{"models":[{"id":"qwen3.6-plus","provider":"Alibaba","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":65536,"input_per_1m":0.5,"output_per_1m":3.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"qwen3.6-plus from Alibaba, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"qwen3.7-max","provider":"Alibaba","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":65536,"input_per_1m":2.5,"output_per_1m":7.5,"cache_read_per_1m":0.35,"vision":false,"reasoning":true,"tool_call":true,"description":"qwen3.7-max from Alibaba, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"qwen3.7-plus","provider":"Alibaba","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":64000,"input_per_1m":0.32,"output_per_1m":1.28,"cache_read_per_1m":0.12,"vision":true,"reasoning":true,"tool_call":true,"description":"qwen3.7-plus from Alibaba, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"qwen3.8-flash","provider":"Alibaba","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":0.15,"output_per_1m":0.47,"cache_read_per_1m":0.016,"vision":false,"reasoning":true,"tool_call":true,"description":"qwen3.8-flash from Alibaba, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"qwen3.8-max","provider":"Alibaba","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":2.0,"output_per_1m":6.0,"cache_read_per_1m":0.7,"vision":true,"reasoning":true,"tool_call":true,"description":"qwen3.8-max from Alibaba, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"RouterPlex bills $2 input / $6 output per 1M tokens, Alibaba's list price. Cached prompt tokens are billed at $0.70 per 1M, above Alibaba's own cache-hit tier: our cache price is set from what our upstream charges us for a cached token, so it does not follow the lab's rate.","long_context_pricing":null,"sale":null},{"id":"claude-fable-5","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":10.0,"output_per_1m":50.0,"cache_read_per_1m":1.2,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-fable-5 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-haiku-4-5","provider":"Anthropic","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":64000,"input_per_1m":1.0,"output_per_1m":5.0,"cache_read_per_1m":0.08,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-haiku-4-5 from Anthropic, 256K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-opus-4-6","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":25.0,"cache_read_per_1m":0.425,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-opus-4-6 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-opus-4-7","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":25.0,"cache_read_per_1m":0.425,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-opus-4-7 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-opus-4-8","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":25.0,"cache_read_per_1m":0.425,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-opus-4-8 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-opus-5","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":25.0,"cache_read_per_1m":0.425,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-opus-5 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-opus-5-5","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":4.0,"output_per_1m":20.0,"cache_read_per_1m":0.425,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-opus-5-5 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-sonnet-4-6","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":64000,"input_per_1m":3.0,"output_per_1m":15.0,"cache_read_per_1m":0.25,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-sonnet-4-6 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"claude-sonnet-5","provider":"Anthropic","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":2.0,"output_per_1m":10.0,"cache_read_per_1m":0.3,"vision":true,"reasoning":true,"tool_call":true,"description":"claude-sonnet-5 from Anthropic, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Anthropic list price. The $2 input / $10 output rate was announced as introductory through August 31, 2026; Anthropic has since made it the standard price and cancelled the planned rise to $3 / $15. Cached prompt tokens are billed at $0.30 per 1M (Anthropic lists $0.20): our rate is set from what our upstream charges us, not from the lab's cache price.","long_context_pricing":null,"sale":null},{"id":"doubao-seed-2.0-code","provider":"ByteDance","mode":"chat","context":"200K","context_tokens":200000,"max_output_tokens":131072,"input_per_1m":0.67,"output_per_1m":3.36,"cache_read_per_1m":0.085,"vision":true,"reasoning":true,"tool_call":true,"description":"doubao-seed-2.0-code from ByteDance, 200K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"doubao-seed-2.0-pro","provider":"ByteDance","mode":"chat","context":"128K","context_tokens":128000,"max_output_tokens":128000,"input_per_1m":0.67,"output_per_1m":3.36,"cache_read_per_1m":0.085,"vision":true,"reasoning":true,"tool_call":true,"description":"doubao-seed-2.0-pro from ByteDance, 128K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"deepseek-v4-flash","provider":"DeepSeek","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":384000,"input_per_1m":0.18,"output_per_1m":0.73,"cache_read_per_1m":0.065,"vision":false,"reasoning":true,"tool_call":true,"description":"deepseek-v4-flash from DeepSeek, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":"DeepSeek has retired V4 Flash: the id is now served by DeepSeek-V4.1-Flash and billed at the Flash price, $0.15 input / $0.60 output per 1M tokens off-peak and double that during peak hours (01:00-04:00 and 06:00-10:00 UTC, Monday to Friday). RouterPlex bills the same flat rate as deepseek-v4.1-flash, the time-weighted average of the two, so you are never billed by the clock.","long_context_pricing":null,"sale":null},{"id":"deepseek-v4-flash-vision-exp","provider":"DeepSeek","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":384000,"input_per_1m":0.22,"output_per_1m":0.66,"cache_read_per_1m":0.007,"vision":true,"reasoning":true,"tool_call":true,"description":"deepseek-v4-flash-vision-exp from DeepSeek, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"DeepSeek has retired this preview: it now serves the id with DeepSeek-V4.1-Flash and bills it at the Flash price ($0.15 input / $0.60 output per 1M tokens off-peak, double during peak hours). RouterPlex serves it through a separate upstream and bills a flat $0.22 input / $0.66 output per 1M tokens at all hours. For the same model at DeepSeek's time-weighted rate, use deepseek-v4.1-flash.","long_context_pricing":null,"sale":null},{"id":"deepseek-v4-pro","provider":"DeepSeek","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":384000,"input_per_1m":0.8,"output_per_1m":2.39,"cache_read_per_1m":0.21,"vision":false,"reasoning":true,"tool_call":true,"description":"deepseek-v4-pro from DeepSeek, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":"DeepSeek prices this model by time of day: $0.66 input / $1.98 output per 1M tokens off-peak, and double that during peak hours (01:00-04:00 and 06:00-10:00 UTC, Monday to Friday). RouterPlex bills a single flat rate of $0.80 / $2.39 in between -- the time-weighted average of the two -- so you are never billed by the clock. Cached prompt tokens are billed at $0.21 per 1M, set from what our upstream charges us rather than DeepSeek's cache-hit rate.","long_context_pricing":null,"sale":null},{"id":"deepseek-v4.1-flash","provider":"DeepSeek","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":384000,"input_per_1m":0.18,"output_per_1m":0.73,"cache_read_per_1m":0.065,"vision":true,"reasoning":true,"tool_call":true,"description":"deepseek-v4.1-flash from DeepSeek, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"DeepSeek prices this model by time of day: $0.15 input / $0.60 output per 1M tokens off-peak, and double that during peak hours (01:00-04:00 and 06:00-10:00 UTC, Monday to Friday). RouterPlex bills a single flat rate in between -- the time-weighted average of the two -- so you are never billed by the clock and never pay the peak rate for off-peak work.","long_context_pricing":null,"sale":null},{"id":"deepseek-v4.1-flash-abliterated","provider":"DeepSeek","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.5,"output_per_1m":1.5,"cache_read_per_1m":0.07,"vision":true,"reasoning":true,"tool_call":true,"description":"deepseek-v4.1-flash-abliterated from DeepSeek, 1M context, reasoning, tool calling, vision.","pricing_basis":"public_reference","pricing_note":"An abliterated build of DeepSeek V4.1 Flash: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.","long_context_pricing":null,"sale":{"previous_input_per_1m":0.7,"previous_output_per_1m":1.2,"previous_cache_read_per_1m":0.2,"input_discount_pct":29,"output_discount_pct":0,"cache_read_discount_pct":65,"since":"2026-10-30"}},{"id":"gemini-2.5-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.3,"output_per_1m":2.5,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-2.5-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-2.5-flash-lite","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.1,"output_per_1m":0.4,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-2.5-flash-lite from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-3-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.5,"output_per_1m":3.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-3.1-flash-lite","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.25,"output_per_1m":1.5,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.1-flash-lite from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-3.1-pro","provider":"Google","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":65536,"input_per_1m":2.0,"output_per_1m":12.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.1-pro from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-3.5-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":65536,"input_per_1m":1.5,"output_per_1m":9.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.5-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gemini-3.6-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.75,"output_per_1m":3.75,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.6-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.","long_context_pricing":null,"sale":null},{"id":"gemini-3.7-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.75,"output_per_1m":3.75,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.7-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.","long_context_pricing":null,"sale":null},{"id":"gemini-3.8-flash","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":0.75,"output_per_1m":3.75,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-3.8-flash from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.","long_context_pricing":null,"sale":null},{"id":"gemini-4-argon","provider":"Google","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":65536,"input_per_1m":2.0,"output_per_1m":10.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"gemini-4-argon from Google, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Google introductory pricing through November 30, 2026; the published rate becomes $4 input / $20 output per 1M tokens on December 1, 2026. Thinking tokens are billed as output. Set reasoning_effort to low, medium (default) or high. Output is capped at 64K tokens per response.","long_context_pricing":null,"sale":null},{"id":"gemma-4-26b-abliterated","provider":"Google","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":8192,"input_per_1m":0.25,"output_per_1m":0.75,"cache_read_per_1m":null,"vision":true,"reasoning":false,"tool_call":true,"description":"gemma-4-26b-abliterated from Google, 256K context, tool calling, vision.","pricing_basis":"public_reference","pricing_note":"A refusal-removed fine-tune of Google's Gemma 4 26B: the open weights retrained so the model stops refusing, served on RouterPlex through a third-party host. This is not Google's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.","long_context_pricing":null,"sale":null},{"id":"LongCat-2.0","provider":"LongCat","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":0.3,"output_per_1m":1.2,"cache_read_per_1m":0.11,"vision":false,"reasoning":true,"tool_call":true,"description":"LongCat-2.0 from LongCat, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":"Current official limited-time LongCat API rate; the published regular rate is $0.75 input / $2.95 output per 1M tokens.","long_context_pricing":null,"sale":null},{"id":"muse-spark-1.2-contributor","provider":"Meta","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.1,"output_per_1m":0.2,"cache_read_per_1m":0.008,"vision":false,"reasoning":true,"tool_call":false,"description":"muse-spark-1.2-contributor from Meta, 1M context, reasoning.","pricing_basis":"vendor_list","pricing_note":"Contributor edition. Meta prices this at $0.10 input / $0.20 output per 1M tokens instead of the standard Muse Spark rate of $1.25 / $4.25, in exchange for the right to use the prompts and completions you send to it to train future Meta models. Do not send confidential, personal, or client-owned material to this model. It is never used as a default or a fallback -- it runs only when you name it explicitly. Tool calling is not supported on RouterPlex, and Meta limits availability to certain regions.","long_context_pricing":null,"sale":null},{"id":"muse-spark-1.3-contributor","provider":"Meta","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.1,"output_per_1m":0.2,"cache_read_per_1m":0.008,"vision":false,"reasoning":true,"tool_call":false,"description":"muse-spark-1.3-contributor from Meta, 1M context, reasoning.","pricing_basis":"vendor_list","pricing_note":"Contributor edition. Meta prices this at $0.10 input / $0.20 output per 1M tokens instead of the standard Muse Spark rate of $1.25 / $4.25, in exchange for the right to use the prompts and completions you send to it to train future Meta models. Do not send confidential, personal, or client-owned material to this model. It is never used as a default or a fallback -- it runs only when you name it explicitly. Tool calling is not supported on RouterPlex, and Meta limits availability to certain regions.","long_context_pricing":null,"sale":null},{"id":"MiniMax-M2.7","provider":"MiniMax","mode":"chat","context":"196K","context_tokens":196000,"max_output_tokens":131072,"input_per_1m":0.3,"output_per_1m":1.2,"cache_read_per_1m":0.025,"vision":false,"reasoning":true,"tool_call":true,"description":"MiniMax-M2.7 from MiniMax, 196K context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"MiniMax-M2.7-highspeed","provider":"MiniMax","mode":"chat","context":"196K","context_tokens":196000,"max_output_tokens":131072,"input_per_1m":0.6,"output_per_1m":2.4,"cache_read_per_1m":0.05,"vision":false,"reasoning":true,"tool_call":true,"description":"MiniMax-M2.7-highspeed from MiniMax, 196K context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"MiniMax-M3","provider":"MiniMax","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":512000,"input_per_1m":0.3,"output_per_1m":1.2,"cache_read_per_1m":0.03,"vision":true,"reasoning":true,"tool_call":true,"description":"MiniMax-M3 from MiniMax, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"MiniMax-M3-highspeed","provider":"MiniMax","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":512000,"input_per_1m":0.45,"output_per_1m":1.8,"cache_read_per_1m":0.06,"vision":true,"reasoning":true,"tool_call":true,"description":"MiniMax-M3-highspeed from MiniMax, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"MiniMax-M3.1-flash","provider":"MiniMax","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":524288,"input_per_1m":0.15,"output_per_1m":0.6,"cache_read_per_1m":0.028,"vision":true,"reasoning":true,"tool_call":true,"description":"MiniMax-M3.1-flash from MiniMax, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"kimi-k2.6","provider":"Moonshot","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":262144,"input_per_1m":0.95,"output_per_1m":4.0,"cache_read_per_1m":0.08,"vision":true,"reasoning":true,"tool_call":true,"description":"kimi-k2.6 from Moonshot, 256K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"RouterPlex bills $0.95 input / $4 output per 1M tokens, Moonshot's list price. Cached prompt tokens are billed at $0.08 per 1M (Moonshot lists $0.16): our cache price is set from what our upstream charges us, not from the lab's rate.","long_context_pricing":null,"sale":null},{"id":"kimi-k2.7","provider":"Moonshot","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":262144,"input_per_1m":0.95,"output_per_1m":4.0,"cache_read_per_1m":0.225,"vision":true,"reasoning":true,"tool_call":true,"description":"kimi-k2.7 from Moonshot, 256K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"RouterPlex bills $0.95 input / $4 output per 1M tokens, Moonshot's list price. Cached prompt tokens are billed at $0.225 per 1M (Moonshot lists $0.19): our cache price is set from what our upstream charges us, not from the lab's rate.","long_context_pricing":null,"sale":null},{"id":"kimi-k3","provider":"Moonshot","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":3.0,"output_per_1m":15.0,"cache_read_per_1m":0.7,"vision":true,"reasoning":true,"tool_call":true,"description":"kimi-k3 from Moonshot, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"RouterPlex bills $3 input / $15 output per 1M tokens, Moonshot's list price. Cached prompt tokens are billed at $0.70 per 1M, not Moonshot's published $0.30 cache-hit rate: our cache price is set from what our upstream charges us for a cached token, so it does not follow the lab's rate.","long_context_pricing":null,"sale":null},{"id":"kimi-k3.1-pro","provider":"Moonshot","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":2.0,"output_per_1m":10.0,"cache_read_per_1m":0.19,"vision":true,"reasoning":true,"tool_call":true,"description":"kimi-k3.1-pro from Moonshot, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"kimi-k3.1-pro-highspeed","provider":"Moonshot","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":4.0,"output_per_1m":20.0,"cache_read_per_1m":0.32,"vision":true,"reasoning":true,"tool_call":true,"description":"kimi-k3.1-pro-highspeed from Moonshot, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"RouterPlex bills $4 input / $20 output per 1M tokens, Moonshot's list price. Cached prompt tokens are billed at $0.32 per 1M, not Moonshot's published $0.20 cache-hit rate: our cache price is set from what our upstream charges us for a cached token, so it does not follow the lab's rate.","long_context_pricing":null,"sale":null},{"id":"gpt-5.4","provider":"OpenAI","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":128000,"input_per_1m":2.5,"output_per_1m":15.0,"cache_read_per_1m":0.2,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-5.4 from OpenAI, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gpt-5.5","provider":"OpenAI","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":30.0,"cache_read_per_1m":0.4,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-5.5 from OpenAI, 256K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gpt-5.6-luna","provider":"OpenAI","mode":"chat","context":"258K","context_tokens":258000,"max_output_tokens":128000,"input_per_1m":0.2,"output_per_1m":1.2,"cache_read_per_1m":0.016,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-5.6-luna from OpenAI, 258K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gpt-5.6-sol","provider":"OpenAI","mode":"chat","context":"258K","context_tokens":258000,"max_output_tokens":128000,"input_per_1m":5.0,"output_per_1m":30.0,"cache_read_per_1m":0.4,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-5.6-sol from OpenAI, 258K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gpt-5.6-terra","provider":"OpenAI","mode":"chat","context":"258K","context_tokens":258000,"max_output_tokens":128000,"input_per_1m":2.0,"output_per_1m":12.0,"cache_read_per_1m":0.16,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-5.6-terra from OpenAI, 258K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"gpt-6-astra","provider":"OpenAI","mode":"chat","context":"922K","context_tokens":922000,"max_output_tokens":128000,"input_per_1m":10.0,"output_per_1m":50.0,"cache_read_per_1m":0.8,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-6-astra from OpenAI, 922K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies at or below 272K prompt tokens. Prompts above 272K are billed at $20 input / $75 output per 1M tokens for the whole request. Cache reads are $0.80 per 1M at or below 272K and $1.60 per 1M above that. OpenAI publishes $1 per 1M cached input.","long_context_pricing":{"threshold_tokens":272000,"input_per_1m":20.0,"output_per_1m":75.0,"cache_read_per_1m":1.6},"sale":null},{"id":"gpt-6-luna","provider":"OpenAI","mode":"chat","context":"922K","context_tokens":922000,"max_output_tokens":128000,"input_per_1m":0.1,"output_per_1m":0.5,"cache_read_per_1m":0.014,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-6-luna from OpenAI, 922K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies at or below 272K prompt tokens. Prompts above 272K are billed at $0.20 input / $0.75 output per 1M tokens for the whole request.","long_context_pricing":{"threshold_tokens":272000,"input_per_1m":0.2,"output_per_1m":0.75,"cache_read_per_1m":0.028},"sale":null},{"id":"gpt-6-sol","provider":"OpenAI","mode":"chat","context":"922K","context_tokens":922000,"max_output_tokens":128000,"input_per_1m":2.0,"output_per_1m":10.0,"cache_read_per_1m":0.16,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-6-sol from OpenAI, 922K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies at or below 272K prompt tokens. Prompts above 272K are billed at $4 input / $15 output per 1M tokens for the whole request.","long_context_pricing":{"threshold_tokens":272000,"input_per_1m":4.0,"output_per_1m":15.0,"cache_read_per_1m":0.32},"sale":null},{"id":"gpt-6.1-sol","provider":"OpenAI","mode":"chat","context":"922K","context_tokens":922000,"max_output_tokens":128000,"input_per_1m":2.0,"output_per_1m":10.0,"cache_read_per_1m":0.16,"vision":true,"reasoning":true,"tool_call":true,"description":"gpt-6.1-sol from OpenAI, 922K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies at or below 272K prompt tokens. Prompts above 272K are billed at $4 input / $15 output per 1M tokens for the whole request.","long_context_pricing":{"threshold_tokens":272000,"input_per_1m":4.0,"output_per_1m":15.0,"cache_read_per_1m":0.32},"sale":null},{"id":"gpt-image-2","provider":"OpenAI","mode":"image_generation","context":"—","context_tokens":null,"max_output_tokens":null,"input_per_1m":5.0,"output_per_1m":30.0,"cache_read_per_1m":null,"vision":true,"reasoning":false,"tool_call":false,"description":"gpt-image-2 image generation from OpenAI on RouterPlex.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"step-3.7-flash","provider":"StepFun","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":256000,"input_per_1m":0.2,"output_per_1m":1.15,"cache_read_per_1m":0.03,"vision":true,"reasoning":true,"tool_call":true,"description":"step-3.7-flash from StepFun, 256K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"hy3","provider":"Tencent Hunyuan","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":64000,"input_per_1m":0.2,"output_per_1m":0.8,"cache_read_per_1m":0.03,"vision":false,"reasoning":true,"tool_call":true,"description":"hy3 from Tencent Hunyuan, 256K context, reasoning, tool calling.","pricing_basis":"public_reference","pricing_note":"Tencent publishes Hy3 as open weights without a first-party hosted API tariff. RouterPlex uses the public market reference of $0.20 input / $0.80 output per 1M tokens.","long_context_pricing":null,"sale":null},{"id":"hy4-preview","provider":"Tencent Hunyuan","mode":"chat","context":"1M","context_tokens":1024000,"max_output_tokens":64000,"input_per_1m":0.834,"output_per_1m":2.501,"cache_read_per_1m":0.042,"vision":false,"reasoning":true,"tool_call":true,"description":"hy4-preview from Tencent Hunyuan, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":"Tencent ships Hy4 as a preview release; the published preview API rate is $0.834 input / $2.501 output per 1M tokens. This model spends heavily on reasoning tokens, so allow a generous max_tokens or replies can come back empty.","long_context_pricing":null,"sale":null},{"id":"mimo-v2.5","provider":"Xiaomi","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":0.11,"output_per_1m":0.28,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"mimo-v2.5 from Xiaomi, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"mimo-v2.5-pro","provider":"Xiaomi","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":0.44,"output_per_1m":0.87,"cache_read_per_1m":null,"vision":false,"reasoning":true,"tool_call":true,"description":"mimo-v2.5-pro from Xiaomi, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"mimo-v2.6-flash","provider":"Xiaomi","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.14,"output_per_1m":0.28,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"mimo-v2.6-flash from Xiaomi, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"mimo-v2.6-pro","provider":"Xiaomi","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.435,"output_per_1m":0.87,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"mimo-v2.6-pro from Xiaomi, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"glm-4.7-flash-abliterated","provider":"Zhipu","mode":"chat","context":"200K","context_tokens":200000,"max_output_tokens":24000,"input_per_1m":0.12,"output_per_1m":0.6,"cache_read_per_1m":0.09,"vision":false,"reasoning":true,"tool_call":true,"description":"glm-4.7-flash-abliterated from Zhipu, 200K context, reasoning, tool calling.","pricing_basis":"public_reference","pricing_note":"An abliterated build of Z.ai's GLM-4.7 Flash: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.","long_context_pricing":null,"sale":null},{"id":"glm-5.1","provider":"Zhipu","mode":"chat","context":"256K","context_tokens":256000,"max_output_tokens":131072,"input_per_1m":1.4,"output_per_1m":4.4,"cache_read_per_1m":null,"vision":false,"reasoning":true,"tool_call":true,"description":"glm-5.1 from Zhipu, 256K context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"glm-5.2","provider":"Zhipu","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":1.4,"output_per_1m":4.4,"cache_read_per_1m":0.225,"vision":false,"reasoning":true,"tool_call":true,"description":"glm-5.2 from Zhipu, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"glm-5.3","provider":"Zhipu","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":1.4,"output_per_1m":4.4,"cache_read_per_1m":0.26,"vision":false,"reasoning":true,"tool_call":true,"description":"glm-5.3 from Zhipu, 1M context, reasoning, tool calling.","pricing_basis":"vendor_list","pricing_note":null,"long_context_pricing":null,"sale":null},{"id":"glm-5.3-abliterated","provider":"Zhipu","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":2.0,"output_per_1m":4.0,"cache_read_per_1m":0.3,"vision":true,"reasoning":true,"tool_call":true,"description":"glm-5.3-abliterated from Zhipu, 1M context, reasoning, tool calling, vision.","pricing_basis":"public_reference","pricing_note":"An abliterated build of Z.ai's GLM-5.3: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.","long_context_pricing":null,"sale":{"previous_input_per_1m":4.0,"previous_output_per_1m":6.0,"previous_cache_read_per_1m":0.7,"input_discount_pct":50,"output_discount_pct":33,"cache_read_discount_pct":57,"since":"2026-10-30"}},{"id":"glm-5.3-flash","provider":"Zhipu","mode":"chat","context":"1M","context_tokens":1000000,"max_output_tokens":131072,"input_per_1m":0.15,"output_per_1m":0.5,"cache_read_per_1m":0.03,"vision":true,"reasoning":true,"tool_call":true,"description":"glm-5.3-flash from Zhipu, 1M context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Z.ai ran a launch promotion at $0.075 input / $0.25 output per 1M tokens through September 9, 2026. RouterPlex bills the standard published list rate of $0.15 input / $0.50 output.","long_context_pricing":null,"sale":null},{"id":"glm-5.3-flash-abliterated","provider":"Zhipu","mode":"chat","context":"1M","context_tokens":1048576,"max_output_tokens":131072,"input_per_1m":0.25,"output_per_1m":1.0,"cache_read_per_1m":0.06,"vision":true,"reasoning":true,"tool_call":true,"description":"glm-5.3-flash-abliterated from Zhipu, 1M context, reasoning, tool calling, vision.","pricing_basis":"public_reference","pricing_note":"An abliterated build of Z.ai's GLM-5.3 Flash: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms.","long_context_pricing":null,"sale":{"previous_input_per_1m":0.5,"previous_output_per_1m":1.6,"previous_cache_read_per_1m":0.3,"input_discount_pct":50,"output_discount_pct":38,"cache_read_discount_pct":80,"since":"2026-10-30"}},{"id":"grok-4.5","provider":"xAI","mode":"chat","context":"500K","context_tokens":500000,"max_output_tokens":500000,"input_per_1m":2.0,"output_per_1m":6.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"grok-4.5 from xAI, 500K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies below 200K prompt tokens. Prompts at or above 200K are billed at $4 input / $12 output per 1M tokens. Cached prompt tokens are billed at the full input rate in both tiers: our upstream charges more for a cached grok token than a fresh one.","long_context_pricing":{"threshold_tokens":200000,"input_per_1m":4.0,"output_per_1m":12.0},"sale":null},{"id":"grok-4.6","provider":"xAI","mode":"chat","context":"500K","context_tokens":500000,"max_output_tokens":500000,"input_per_1m":2.0,"output_per_1m":6.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"grok-4.6 from xAI, 500K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"Base rate applies below 200K prompt tokens. Prompts at or above 200K are billed at $4 input / $12 output per 1M tokens. Cached prompt tokens are billed at the full input rate in both tiers ($2, or $4 at or above 200K): our upstream charges more for a cached grok token than a fresh one, so there is no cache discount to pass through on this model.","long_context_pricing":{"threshold_tokens":200000,"input_per_1m":4.0,"output_per_1m":12.0},"sale":null},{"id":"grok-4.7","provider":"xAI","mode":"chat","context":"500K","context_tokens":500000,"max_output_tokens":500000,"input_per_1m":2.0,"output_per_1m":6.0,"cache_read_per_1m":null,"vision":true,"reasoning":true,"tool_call":true,"description":"grok-4.7 from xAI, 500K context, reasoning, tool calling, vision.","pricing_basis":"vendor_list","pricing_note":"xAI list price. Base rate applies below 200K prompt tokens; prompts at or above 200K are billed at $4 input / $12 output per 1M tokens. Cached prompt tokens are billed at the full input rate for now: RouterPlex does not yet pass xAI's $0.50 cache-read tier through on this model.","long_context_pricing":{"threshold_tokens":200000,"input_per_1m":4.0,"output_per_1m":12.0},"sale":null}]}