page lists a newer Flash version; the price of this dated gateway route is unconfirmed.Official source |
DeepSeek V4-Pro deepseek-v4-pro-0813 | USD 0.528Official | USD 1.584Official | Off-peakDeepSeek direct APIPeak: Mon-Fri 01:00-04:00 and 06:00-10:00 UTC, excluding Chinese public holidays. Other times are off-peak.Official source |
DeepSeek V4-Pro deepseek-v4-pro-0813 | USD 1.056Official | USD 3.168Official | PeakDeepSeek direct APIPeak: Mon-Fri 01:00-04:00 and 06:00-10:00 UTC, excluding Chinese public holidays. Other times are off-peak.Official source |
Qwen 3.8 Max qwen3.8-max | USD 1.6Official | USD 4.8Official | Input up to 1M tokensSingapore / International; standard list priceCache pricing is separate; see the official caching rules.Official source |
Qwen 3.7 Plus qwen3.7-plus | USD 0.32Official | USD 1.28Official | Input up to 256K tokensSingapore / International; standard list pricePromotional discounts excluded. The input tier determines the rate for the whole request; cache pricing is separate.Official source |
Qwen 3.7 Plus qwen3.7-plus | USD 0.96Official | USD 3.84Official | Input over 256K, up to 1M tokensSingapore / International; standard list pricePromotional discounts excluded. The input tier determines the rate for the whole request; cache pricing is separate.Official source |
Qwen 3.7 Flash qwen3.7-flash | USD 0.024Official | USD 0.104Official | Input up to 32K tokensSingapore / International; standard list priceThe input tier determines the rate for the whole request; cache pricing is separate.Official source |
Qwen 3.7 Flash qwen3.7-flash | USD 0.08Official | USD 0.32Official | Input over 32K, up to 256K tokensSingapore / International; standard list priceThe input tier determines the rate for the whole request; cache pricing is separate.Official source |
Qwen 3.7 Flash qwen3.7-flash | USD 0.16Official | USD 0.64Official | Input over 256K, up to 1M tokensSingapore / International; standard list priceThe input tier determines the rate for the whole request; cache pricing is separate.Official source |
GLM-5.3-Flash glm-5.3-flash | USD 0.12Official | USD 0.4Official | Standard inferenceZ.AI direct APITool usage and cache storage follow separate provider rules.Official source |
GLM-5.3 glm-5.3 | USD 1.12Official | USD 3.52Official | Standard inferenceZ.AI direct APITool usage and cache storage follow separate provider rules.Official source |
GLM-5.2 glm-5.2 | USD 1.12Official | USD 3.52Official | Standard inferenceZ.AI direct APITool usage and cache storage follow separate provider rules.Official source |
Kimi K3 k3 | CNY 16Official | CNY 80Official | Standard inferenceKimi direct APIOfficial model ID: kimi-k3; confirm the gateway alias mapping. Cache writes: CNY 20 / 1M (5-minute TTL) or CNY 40 / 1M (1-hour TTL).Official source |
Kimi K3 256 k3-256 | — | — | Official price unconfirmedKimi direct APIThis gateway alias is not identified in the official price table; confirm the underlying model before quoting.Official source |
Kimi K2.7 Code kimi-k2.7-code | CNY 5.2Official | CNY 21.6Official | Standard inferenceKimi direct APIOfficial source |
Kimi K2.7 Code Highspeed kimi-k2.7-code-highspeed | CNY 10.4Official | CNY 43.2Official | Highspeed inferenceKimi direct APIOfficial source |
MiniMax M3 MiniMax-M3 | USD 0.24Official | USD 0.96Official | Input up to 512K tokensMiniMax direct API; Standard tierPriority-tier pricing is excluded.Official source |
MiniMax M3 MiniMax-M3 | USD 0.48Official | USD 1.92Official | Input over 512K tokensMiniMax direct API; Standard tierPriority-tier pricing is excluded.Official source |
MiniMax M2.7 MiniMax-M2.7 | — | — | Official price unconfirmedMiniMax direct APIThis older model is absent from the current official price table; confirm its active quote.Official source |
MiniMax M2.7 Highspeed MiniMax-M2.7-highspeed | — | — | Official price unconfirmedMiniMax direct APIThis older model is absent from the current official price table; confirm its active quote.Official source |
Doubao Seed 2.1 Pro doubao-seed-2-1-pro-260628 | CNY 4.8Official | CNY 24Official | Non-audio input up to 1024K tokensVolcengine Ark; standard online inferenceProvider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate.Official source |
Doubao Seed 2.1 Turbo doubao-seed-2-1-turbo-260628 | CNY 2.4Official | CNY 12Official | Non-audio input up to 256K tokensVolcengine Ark; standard online inferenceProvider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate.Official source |
Doubao Seed Evolving doubao-seed-evolving-latest-version | CNY 4.8Official | CNY 24Official | Non-audio input up to 1024K tokensVolcengine Ark; standard online inferenceProvider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate.Official source |
MiMo V2.5 Pro mimo-v2.5-pro | USD 0.348Official | USD 0.696Official | Standard inferenceMiMo overseas; real-time inferenceProvider deprecation scheduled for 2026-10-21 at 10:00 Beijing time. Confirm replacement and gateway availability before use.Official source |
MiMo V2.5 mimo-v2.5 | USD 0.112Official | USD 0.224Official | Standard inferenceMiMo overseas; real-time inferenceProvider deprecation scheduled for 2026-10-21 at 10:00 Beijing time. Confirm replacement and gateway availability before use.Official source |
Hunyuan HY3 hy3 | CNY 0.8Official | CNY 3.2Official | Standard inferenceTencent TokenHub; SingaporeOfficial source |
Hunyuan HY3 Preview hy3-preview | — | — | Official price unconfirmedTencent TokenHubProvider retirement announced for 2026-08-31; no current official quote for this preview route.Official source |
ERNIE 5.1 ernie-5.1 | — | — | Official price unconfirmedBaidu QianfanA current official input/output price for this exact model has not been verified.Official source |
ERNIE 5.0 ernie-5.0 | USD 1.12Official | USD 4.48Official | Published offerBaidu international published offerPublished on the international offer page; region, promotion and account terms may differ.Official source |
Swipe horizontally to compare input, output, conditions and official sources.
Official reference prices checked: 2026-10-20. Website offer = official rate × 0.8, per 1 million tokens in the original currency and tier; no currency conversion. Includes displayed input, output and cache-hit token rates. Tool, cache-write, storage and media fees are excluded. Live account billing has not been synchronized by this website change; confirm your API Console quote before purchasing credits.
Video generation · limited availability
Video billing units, account quotes, and failed-task charges require route-specific confirmation. Confirm the meter and failure policy before purchasing credits or submitting jobs.
| Model | Meter | Account quote | Output |
|---|---|---|---|
Seedance 2.5 doubao-seedance-2-5-260628 | 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 2.0 Mini doubao-seedance-2-0-mini-260615 | Confirm task meter | Confirm account quote | Limited availability |
MiniMax H3 MiniMax-H3 | 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.
Image generation · public listings
Confirm route access, billing units, supported inputs, and account quotes before use.
| Model | Meter | Account quote |
|---|---|---|
Seedream 5.0 doubao-seedream-5-0-260128 | Confirm media meter | Confirm account quote |
Seedream 5.0 Pro doubao-seedream-5-0-pro-260628 | Confirm media meter | Confirm account quote |
Qwen Image 3.0 Pro qwen-image-3.0-pro | Confirm media meter | Confirm account quote |
Wan 2.7 Image Pro wan2.7-image-pro | Confirm media meter | Confirm account quote |
Illustrative monthly offers
Estimates use the website offer (official rate × 0.8), 30 days and uncached input. Ranges reflect official tiers; your actual request tier and time band determine the applicable rate. These are estimates, not confirmed account charges.
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.3D generation · public listings
Confirm route access, billing units, supported inputs, and account quotes before use.
| Model | Meter | Account quote |
|---|---|---|
Seed3D 2.0 doubao-seed3d-2-0-260328 | Confirm media meter | Confirm account quote |