RelayRouter151 models. Every modality.
Access leading AI models through a single OpenAI-compatible endpoint. Mainstream model groups are priced 30% or more below official list prices, no platform fee.
Not sure which one to pick? How to access GPT-5.5 and Gemini 3.5 with one API key
151
Total models
143
Text / LLM
8
Image generation
0
Video generation
7
Providers
Models are sold through pools: same API, different routes and rates. Each pool settles at a fixed rate of yuan per $1 of standard provider usage, versus a market rate of about ¥6.8 per $1, so a ¥2 pool means you pay roughly 2/6.8 of standard cost. Direct-route pools bill an explicit per-million-token price instead. Pick the pool when you create an API key in the console. Failed requests are never billed.
18 pools · 261 models
GPTOpenAI
¥0.5 / $1~93% below market ¥6.8/$12 models
codex-auto-reviewtext¥0.5/$gpt-5.2text¥0.5/$gpt-5.3-codex-sparktext¥0.5/$gpt-5.4text¥0.5/$gpt-5.4-minitext¥0.5/$gpt-5.5text¥0.5/$gpt-5.6-lunatext¥0.5/$gpt-5.6-soltext¥0.5/$gpt-5.6-terratext¥0.5/$gpt-image-1image¥0.5/$gpt-image-1.5image¥0.5/$gpt-image-2image¥0.5/$
Codex FastOpenAI
¥0.75 / $1~89% below market ¥6.8/$14 models
gpt-5.2text¥0.75/$gpt-5.2-2025-12-11text¥0.75/$gpt-5.2-chat-latesttext¥0.75/$gpt-5.2-protext¥0.75/$gpt-5.2-pro-2025-12-11text¥0.75/$gpt-5.3-codextext¥0.75/$gpt-5.3-codex-sparktext¥0.75/$gpt-5.4text¥0.75/$gpt-5.4-2026-03-05text¥0.75/$gpt-5.4-minitext¥0.75/$gpt-5.5text¥0.75/$gpt-image-1image¥0.75/$gpt-image-1.5image¥0.75/$gpt-image-2image¥0.75/$
DeepSeekAnthropic
Per-token pricedirect route, near official list2 models
deepseek-v4-flashtext$0.162 in · $0.324 out / 1Mdeepseek-v4-protext$1.94 in · $3.88 out / 1M
KimiOpenAI
Per-token pricedirect route, near official list1 models
kimi-k2.6text$0.456 in · $1.92 out / 1M
MiniMaxOpenAI
Per-token pricedirect route, near official list1 models
MiniMax-M2.7text$0.259 in · $1.04 out / 1M
Z.aiOpenAI
Per-token pricedirect route, near official list2 models
glm-5.1text$0.918 in · $2.89 out / 1Mglm-5.2text$1.67 in · $5.25 out / 1M
Claude FastAnthropic
¥1.2 / $1~82% below market ¥6.8/$21 models
claude-3-5-haiku-20241022text¥1.2/$claude-3-5-sonnet-20240620text¥1.2/$claude-3-5-sonnet-20241022text¥1.2/$claude-3-7-sonnet-20250219text¥1.2/$claude-haiku-4-5-20251001text¥1.2/$claude-haiku-4-5-20251001-thinkingtext¥1.2/$claude-opus-4-1-20250805text¥1.2/$claude-opus-4-20250514text¥1.2/$claude-opus-4-5-20251101text¥1.2/$claude-opus-4-5-20251101-thinkingtext¥1.2/$claude-opus-4-6text¥1.2/$claude-opus-4-6-thinkingtext¥1.2/$claude-opus-4-7text¥1.2/$claude-opus-4-8text¥1.2/$claude-sonnet-4-20250514text¥1.2/$claude-sonnet-4-5text¥1.2/$claude-sonnet-4-5-20250929text¥1.2/$claude-sonnet-4-5-20250929-thinkingtext¥1.2/$claude-sonnet-4-6text¥1.2/$claude-sonnet-4-6-thinkingtext¥1.2/$claude-sonnet-5text¥1.2/$
GPT ImageOpenAI
¥1.25 / $1~82% below market ¥6.8/$3 models
gpt-image-1image¥1.25/$gpt-image-1.5image¥1.25/$gpt-image-2image¥1.25/$
ClaudeAnthropic
¥2 / $1~71% below market ¥6.8/$9 models
claude-fable-5text¥2/$claude-haiku-4-5-20251001text¥2/$claude-opus-4-5-20251101text¥2/$claude-opus-4-6text¥2/$claude-opus-4-7text¥2/$claude-opus-4-8text¥2/$claude-sonnet-4-5-20250929text¥2/$claude-sonnet-4-6text¥2/$claude-sonnet-5text¥2/$
Claude Code FastAnthropic
¥2.3 / $1~66% below market ¥6.8/$17 models
claude-3-5-haiku-20241022text¥2.3/$claude-3-5-sonnet-20240620text¥2.3/$claude-3-5-sonnet-20241022text¥2.3/$claude-3-7-sonnet-20250219text¥2.3/$claude-fable-5text¥2.3/$claude-haiku-4-5text¥2.3/$claude-haiku-4-5-20251001text¥2.3/$claude-opus-4-1-20250805text¥2.3/$claude-opus-4-20250514text¥2.3/$claude-opus-4-5-20251101text¥2.3/$claude-opus-4-6text¥2.3/$claude-opus-4-7text¥2.3/$claude-opus-4-8text¥2.3/$claude-sonnet-4-20250514text¥2.3/$claude-sonnet-4-5-20250929text¥2.3/$claude-sonnet-4-6text¥2.3/$claude-sonnet-5text¥2.3/$
GPT AzureOpenAI
¥2.38 / $1~65% below market ¥6.8/$88 models
codex-auto-reviewtext¥2.38/$dall-e-3image¥2.38/$davinci-002text¥2.38/$gpt-3.5-turbo-1106text¥2.38/$gpt-4text¥2.38/$gpt-4-0125-previewtext¥2.38/$gpt-4-0613text¥2.38/$gpt-4-1106-previewtext¥2.38/$gpt-4-32ktext¥2.38/$gpt-4-32k-0613text¥2.38/$gpt-4-alltext¥2.38/$gpt-4-turbotext¥2.38/$gpt-4-turbo-2024-04-09text¥2.38/$gpt-4-turbo-previewtext¥2.38/$gpt-4-vision-previewtext¥2.38/$gpt-4.1text¥2.38/$gpt-4.1-2025-04-14text¥2.38/$gpt-4.1-minitext¥2.38/$gpt-4.1-mini-2025-04-14text¥2.38/$gpt-4.1-nanotext¥2.38/$gpt-4.1-nano-2025-04-14text¥2.38/$gpt-4otext¥2.38/$gpt-4o-2024-05-13text¥2.38/$gpt-4o-2024-08-06text¥2.38/$
Gemini FastGemini
¥2.72 / $1~60% below market ¥6.8/$28 models
gemini-2.0-flashtext¥2.72/$gemini-2.5-flashtext¥2.72/$gemini-2.5-flash-imageimage¥2.72/$gemini-2.5-flash-litetext¥2.72/$gemini-2.5-flash-lite-preview-09-2025text¥2.72/$gemini-2.5-flash-nothinkingtext¥2.72/$gemini-2.5-flash-thinkingtext¥2.72/$gemini-2.5-protext¥2.72/$gemini-2.5-pro-nothinkingtext¥2.72/$gemini-2.5-pro-thinkingtext¥2.72/$gemini-3-flash-previewtext¥2.72/$gemini-3-flash-preview-thinkingtext¥2.72/$gemini-3-pro-image-previewimage¥2.72/$gemini-3-pro-previewtext¥2.72/$gemini-3-pro-preview-thinkingtext¥2.72/$gemini-3.1-flash-image-previewimage¥2.72/$gemini-3.1-flash-lite-previewtext¥2.72/$gemini-3.1-pro-preview-mediumtext¥2.72/$gemini-3.5-flashtext¥2.72/$gemini-flash-latesttext¥2.72/$gemini-flash-latest-nothinkingtext¥2.72/$gemini-flash-latest-thinkingtext¥2.72/$gemini-flash-lite-latesttext¥2.72/$gemini-flash-lite-latest-nothinkingtext¥2.72/$
OpenAI StableOpenAI
¥2.8 / $1~59% below market ¥6.8/$12 models
gpt-4o-minitext¥2.8/$gpt-5text¥2.8/$gpt-5.1text¥2.8/$gpt-5.1-codextext¥2.8/$gpt-5.2text¥2.8/$gpt-5.2-codextext¥2.8/$gpt-5.3-chattext¥2.8/$gpt-5.3-codextext¥2.8/$gpt-5.4text¥2.8/$gpt-5.4-minitext¥2.8/$gpt-5.4-nanotext¥2.8/$gpt-5.5text¥2.8/$
Claude AWSAnthropic
¥5.4 / $1~21% below market ¥6.8/$9 models
claude-fable-5text¥5.4/$claude-haiku-4-5-20251001text¥5.4/$claude-opus-4-5-20251101text¥5.4/$claude-opus-4-6text¥5.4/$claude-opus-4-7text¥5.4/$claude-opus-4-8text¥5.4/$claude-sonnet-4-5-20250929text¥5.4/$claude-sonnet-4-6text¥5.4/$claude-sonnet-5text¥5.4/$
Claude HermesAnthropic
¥5.4 / $1~21% below market ¥6.8/$20 models
claude-fable-5text¥5.4/$claude-haiku-4-5text¥5.4/$claude-haiku-4-5-20251001text¥5.4/$claude-haiku-4-5-20251001-thinkingtext¥5.4/$claude-opus-4-1-20250805text¥5.4/$claude-opus-4-5text¥5.4/$claude-opus-4-5-20251101text¥5.4/$claude-opus-4-5-20251101-thinkingtext¥5.4/$claude-opus-4-6text¥5.4/$claude-opus-4-6-thinkingtext¥5.4/$claude-opus-4-6-v1text¥5.4/$claude-opus-4-7text¥5.4/$claude-opus-4-8text¥5.4/$claude-sonnet-4-20250514text¥5.4/$claude-sonnet-4-5text¥5.4/$claude-sonnet-4-5-20250929text¥5.4/$claude-sonnet-4-5-20250929-thinkingtext¥5.4/$claude-sonnet-4-6text¥5.4/$claude-sonnet-4-6-thinkingtext¥5.4/$claude-sonnet-5text¥5.4/$
Gemini Vertex OfficialGemini
¥5.4 / $1~21% below market ¥6.8/$8 models
gemini-2.0-flashtext¥5.4/$gemini-2.5-flashtext¥5.4/$gemini-2.5-flash-imageimage¥5.4/$gemini-2.5-protext¥5.4/$gemini-3-flash-previewtext¥5.4/$gemini-3-pro-previewtext¥5.4/$gemini-3.1-flash-imageimage¥5.4/$gemini-3.5-flashtext¥5.4/$
Claude FailoverAnthropic
¥5.5 / $1~19% below market ¥6.8/$6 models
claude-fable-5text¥5.5/$claude-haiku-4-5text¥5.5/$claude-opus-4-6text¥5.5/$claude-opus-4-7text¥5.5/$claude-opus-4-8text¥5.5/$claude-sonnet-4-6text¥5.5/$
Claude Official APIAnthropic
¥5.5 / $1~19% below market ¥6.8/$8 models
claude-haiku-4-5text¥5.5/$claude-haiku-4-5-20251001text¥5.5/$claude-opus-4-5text¥5.5/$claude-opus-4-6text¥5.5/$claude-opus-4-7text¥5.5/$claude-opus-4-8text¥5.5/$claude-sonnet-4-5text¥5.5/$claude-sonnet-4-6text¥5.5/$
Rates are indicative and settle from your prepaid balance; the exact rate at request time is authoritative and shown in the console. The same model can appear in several pools at different rates, pick the pool that fits your stability and budget needs. Market rate ¥6.8/$ is a reference only.
All available models on RelayRouter
- DeepSeek pool (Anthropic): direct route billed per million tokens at prices near the official list. Models: deepseek-v4-flash ($0.162 per 1M input, $0.324 per 1M output), deepseek-v4-pro ($1.94 per 1M input, $3.88 per 1M output)
- Claude Fast pool (Anthropic): settlement rate ¥1.2 per $1 of standard usage, about 82% below the ¥6.8/$ market reference. Models: claude-3-5-haiku-20241022, claude-3-5-sonnet-20240620, claude-3-5-sonnet-20241022, claude-3-7-sonnet-20250219, claude-haiku-4-5-20251001, claude-haiku-4-5-20251001-thinking, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-opus-4-5-20251101, claude-opus-4-5-20251101-thinking, claude-opus-4-6, claude-opus-4-6-thinking, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-20250514, claude-sonnet-4-5, claude-sonnet-4-5-20250929, claude-sonnet-4-5-20250929-thinking, claude-sonnet-4-6, claude-sonnet-4-6-thinking, claude-sonnet-5
- Claude pool (Anthropic): settlement rate ¥2 per $1 of standard usage, about 71% below the ¥6.8/$ market reference. Models: claude-fable-5, claude-haiku-4-5-20251001, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-sonnet-5
- Claude Code Fast pool (Anthropic): settlement rate ¥2.3 per $1 of standard usage, about 66% below the ¥6.8/$ market reference. Models: claude-3-5-haiku-20241022, claude-3-5-sonnet-20240620, claude-3-5-sonnet-20241022, claude-3-7-sonnet-20250219, claude-fable-5, claude-haiku-4-5, claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-20250514, claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-sonnet-5
- Claude AWS pool (Anthropic): settlement rate ¥5.4 per $1 of standard usage, about 21% below the ¥6.8/$ market reference. Models: claude-fable-5, claude-haiku-4-5-20251001, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-sonnet-5
- Claude Hermes pool (Anthropic): settlement rate ¥5.4 per $1 of standard usage, about 21% below the ¥6.8/$ market reference. Models: claude-fable-5, claude-haiku-4-5, claude-haiku-4-5-20251001, claude-haiku-4-5-20251001-thinking, claude-opus-4-1-20250805, claude-opus-4-5, claude-opus-4-5-20251101, claude-opus-4-5-20251101-thinking, claude-opus-4-6, claude-opus-4-6-thinking, claude-opus-4-6-v1, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-20250514, claude-sonnet-4-5, claude-sonnet-4-5-20250929, claude-sonnet-4-5-20250929-thinking, claude-sonnet-4-6, claude-sonnet-4-6-thinking, claude-sonnet-5
- Claude Failover pool (Anthropic): settlement rate ¥5.5 per $1 of standard usage, about 19% below the ¥6.8/$ market reference. Models: claude-fable-5, claude-haiku-4-5, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-6
- Claude Official API pool (Anthropic): settlement rate ¥5.5 per $1 of standard usage, about 19% below the ¥6.8/$ market reference. Models: claude-haiku-4-5, claude-haiku-4-5-20251001, claude-opus-4-5, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-5, claude-sonnet-4-6
- Gemini Fast pool (Gemini): settlement rate ¥2.72 per $1 of standard usage, about 60% below the ¥6.8/$ market reference. Models: gemini-2.0-flash, gemini-2.5-flash, gemini-2.5-flash-image, gemini-2.5-flash-lite, gemini-2.5-flash-lite-preview-09-2025, gemini-2.5-flash-nothinking, gemini-2.5-flash-thinking, gemini-2.5-pro, gemini-2.5-pro-nothinking, gemini-2.5-pro-thinking, gemini-3-flash-preview, gemini-3-flash-preview-thinking, gemini-3-pro-image-preview, gemini-3-pro-preview, gemini-3-pro-preview-thinking, gemini-3.1-flash-image-preview, gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview-medium, gemini-3.5-flash, gemini-flash-latest, gemini-flash-latest-nothinking, gemini-flash-latest-thinking, gemini-flash-lite-latest, gemini-flash-lite-latest-nothinking, gemini-flash-lite-latest-thinking, gemini-pro-latest, gemini-pro-latest-thinking, gemini-robotics-er-1.5-preview
- Gemini Vertex Official pool (Gemini): settlement rate ¥5.4 per $1 of standard usage, about 21% below the ¥6.8/$ market reference. Models: gemini-2.0-flash, gemini-2.5-flash, gemini-2.5-flash-image, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview, gemini-3.1-flash-image, gemini-3.5-flash
- GPT pool (OpenAI): settlement rate ¥0.5 per $1 of standard usage, about 93% below the ¥6.8/$ market reference. Models: codex-auto-review, gpt-5.2, gpt-5.3-codex-spark, gpt-5.4, gpt-5.4-mini, gpt-5.5, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-image-1, gpt-image-1.5, gpt-image-2
- Codex Fast pool (OpenAI): settlement rate ¥0.75 per $1 of standard usage, about 89% below the ¥6.8/$ market reference. Models: gpt-5.2, gpt-5.2-2025-12-11, gpt-5.2-chat-latest, gpt-5.2-pro, gpt-5.2-pro-2025-12-11, gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.4, gpt-5.4-2026-03-05, gpt-5.4-mini, gpt-5.5, gpt-image-1, gpt-image-1.5, gpt-image-2
- Kimi pool (OpenAI): direct route billed per million tokens at prices near the official list. Models: kimi-k2.6 ($0.456 per 1M input, $1.92 per 1M output)
- MiniMax pool (OpenAI): direct route billed per million tokens at prices near the official list. Models: MiniMax-M2.7 ($0.259 per 1M input, $1.04 per 1M output)
- Z.ai pool (OpenAI): direct route billed per million tokens at prices near the official list. Models: glm-5.1 ($0.918 per 1M input, $2.89 per 1M output), glm-5.2 ($1.67 per 1M input, $5.25 per 1M output)
- GPT Image pool (OpenAI): settlement rate ¥1.25 per $1 of standard usage, about 82% below the ¥6.8/$ market reference. Models: gpt-image-1, gpt-image-1.5, gpt-image-2
- GPT Azure pool (OpenAI): settlement rate ¥2.38 per $1 of standard usage, about 65% below the ¥6.8/$ market reference. Models: codex-auto-review, dall-e-3, davinci-002, gpt-3.5-turbo-1106, gpt-4, gpt-4-0125-preview, gpt-4-0613, gpt-4-1106-preview, gpt-4-32k, gpt-4-32k-0613, gpt-4-all, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-turbo-preview, gpt-4-vision-preview, gpt-4.1, gpt-4.1-2025-04-14, gpt-4.1-mini, gpt-4.1-mini-2025-04-14, gpt-4.1-nano, gpt-4.1-nano-2025-04-14, gpt-4o, gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-4o-all, gpt-4o-mini, gpt-4o-mini-2024-07-18, gpt-5, gpt-5-2025-08-07, gpt-5-chat, gpt-5-chat-2025-08-07, gpt-5-chat-latest, gpt-5-codex, gpt-5-mini, gpt-5-mini-2025-08-07, gpt-5-nano, gpt-5-nano-2025-08-07, gpt-5-pro, gpt-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat, gpt-5.1-chat-2025-11-13, gpt-5.1-chat-latest, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-max-2025-12-04, gpt-5.1-codex-mini, gpt-5.2, gpt-5.2-2025-12-11, gpt-5.2-chat, gpt-5.2-chat-2025-12-11, gpt-5.2-chat-latest, gpt-5.2-codex, gpt-5.2-codex-2026-01-14, gpt-5.2-pro, gpt-5.2-pro-2025-12-11, gpt-5.3-chat, gpt-5.3-chat-2026-03-03, gpt-5.3-chat-latest, gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.4, gpt-5.4-2026-03-05, gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-nano, gpt-5.4-nano-2026-03-17, gpt-5.4-pro, gpt-5.4-pro-2026-03-05, gpt-5.5, gpt-image-1, gpt-image-1.5, gpt-image-2, o1, o1-2024-12-17, o1-mini, o1-mini-2024-09-12, o1-preview, o1-preview-2024-09-12, o3, o3-2025-04-16, o3-mini, o3-mini-2025-01-31, o3-pro, o3-pro-2025-06-10, o4-mini, o4-mini-2025-04-16
- OpenAI Stable pool (OpenAI): settlement rate ¥2.8 per $1 of standard usage, about 59% below the ¥6.8/$ market reference. Models: gpt-4o-mini, gpt-5, gpt-5.1, gpt-5.1-codex, gpt-5.2, gpt-5.2-codex, gpt-5.3-chat, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5