{ "name": "XinoAPI model and pricing facts", "updated": "2026-10-20", "website": "https://xinoapi.com/", "api_base_url": "https://api.xinoapi.com/v1", "audience": "Developers and businesses outside mainland China", "regional_restriction": "The paid API service is not available to users located in mainland China.", "billing": { "currency": "USD", "minimum_topup_usd": 20, "pricing_policy": "Website language offers are 20% below reviewed official token prices, preserving original currencies and tiers. Stored gateway USD fields remain historical observations, not the website offer. Actual account billing requires Console confirmation.", "topup_fee_percent": 0, "payment_processor": "Stripe", "website_discount_percent": 20, "website_discount_scope": "Reviewed official language input, output and cache-hit token rates, in the original currency and tier. Website offer only; live account billing must be confirmed in API Console. Media and ancillary fees excluded." }, "data_handling": { "plaintext_prompt_response_retention_default": false, "billing_logs": [ "model", "token_counts", "status", "latency", "timestamps" ], "upstream_provider_terms_apply": true, "privacy_sdk": "https://pypi.org/project/xinoapi-privacy/" }, "models": [ { "id": "deepseek-v4-flash-0731", "display_name": "DeepSeek V4-Flash", "provider": "DeepSeek", "workload": "General chat and code edits", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "pending_verification", "input_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "output_usd_per_1m": null, "verified_at": "2026-10-20", "slug": "deepseek-v4-flash-0731", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 3 }, "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://api-docs.deepseek.com/quick_start/pricing/", "currency": "USD", "scope": "DeepSeek direct API", "provider_model": "deepseek-v4-flash-0731", "tiers": [], "notes": "The current page lists a newer Flash version; the price of this dated gateway route is unconfirmed." } }, { "id": "deepseek-v4-pro-0813", "display_name": "DeepSeek V4-Pro", "provider": "DeepSeek", "workload": "Planning and code review", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "pending_verification", "input_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "output_usd_per_1m": null, "verified_at": "2026-10-20", "slug": "deepseek-v4-pro-0813", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 3 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://api-docs.deepseek.com/quick_start/pricing/", "currency": "USD", "scope": "DeepSeek direct API", "provider_model": "deepseek-v4-pro-0813", "tiers": [ { "condition": "Off-peak", "input_per_1m": 0.66, "output_per_1m": 1.98, "cache_hit_per_1m": 0.022 }, { "condition": "Peak", "input_per_1m": 1.32, "output_per_1m": 3.96, "cache_hit_per_1m": 0.044 } ], "notes": "Peak: Mon-Fri 01:00-04:00 and 06:00-10:00 UTC, excluding Chinese public holidays. Other times are off-peak." } }, { "id": "qwen3.8-max", "display_name": "Qwen 3.8 Max", "provider": "Alibaba Qwen", "workload": "Evaluate for complex tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 1.8068, "cache_hit_input_usd_per_1m": 0.2259, "output_usd_per_1m": 5.4205, "verified_at": "2026-10-20", "slug": "qwen3-8-max", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.903409091, "completion_ratio": 3 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "currency": "USD", "scope": "Singapore / International; standard list price", "provider_model": "qwen3.8-max", "tiers": [ { "condition": "Input up to 1M tokens", "input_per_1m": 2, "output_per_1m": 6, "cache_hit_per_1m": null } ], "notes": "Cache pricing is separate; see the official caching rules." } }, { "id": "qwen3.7-plus", "display_name": "Qwen 3.7 Plus", "provider": "Alibaba Qwen", "workload": "General language tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 0.3011, "cache_hit_input_usd_per_1m": 0.0602, "output_usd_per_1m": 1.2045, "verified_at": "2026-10-20", "slug": "qwen3-7-plus", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.150568182, "completion_ratio": 4 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "currency": "USD", "scope": "Singapore / International; standard list price", "provider_model": "qwen3.7-plus", "tiers": [ { "condition": "Input up to 256K tokens", "input_per_1m": 0.4, "output_per_1m": 1.6, "cache_hit_per_1m": null }, { "condition": "Input over 256K, up to 1M tokens", "input_per_1m": 1.2, "output_per_1m": 4.8, "cache_hit_per_1m": null } ], "notes": "Promotional discounts excluded. The input tier determines the rate for the whole request; cache pricing is separate." } }, { "id": "qwen3.7-flash", "display_name": "Qwen 3.7 Flash", "provider": "Alibaba Qwen", "workload": "Cost-sensitive chat", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 0.0301, "cache_hit_input_usd_per_1m": null, "output_usd_per_1m": 0.1205, "verified_at": "2026-10-20", "slug": "qwen3-7-flash", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.015056818, "completion_ratio": 4 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "currency": "USD", "scope": "Singapore / International; standard list price", "provider_model": "qwen3.7-flash", "tiers": [ { "condition": "Input up to 32K tokens", "input_per_1m": 0.03, "output_per_1m": 0.13, "cache_hit_per_1m": null }, { "condition": "Input over 32K, up to 256K tokens", "input_per_1m": 0.1, "output_per_1m": 0.4, "cache_hit_per_1m": null }, { "condition": "Input over 256K, up to 1M tokens", "input_per_1m": 0.2, "output_per_1m": 0.8, "cache_hit_per_1m": null } ], "notes": "The input tier determines the rate for the whole request; cache pricing is separate." } }, { "id": "glm-5.3-flash", "display_name": "GLM-5.3-Flash", "provider": "Zhipu GLM", "workload": "Evaluate for agent workflows", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "pending_verification", "input_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "output_usd_per_1m": null, "verified_at": "2026-10-20", "slug": "glm-5-3-flash", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 3.333333333333 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.z.ai/guides/overview/pricing", "currency": "USD", "scope": "Z.AI direct API", "provider_model": "glm-5.3-flash", "tiers": [ { "condition": "Standard inference", "input_per_1m": 0.15, "output_per_1m": 0.5, "cache_hit_per_1m": 0.03 } ], "notes": "Tool usage and cache storage follow separate provider rules." } }, { "id": "glm-5.3", "display_name": "GLM-5.3", "provider": "Zhipu GLM", "workload": "Evaluate for reasoning", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "pending_verification", "input_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "output_usd_per_1m": null, "verified_at": "2026-10-20", "slug": "glm-5-3", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 3.142857142857 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.z.ai/guides/overview/pricing", "currency": "USD", "scope": "Z.AI direct API", "provider_model": "glm-5.3", "tiers": [ { "condition": "Standard inference", "input_per_1m": 1.4, "output_per_1m": 4.4, "cache_hit_per_1m": 0.26 } ], "notes": "Tool usage and cache storage follow separate provider rules." } }, { "id": "glm-5.2", "display_name": "GLM-5.2", "provider": "Zhipu GLM", "workload": "General language tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 1.2045, "cache_hit_input_usd_per_1m": 0.3011, "output_usd_per_1m": 4.2159, "verified_at": "2026-10-20", "slug": "glm-5-2", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.602272727, "completion_ratio": 3.5 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.z.ai/guides/overview/pricing", "currency": "USD", "scope": "Z.AI direct API", "provider_model": "glm-5.2", "tiers": [ { "condition": "Standard inference", "input_per_1m": 1.4, "output_per_1m": 4.4, "cache_hit_per_1m": 0.26 } ], "notes": "Tool usage and cache storage follow separate provider rules." } }, { "id": "k3", "display_name": "Kimi K3", "provider": "Moonshot Kimi", "category": "language", "slug": "k3", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 1.505681818, "completion_ratio": 5 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 3.0114, "output_usd_per_1m": 15.0568, "cache_hit_input_usd_per_1m": 0.3011, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://platform.kimi.com/docs/pricing/chat", "currency": "CNY", "scope": "Kimi direct API", "provider_model": "kimi-k3", "tiers": [ { "condition": "Standard inference", "input_per_1m": 20, "output_per_1m": 100, "cache_hit_per_1m": 2 } ], "notes": "Official model ID: kimi-k3; confirm the gateway alias mapping. Cache writes: CNY 20 / 1M (5-minute TTL) or CNY 40 / 1M (1-hour TTL)." } }, { "id": "k3-256", "display_name": "Kimi K3 256", "provider": "Moonshot Kimi", "category": "language", "slug": "k3-256", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 1.505681818, "completion_ratio": 5 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 3.0114, "output_usd_per_1m": 15.0568, "cache_hit_input_usd_per_1m": 0.3011, "billing_unit": "1M tokens", "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://platform.kimi.com/docs/pricing/chat", "currency": "CNY", "scope": "Kimi direct API", "provider_model": "k3-256", "tiers": [], "notes": "This gateway alias is not identified in the official price table; confirm the underlying model before quoting." } }, { "id": "kimi-k2.7-code", "display_name": "Kimi K2.7 Code", "provider": "Moonshot Kimi", "workload": "Coding tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 0.9787, "cache_hit_input_usd_per_1m": 0.1957, "output_usd_per_1m": 4.0653, "verified_at": "2026-10-20", "slug": "kimi-k2-7-code", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.489347, "completion_ratio": 4.153846 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://platform.kimi.com/docs/pricing/chat", "currency": "CNY", "scope": "Kimi direct API", "provider_model": "kimi-k2.7-code", "tiers": [ { "condition": "Standard inference", "input_per_1m": 6.5, "output_per_1m": 27, "cache_hit_per_1m": 1.3 } ], "notes": "" } }, { "id": "kimi-k2.7-code-highspeed", "display_name": "Kimi K2.7 Code Highspeed", "provider": "Moonshot Kimi", "category": "language", "slug": "kimi-k2-7-code-highspeed", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.978693, "completion_ratio": 4.153846 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 1.9574, "output_usd_per_1m": 8.1307, "cache_hit_input_usd_per_1m": 0.3915, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://platform.kimi.com/docs/pricing/chat", "currency": "CNY", "scope": "Kimi direct API", "provider_model": "kimi-k2.7-code-highspeed", "tiers": [ { "condition": "Highspeed inference", "input_per_1m": 13, "output_per_1m": 54, "cache_hit_per_1m": 2.6 } ], "notes": "" } }, { "id": "MiniMax-M3", "display_name": "MiniMax M3", "provider": "MiniMax", "workload": "General language tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 0.3162, "cache_hit_input_usd_per_1m": 0.0632, "output_usd_per_1m": 1.2648, "verified_at": "2026-10-20", "slug": "minimax-m3", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.1581, "completion_ratio": 4 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://platform.minimax.io/docs/pricing/overview", "currency": "USD", "scope": "MiniMax direct API; Standard tier", "provider_model": "MiniMax-M3", "tiers": [ { "condition": "Input up to 512K tokens", "input_per_1m": 0.3, "output_per_1m": 1.2, "cache_hit_per_1m": 0.06 }, { "condition": "Input over 512K tokens", "input_per_1m": 0.6, "output_per_1m": 2.4, "cache_hit_per_1m": 0.12 } ], "notes": "Priority-tier pricing is excluded." } }, { "id": "MiniMax-M2.7", "display_name": "MiniMax M2.7", "provider": "MiniMax", "category": "language", "slug": "minimax-m2-7", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.1581, "completion_ratio": 4 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.3162, "output_usd_per_1m": 1.2648, "cache_hit_input_usd_per_1m": 0.0632, "billing_unit": "1M tokens", "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://platform.minimax.io/docs/pricing/overview", "currency": "USD", "scope": "MiniMax direct API", "provider_model": "MiniMax-M2.7", "tiers": [], "notes": "This older model is absent from the current official price table; confirm its active quote." } }, { "id": "MiniMax-M2.7-highspeed", "display_name": "MiniMax M2.7 Highspeed", "provider": "MiniMax", "category": "language", "slug": "minimax-m2-7-highspeed", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.31619, "completion_ratio": 4 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.6324, "output_usd_per_1m": 2.5295, "cache_hit_input_usd_per_1m": 0.0632, "billing_unit": "1M tokens", "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://platform.minimax.io/docs/pricing/overview", "currency": "USD", "scope": "MiniMax direct API", "provider_model": "MiniMax-M2.7-highspeed", "tiers": [], "notes": "This older model is absent from the current official price table; confirm its active quote." } }, { "id": "doubao-seed-2-1-pro-260628", "display_name": "Doubao Seed 2.1 Pro", "provider": "ByteDance Seed / Doubao", "category": "language", "slug": "doubao-seed-2-1-pro-260628", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.4517, "completion_ratio": 5 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.9034, "output_usd_per_1m": 4.517, "cache_hit_input_usd_per_1m": 0.1807, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.volcengine.com/docs/ark/model-pricing?lang=zh", "currency": "CNY", "scope": "Volcengine Ark; standard online inference", "provider_model": "doubao-seed-2.1-pro", "tiers": [ { "condition": "Non-audio input up to 1024K tokens", "input_per_1m": 6, "output_per_1m": 30, "cache_hit_per_1m": 1.2 } ], "notes": "Provider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate." } }, { "id": "doubao-seed-2-1-turbo-260628", "display_name": "Doubao Seed 2.1 Turbo", "provider": "ByteDance Seed / Doubao", "workload": "General language tasks", "status": "listed_in_public_pricing", "context": null, "max_output": null, "capabilities": null, "pricing_type": "public_snapshot", "input_usd_per_1m": 0.4517, "cache_hit_input_usd_per_1m": 0.0903, "output_usd_per_1m": 2.2585, "verified_at": "2026-10-20", "slug": "doubao-seed-2-1-turbo-260628", "category": "language", "integration_status": "public_listing", "integration_pattern": "Chat completions", "billing_unit": "1M tokens", "preview": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.22585, "completion_ratio": 5 }, "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.volcengine.com/docs/ark/model-pricing?lang=zh", "currency": "CNY", "scope": "Volcengine Ark; standard online inference", "provider_model": "doubao-seed-2.1-turbo", "tiers": [ { "condition": "Non-audio input up to 256K tokens", "input_per_1m": 3, "output_per_1m": 15, "cache_hit_per_1m": 0.6 } ], "notes": "Provider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate." } }, { "id": "doubao-seed-evolving-latest-version", "display_name": "Doubao Seed Evolving", "provider": "ByteDance Seed / Doubao", "category": "language", "slug": "doubao-seed-evolving-latest-version", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.4517, "completion_ratio": 5 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.9034, "output_usd_per_1m": 4.517, "cache_hit_input_usd_per_1m": 0.1807, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://docs.volcengine.com/docs/ark/model-pricing?lang=zh", "currency": "CNY", "scope": "Volcengine Ark; standard online inference", "provider_model": "doubao-seed-evolving", "tiers": [ { "condition": "Non-audio input up to 1024K tokens", "input_per_1m": 6, "output_per_1m": 30, "cache_hit_per_1m": 1.2 } ], "notes": "Provider-family reference; confirm the dated gateway route. Audio, cache storage, batch and low-latency rates are separate." } }, { "id": "mimo-v2.5-pro", "display_name": "MiMo V2.5 Pro", "provider": "Xiaomi MiMo", "category": "language", "slug": "mimo-v2-5-pro", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.22585, "completion_ratio": 2 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.4517, "output_usd_per_1m": 0.9034, "cache_hit_input_usd_per_1m": 0.0038, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go", "currency": "USD", "scope": "MiMo overseas; real-time inference", "provider_model": "mimo-v2.5-pro", "tiers": [ { "condition": "Standard inference", "input_per_1m": 0.435, "output_per_1m": 0.87, "cache_hit_per_1m": 0.0036 } ], "notes": "Provider deprecation scheduled for 2026-10-21 at 10:00 Beijing time. Confirm replacement and gateway availability before use." } }, { "id": "mimo-v2.5", "display_name": "MiMo V2.5", "provider": "Xiaomi MiMo", "category": "language", "slug": "mimo-v2-5", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.07528, "completion_ratio": 2 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.1506, "output_usd_per_1m": 0.3011, "cache_hit_input_usd_per_1m": 0.003, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go", "currency": "USD", "scope": "MiMo overseas; real-time inference", "provider_model": "mimo-v2.5", "tiers": [ { "condition": "Standard inference", "input_per_1m": 0.14, "output_per_1m": 0.28, "cache_hit_per_1m": 0.0028 } ], "notes": "Provider deprecation scheduled for 2026-10-21 at 10:00 Beijing time. Confirm replacement and gateway availability before use." } }, { "id": "hy3", "display_name": "Hunyuan HY3", "provider": "Tencent Hunyuan", "category": "language", "slug": "hy3", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.075284091, "completion_ratio": 4 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.1506, "output_usd_per_1m": 0.6023, "cache_hit_input_usd_per_1m": 0.0376, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://cloud.tencent.com/document/product/1823/130055", "currency": "CNY", "scope": "Tencent TokenHub; Singapore", "provider_model": "hy3", "tiers": [ { "condition": "Standard inference", "input_per_1m": 1, "output_per_1m": 4, "cache_hit_per_1m": 0.25 } ], "notes": "" } }, { "id": "hy3-preview", "display_name": "Hunyuan HY3 Preview", "provider": "Tencent Hunyuan", "category": "language", "slug": "hy3-preview", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 0.075284091, "completion_ratio": 4 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "public_snapshot", "input_usd_per_1m": 0.1506, "output_usd_per_1m": 0.6023, "cache_hit_input_usd_per_1m": 0.0376, "billing_unit": "1M tokens", "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://cloud.tencent.com/announce/detail/2391", "currency": "CNY", "scope": "Tencent TokenHub", "provider_model": "hy3-preview", "tiers": [], "notes": "Provider retirement announced for 2026-08-31; no current official quote for this preview route." } }, { "id": "ernie-5.1", "display_name": "ERNIE 5.1", "provider": "Baidu ERNIE", "category": "language", "slug": "ernie-5-1", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 1 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "pending_verification", "input_usd_per_1m": null, "output_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "billing_unit": "1M tokens", "official_pricing": { "status": "unconfirmed", "reviewed_at": "2026-10-20", "source_url": "https://cloud.baidu.com/product/wenxinworkshop", "currency": "CNY", "scope": "Baidu Qianfan", "provider_model": "ernie-5.1", "tiers": [], "notes": "A current official input/output price for this exact model has not been verified." } }, { "id": "ernie-5.0", "display_name": "ERNIE 5.0", "provider": "Baidu ERNIE", "category": "language", "slug": "ernie-5-0", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 37.5, "completion_ratio": 1 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Language and coding workflows", "integration_pattern": "Chat completions", "pricing_type": "pending_verification", "input_usd_per_1m": null, "output_usd_per_1m": null, "cache_hit_input_usd_per_1m": null, "billing_unit": "1M tokens", "official_pricing": { "status": "published", "reviewed_at": "2026-10-20", "source_url": "https://intl.cloud.baidu.com/en/product/qianfan_campaign.html", "currency": "USD", "scope": "Baidu international published offer", "provider_model": "ernie-5.0", "tiers": [ { "condition": "Published offer", "input_per_1m": 1.4, "output_per_1m": 5.6, "cache_hit_per_1m": null } ], "notes": "Published on the international offer page; region, promotion and account terms may differ." } } ], "video_models": [ { "id": "doubao-seedance-2-5-260628", "display_name": "Seedance 2.5", "status": "limited_availability", "pricing_type": "confirm_account_quote", "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration.", "slug": "doubao-seedance-2-5-260628", "category": "video", "provider": "ByteDance Seedance", "workload": "Asynchronous video generation", "integration_status": "limited_availability", "integration_pattern": "Asynchronous jobs", "billing_unit": null, "capabilities": null, "preview": null, "verified_at": "2026-10-20", "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 5.26989, "completion_ratio": 1 }, "context": null, "max_output": null }, { "id": "doubao-seedance-2-0-260128", "display_name": "Seedance 2.0", "status": "limited_availability", "pricing_type": "confirm_account_quote", "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration.", "slug": "doubao-seedance-2-0-260128", "category": "video", "provider": "ByteDance Seedance", "workload": "Asynchronous video generation", "integration_status": "limited_availability", "integration_pattern": "Asynchronous jobs", "billing_unit": null, "capabilities": null, "preview": null, "verified_at": "2026-10-20", "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 3.46307, "completion_ratio": 1 }, "context": null, "max_output": null }, { "id": "doubao-seedance-2-0-mini-260615", "display_name": "Seedance 2.0 Mini", "provider": "ByteDance Seedance", "category": "video", "slug": "doubao-seedance-2-0-mini-260615", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 0, "model_price": 0, "model_ratio": 1.73153, "completion_ratio": 1 }, "integration_status": "limited_availability", "status": "limited_availability", "context": null, "max_output": null, "workload": "Asynchronous video generation", "integration_pattern": "Asynchronous jobs", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." }, { "id": "MiniMax-H3", "display_name": "MiniMax H3", "status": "limited_availability", "pricing_type": "confirm_account_quote", "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration.", "slug": "minimax-h3", "category": "video", "provider": "MiniMax", "workload": "Asynchronous video generation", "integration_status": "limited_availability", "integration_pattern": "Asynchronous jobs", "billing_unit": null, "capabilities": null, "preview": null, "verified_at": "2026-10-20", "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.1264725, "model_ratio": 0, "completion_ratio": 0 }, "context": null, "max_output": null } ], "pages": { "pricing": "https://xinoapi.com/pricing", "docs": "https://xinoapi.com/docs", "agents": "https://xinoapi.com/agents", "compliance": "https://xinoapi.com/compliance", "security": "https://xinoapi.com/security", "deepseek_api": "https://xinoapi.com/deepseek-api", "qwen_api": "https://xinoapi.com/qwen-api", "chinese_llm_api": "https://xinoapi.com/chinese-llm-api", "openrouter_alternative": "https://xinoapi.com/openrouter-alternative", "cc_switch_xinoapi": "https://xinoapi.com/cc-switch-xinoapi", "models": "https://xinoapi.com/models", "video_api": "https://xinoapi.com/video-api", "image_api": "https://xinoapi.com/image-api" }, "agent_integrations": { "cc_switch": { "docs": "https://www.ccswitch.io/zh/docs?section=getting-started", "xinoapi_setup": { "provider_type": "OpenAI compatible", "base_url": "https://api.xinoapi.com/v1", "recommended_models": [ "deepseek-v4-flash-0731", "deepseek-v4-pro-0813" ] } }, "xinoapi_docs": "https://xinoapi.com/docs#agent-integrations" }, "privacy": "XinoAPI does not retain plaintext prompts or responses by default. Billing and abuse-prevention systems use metadata such as model, token counts, status, latency, and timestamps.", "positioning": "Chinese AI gateway for global developers outside mainland China, with OpenAI-compatible language routes, asynchronous video-generation routes, Stripe billing, transparent pricing, and privacy-conscious defaults.", "model_id_guidance": "Use the explicit IDs in this catalog; validate access with your account before production. Native Anthropic bridging is planned and not available for production.", "public_price_version": "a42d372ccf0b5dd13ecf71203521f9d2", "pricing_source": "https://api.xinoapi.com/api/pricing", "verification_scope": "Public pricing listing observed on 2026-10-20; authenticated access, capabilities, media meters and final billed amounts are not verified.", "image_models": [ { "id": "doubao-seedream-5-0-260128", "display_name": "Seedream 5.0", "provider": "ByteDance Seed / Doubao", "category": "image", "slug": "doubao-seedream-5-0-260128", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.039522, "model_ratio": 0, "completion_ratio": 0 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Image generation", "integration_pattern": "Confirm image route endpoint", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." }, { "id": "doubao-seedream-5-0-pro-260628", "display_name": "Seedream 5.0 Pro", "provider": "ByteDance Seed / Doubao", "category": "image", "slug": "doubao-seedream-5-0-pro-260628", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.0474285, "model_ratio": 0, "completion_ratio": 0 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Image generation", "integration_pattern": "Confirm image route endpoint", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." }, { "id": "qwen-image-3.0-pro", "display_name": "Qwen Image 3.0 Pro", "provider": "Alibaba Qwen", "category": "image", "slug": "qwen-image-3-0-pro", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "image-generation", "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.079065, "model_ratio": 0, "completion_ratio": 0 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Image generation", "integration_pattern": "Confirm image route endpoint", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." }, { "id": "wan2.7-image-pro", "display_name": "Wan 2.7 Image Pro", "provider": "Alibaba Qwen", "category": "image", "slug": "wan2-7-image-pro", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "image-generation", "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.076545, "model_ratio": 0, "completion_ratio": 0 }, "integration_status": "public_listing", "status": "listed_in_public_pricing", "context": null, "max_output": null, "workload": "Image generation", "integration_pattern": "Confirm image route endpoint", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." } ], "image_catalog_status": "public_listings_unverified", "provider_logos": { "DeepSeek": "/assets/logos/deepseek.svg", "Alibaba Qwen": "/assets/logos/qwen.svg", "Zhipu GLM": "/assets/logos/zai.svg", "Moonshot Kimi": "/assets/logos/kimi.svg", "MiniMax": "/assets/logos/minimax.svg", "ByteDance Seed / Doubao": "/assets/logos/doubao.svg", "ByteDance Seedance": "/assets/logos/bytedance.svg", "Tencent Hunyuan": "/assets/logos/hunyuan.svg", "Xiaomi MiMo": "/assets/logos/xiaomimimo.svg", "Baidu ERNIE": "/assets/logos/baidu.svg" }, "other_models": [ { "id": "doubao-seed3d-2-0-260328", "display_name": "Seed3D 2.0", "provider": "ByteDance Seed / Doubao", "category": "3d", "slug": "doubao-seed3d-2-0-260328", "verified_at": "2026-10-20", "preview": null, "capabilities": null, "public_endpoint_types": [ "openai" ], "public_quote": { "quota_type": 1, "model_price": 0.379428, "model_ratio": 0, "completion_ratio": 0 }, "integration_status": "limited_availability", "status": "limited_availability", "context": null, "max_output": null, "workload": "3D asset generation", "integration_pattern": "Confirm 3D task API", "pricing_type": "confirm_account_quote", "billing_unit": null, "notes": "Public listing only. Confirm endpoint, access, meter, parameters and account quote before integration." } ], "featured_model_ids": [ "qwen3.8-max", "glm-5.3-flash", "k3" ], "public_catalog_sha256": "9fdd05a012d8c84f6c5a195c580f81f79ff689bb05bb5fb276c5c5568a48cd99", "provider_releases": [ { "display_name": "MiMo V2.6 Pro / Flash", "provider": "Xiaomi MiMo", "official_url": "https://mimo.mi.com/docs/en-US/news/latest/v2-6", "reviewed_at": "2026-10-20", "status": "not_in_public_gateway_listing" }, { "display_name": "MiniMax M3.1 Flash", "provider": "MiniMax", "official_url": "https://platform.minimax.io/docs/guides/models-intro", "reviewed_at": "2026-10-20", "status": "not_in_public_gateway_listing" } ], "official_pricing_reviewed_at": "2026-10-20" }