{"object":"list","data":[{"id":"qwen-3.7-max","object":"model","created":0,"owned_by":"alibaba","name":"Qwen 3.7 Max","description":"Alibaba's newest closed-weight flagship. 1M context, top reasoning + multilingual.","context_window":1000000,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":3.375,"output":10.125},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["general","coding","reasoning","multilingual","long-context"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"qwen-3.6-plus","object":"model","created":0,"owned_by":"alibaba","name":"Qwen 3.6 Plus","description":"Alibaba's newest flagship. #1 on Kyma.","context_window":131072,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.675,"output":4.05},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["general","coding","reasoning","multilingual"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"qwen-3-coder","object":"model","created":0,"owned_by":"alibaba","name":"Qwen 3 Coder","description":"Purpose-built for code generation.","context_window":131072,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.675,"output":2.16},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["coding","agent","debugging"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"qwen-3-32b","object":"model","created":0,"owned_by":"alibaba","name":"Qwen 3 32B","description":"Top coding model. Ultra fast inference.","context_window":32768,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.392,"output":0.81},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"balanced","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["coding","math","multilingual","fast"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemma-4-31b","object":"model","created":0,"owned_by":"google","name":"Gemma 4 31B","description":"Google's newest open model. Multimodal.","context_window":128000,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.189,"output":0.54},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["vision","general","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-m2.5","object":"model","created":0,"owned_by":"minimax","name":"MiniMax M2.5","description":"SWE-bench 80.2%. Top agentic coding.","context_window":196608,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.405,"output":1.62},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["coding","agent","debugging"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"deepseek-v4-pro","object":"model","created":0,"owned_by":"deepseek","name":"DeepSeek V4 Pro","description":"1.6T MoE flagship. 1M context. Top reasoning tier.","context_window":1000000,"max_output_tokens":65536,"pricing":{"mode":"per-token","input":2.349,"output":4.698},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"preview","recommended_for":["reasoning","coding","long-context","agent"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"deepseek-v4-flash","object":"model","created":0,"owned_by":"deepseek","name":"DeepSeek V4 Flash","description":"284B MoE. 1M context. Fast + cheap V4 tier.","context_window":1000000,"max_output_tokens":65536,"pricing":{"mode":"per-token","input":0.189,"output":0.378},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"preview","recommended_for":["general","coding","long-context","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"deepseek-v3","object":"model","created":0,"owned_by":"deepseek","name":"DeepSeek V3","description":"Previous-gen flagship. Stable, proven.","context_window":160000,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.81,"output":2.295},"pricing_mode":"per-token","supports_caching":false,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["general","coding","reasoning","value"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"deepseek-r1","object":"model","created":0,"owned_by":"deepseek","name":"DeepSeek R1","description":"Top reasoning model. 96% cheaper than o1.","context_window":64000,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.675,"output":2.903},"pricing_mode":"per-token","supports_caching":false,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","reasoning"],"latency_tier":"slow","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["reasoning","analysis","math"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemini-3.5-flash","object":"model","created":0,"owned_by":"google","name":"Gemini 3.5 Flash","description":"Newest Gemini Flash. 1M context, multimodal input.","context_window":1048576,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":2.025,"output":12.15},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["long-context","fast","vision","reasoning"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemini-2.5-flash","object":"model","created":0,"owned_by":"google","name":"Gemini 2.5 Flash","description":"Google's fastest. 1M context.","context_window":1048576,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.405,"output":3.375},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["long-context","fast","vision"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemini-3-flash","object":"model","created":0,"owned_by":"google","name":"Gemini 3 Flash","description":"Newest Gemini. 1M context.","context_window":1048576,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.675,"output":4.05},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"preview","recommended_for":["long-context","reasoning","vision"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"llama-3.3-70b","object":"model","created":0,"owned_by":"meta","name":"Llama 3.3 70B","description":"Most popular open model. Great all-rounder.","context_window":128000,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":1.188,"output":1.188},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["general","coding","balanced"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gpt-oss-120b","object":"model","created":0,"owned_by":"openai","name":"GPT-OSS 120B","description":"OpenAI's open source. 120B parameters.","context_window":128000,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.203,"output":0.81},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["writing","general","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"kimi-k2.6","object":"model","created":0,"owned_by":"moonshot","name":"Kimi K2.6","description":"Moonshot's newest. Agentic + vision + reasoning. 262K context.","context_window":262144,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":1.283,"output":5.4},"pricing_mode":"per-token","supports_caching":false,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["agent","coding","vision","long-context","reasoning"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"kimi-k2.5","object":"model","created":0,"owned_by":"moonshot","name":"Kimi K2.5","description":"Multimodal agentic. 262K context.","context_window":262144,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.675,"output":3.78},"pricing_mode":"per-token","supports_caching":false,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["agent","coding","vision","long-context"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-m2.7","object":"model","created":0,"owned_by":"minimax","name":"MiniMax M2.7","description":"Next-gen agentic productivity.","context_window":204800,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":0.405,"output":1.62},"pricing_mode":"per-token","supports_caching":false,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["agent","coding","productivity"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"glm-5.1","object":"model","created":0,"owned_by":"zhipu","name":"GLM 5.1","description":"#1 SWE-Bench Pro open-weight. 8-hour agentic runs.","context_window":203000,"max_output_tokens":65536,"pricing":{"mode":"per-token","input":1.89,"output":5.94},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["agent","coding","reasoning"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"glm-4.5-air","object":"model","created":0,"owned_by":"zhipu","name":"GLM 4.5 Air","description":"Cheap agentic MoE (106B/12B active). Fast with implicit caching.","context_window":131072,"max_output_tokens":8192,"pricing":{"mode":"per-token","input":0.176,"output":1.148},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["cheap","agent","bulk"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"glm-4.7-flash","object":"model","created":0,"owned_by":"zhipu","name":"GLM 4.7 Flash","description":"Ultra cheap. 200K context. Fast.","context_window":203000,"max_output_tokens":65536,"pricing":{"mode":"per-token","input":0.081,"output":0.54},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"efficient","tier":null,"capability":null,"release_stage":"preview","recommended_for":["cheap","long-context","fast"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"grok-4.3","object":"model","created":0,"owned_by":"xai","name":"Grok 4.3","description":"xAI's frontier model. 1M context, strong reasoning + tool use.","context_window":1000000,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":1.688,"output":3.375},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["general","reasoning","coding","agent","long-context"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"grok-build","object":"model","created":0,"owned_by":"xai","name":"Grok Build","description":"xAI's coding-specialized model. Fast, tool-native, built for agentic dev.","context_window":256000,"max_output_tokens":32768,"pricing":{"mode":"per-token","input":1.35,"output":2.7},"pricing_mode":"per-token","supports_caching":true,"supports_tools":true,"supports_structured_outputs":true,"supports_reasoning":true,"supports_vision":false,"input_modalities":["text"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching","reasoning"],"latency_tier":"fast","cost_tier":"balanced","quality_tier":"strong","tier":null,"capability":null,"release_stage":"preview","recommended_for":["coding","agent","debugging","fast"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"sonar","object":"model","created":0,"owned_by":"perplexity","name":"Sonar","description":"Perplexity's live web-search model. Returns current, cited answers — grounded in a real-time search of the web. Bills a small per-request search fee on top of tokens.","context_window":127072,"max_output_tokens":4096,"pricing":{"mode":"per-token","input":1.35,"output":1.35},"pricing_mode":"per-token","supports_caching":true,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["search","research","web","news","citations"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"sonar-pro","object":"model","created":0,"owned_by":"perplexity","name":"Sonar Pro","description":"Perplexity's pro web-search model. Deeper multi-step search, 200K context, longer cited answers. Per-request search fee on top of tokens.","context_window":200000,"max_output_tokens":8000,"pricing":{"mode":"per-token","input":4.05,"output":20.25},"pricing_mode":"per-token","supports_caching":true,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["search","research","web","news","citations"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"flux-2-pro","object":"model","created":0,"owned_by":"bfl","name":"FLUX.2 Pro","description":"BFL's 32B flagship (3× larger than Flux 1.1). Photoreal, multi-reference (up to 10 sources), unified gen+edit, ~60% accurate text-in-image. $0.03/MP base + $0.015 per extra MP.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.0405},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","photo","hero","blend","edit"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"flux-1.1-ultra","object":"model","created":0,"owned_by":"bfl","name":"FLUX 1.1 Pro Ultra","description":"Legacy. Recommend flux-2-pro for new projects (cheaper at 1MP, higher quality, multi-reference).","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.081},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["image","photo","hero","editorial"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"flux-kontext-pro","object":"model","created":0,"owned_by":"bfl","name":"FLUX.1 Kontext Pro","description":"Image-to-image edit and refinement. Mask + inpaint.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.054},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"strong","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["image","edit","inpaint"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"ideogram-v3","object":"model","created":0,"owned_by":"ideogram","name":"Ideogram V3","description":"Text-in-image specialist. Best for typography, packaging, logos.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.108},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","typography","logo","packaging"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"recraft-v4","object":"model","created":0,"owned_by":"recraft","name":"Recraft V4","description":"Top of HF Arena (#1, beats Midjourney V8 / DALL-E 3 / FLUX). Design-aware composition, lighting, textures.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.054},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"frontier-open","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["image","design","brand","illustration"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"recraft-v4-pro","object":"model","created":0,"owned_by":"recraft","name":"Recraft V4 Pro","description":"Recraft V4 at 4MP for print-ready / large-scale assets. Same design taste as V4, higher resolution.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.3375},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","design","print","premium"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"recraft-v4-vector","object":"model","created":0,"owned_by":"recraft","name":"Recraft V4 Vector","description":"Native SVG output — actual paths + structured layers, edit in Figma/Illustrator. Only model on the market that ships true vector files.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.108},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":"vector","release_stage":"stable","recommended_for":["image","vector","svg","logo","icon"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"recraft-v4-vector-pro","object":"model","created":0,"owned_by":"recraft","name":"Recraft V4 Vector Pro","description":"Native SVG at 4MP for print-ready vector assets. Same as V4 Vector with higher detail / scale.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.405},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":"vector","release_stage":"stable","recommended_for":["image","vector","svg","print","premium"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"recraft-v3","object":"model","created":0,"owned_by":"recraft","name":"Recraft V3","description":"Legacy. Recommend recraft-v4 for new projects (same price, top of HF Arena).","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.054},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":null,"release_stage":"stable","recommended_for":["image","vector","illustration","brand"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"kling-2.5-pro","object":"model","created":0,"owned_by":"kuaishou","name":"Kling 2.5 Pro","description":"Cinematic 5-10s video. Photoreal humans, smooth motion. Cheapest Kling tier. T2V or I2V via image_url.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.0945},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"balanced","quality_tier":"strong","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["video","cinematic","cheap","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"kling-3-pro","object":"model","created":0,"owned_by":"kuaishou","name":"Kling 3 Pro","description":"Flagship Kling. Photoreal humans, smooth motion, sharper than 2.5. T2V or I2V via image_url. For native audio, use kling-3-pro-audio.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.1512},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["video","cinematic","premium","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"kling-3-pro-audio","object":"model","created":0,"owned_by":"kuaishou","name":"Kling 3 Pro (Audio)","description":"Kling 3 Pro with native audio (ambient + dialogue). Same visuals as kling-3-pro plus synchronized sound. ~50% premium for audio.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.2268},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video","audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["video","cinematic","audio","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"seedance-2-pro","object":"model","created":0,"owned_by":"bytedance","name":"Seedance 2 Pro","description":"ByteDance flagship video. Multi-shot, native audio bundled, dynamic camera moves. T2V or I2V via image_url. 720p.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.40959},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video","audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["video","social","action","audio","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"seedance-2-fast","object":"model","created":0,"owned_by":"bytedance","name":"Seedance 2 Fast","description":"Seedance 2 fast tier — quicker generation, ~20% cheaper than Pro. Native audio bundled. Best for short social clips.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.326565},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video","audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"balanced","quality_tier":"strong","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["video","social","fast","audio","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"imagen-4-fast","object":"model","created":0,"owned_by":"google","name":"Imagen 4 Fast","description":"Google Imagen 4 fast tier — quickest gen, lower fidelity. Photoreal, multi-style.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.027},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["image","fast","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"imagen-4","object":"model","created":0,"owned_by":"google","name":"Imagen 4","description":"Google Imagen 4 standard. Photoreal humans, sharp text, rich composition. Default quality tier.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.054},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","photoreal","quality"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"imagen-4-ultra","object":"model","created":0,"owned_by":"google","name":"Imagen 4 Ultra","description":"Google Imagen 4 highest fidelity. Best detail, slowest gen. Use for hero / print-ready assets.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.081},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","premium","print","ultra"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"nano-banana","object":"model","created":0,"owned_by":"google","name":"Nano Banana","description":"Google Gemini image-gen. Native edit-mode (image-in + prompt → image-out). 3 size tiers (512/1K/2K). Cheapest at small sizes.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.046},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"frontier-open","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["image","edit","cheap","fast"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"nano-banana-3-flash","object":"model","created":0,"owned_by":"google","name":"Nano Banana 3 Flash (preview)","description":"Newer Gemini 3.1 image-gen, preview tier. Same edit-mode + tier pricing as stable; sharper output. Routed to Vertex global region.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.046},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"frontier-open","tier":"fast","capability":null,"release_stage":"preview","recommended_for":["image","edit","preview"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"veo-3-fast","object":"model","created":0,"owned_by":"google","name":"Veo 3 Fast","description":"Google Veo 3 fast tier — 720p, no audio. Cheapest Veo. Balanced quality and speed for social/drafts.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.135},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["video","fast","balanced"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"veo-3","object":"model","created":0,"owned_by":"google","name":"Veo 3","description":"Google Veo 3 flagship — 1080p with native audio (dialogue + ambient + lip-sync). Top-quality cinematic clips.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.54},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video","audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["video","premium","audio","cinematic"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"whisper-v3-turbo","object":"model","created":0,"owned_by":"openai","name":"Whisper Large v3 Turbo","description":"Speech-to-text. 228x realtime inference. Transcripts with timestamps + language detect.","context_window":3600,"max_output_tokens":null,"pricing":{"mode":"per-minute","input":0,"output":0,"per_minute_usd":0.0009},"pricing_mode":"per-minute","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":"stt","release_stage":"stable","recommended_for":["audio","transcribe","fast","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gpt-4o-mini-transcribe-2025-12-15","object":"model","created":0,"owned_by":"openai","name":"GPT-4o mini Transcribe","description":"Speech-to-text. OpenAI's premium quality STT — best real-world accuracy on conversational audio, noisy backgrounds, and code-switching (Vi/En etc).","context_window":1500,"max_output_tokens":null,"pricing":{"mode":"per-minute","input":0,"output":0,"per_minute_usd":0.00405},"pricing_mode":"per-minute","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":"stt","release_stage":"stable","recommended_for":["audio","transcribe","quality","multilingual"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemini-3-flash-audio","object":"model","created":0,"owned_by":"google","name":"Gemini 3 Flash (Audio)","description":"Audio understanding. Hears tone, music, SFX, language, speaker emotion — beyond pure transcription. Inline payload up to 30 min.","context_window":1800,"max_output_tokens":4096,"pricing":{"mode":"per-minute","input":0,"output":0,"per_minute_usd":0.002592},"pricing_mode":"per-minute","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["text"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"frontier-open","tier":null,"capability":"audio-understand","release_stage":"preview","recommended_for":["audio","understand","scene","tone"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gpt-realtime-translate","object":"model","created":0,"owned_by":"openai","name":"GPT Realtime Translate","description":"Native audio-to-audio translation with voice cloning. Preserves original speaker tone. 13 target languages (es/pt/fr/ja/ru/zh/de/ko/hi/id/vi/it/en).","context_window":3600,"max_output_tokens":null,"pricing":{"mode":"per-minute","input":0,"output":0,"per_minute_usd":0.0459},"pricing_mode":"per-minute","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":"realtime","release_stage":"preview","recommended_for":["audio","realtime","translate","voice"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gemini-2.5-flash-native-audio-preview-12-2025","object":"model","created":0,"owned_by":"google","name":"Gemini 2.5 Flash Native Audio","description":"Conversational realtime with 30 pickable voices + 24 output languages. WebSocket-based, ephemeral token auth. Native audio understanding + generation in one round-trip.","context_window":1800,"max_output_tokens":null,"pricing":{"mode":"per-minute","input":0,"output":0,"per_minute_usd":0.03888},"pricing_mode":"per-minute","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"balanced","quality_tier":"frontier-open","tier":null,"capability":"realtime","release_stage":"preview","recommended_for":["audio","realtime","voice","conversational"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"eleven-multilingual-v2","object":"model","created":0,"owned_by":"elevenlabs","name":"ElevenLabs Multilingual v2","description":"Hero-quality multilingual TTS. 29 languages, expressive voices, brand-safe consistent delivery.","context_window":5000,"max_output_tokens":null,"pricing":{"mode":"per-char","input":0,"output":0,"per_kchar_usd":0.405},"pricing_mode":"per-char","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":"quality","capability":"tts","release_stage":"stable","recommended_for":["audio","tts","voice","multilingual"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"eleven-flash-v2-5","object":"model","created":0,"owned_by":"elevenlabs","name":"ElevenLabs Flash v2.5","description":"Ultra-low-latency TTS, ~75ms time-to-first-byte. Half the per-char cost of Multilingual v2. 32 languages.","context_window":5000,"max_output_tokens":null,"pricing":{"mode":"per-char","input":0,"output":0,"per_kchar_usd":0.2025},"pricing_mode":"per-char","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":"fast","capability":"tts","release_stage":"stable","recommended_for":["audio","tts","voice","fast","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"eleven-turbo-v2-5","object":"model","created":0,"owned_by":"elevenlabs","name":"ElevenLabs Turbo v2.5","description":"Balanced TTS — quicker than Multilingual, better quality than Flash. Half cost vs Multilingual. 32 languages.","context_window":5000,"max_output_tokens":null,"pricing":{"mode":"per-char","input":0,"output":0,"per_kchar_usd":0.2025},"pricing_mode":"per-char","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":"fast","capability":"tts","release_stage":"stable","recommended_for":["audio","tts","voice","balanced"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"elevenlabs-music","object":"model","created":0,"owned_by":"elevenlabs","name":"ElevenLabs Music","description":"Prompt-driven music generation. Lyrics, instrumental, configurable duration up to 5 min.","context_window":2000,"max_output_tokens":null,"pricing":{"mode":"per-second","input":0,"output":0,"per_second_usd":0.135},"pricing_mode":"per-second","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"quality","capability":"music","release_stage":"stable","recommended_for":["audio","music","soundtrack"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"elevenlabs-sfx","object":"model","created":0,"owned_by":"elevenlabs","name":"ElevenLabs Sound Effects","description":"Generates non-speech audio (whoosh, explosion, rain) from a text prompt. Flat $0.027 per generation, 0.5-22 sec.","context_window":500,"max_output_tokens":null,"pricing":{"mode":"per-call","input":0,"output":0,"per_call_usd":0.027},"pricing_mode":"per-call","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":null,"capability":"sfx","release_stage":"stable","recommended_for":["audio","sfx","sound","fast"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-speech-hd","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Speech HD","description":"MiniMax HD voice. Multilingual, expressive, ~2.9× cheaper than ElevenLabs Multilingual v2 at the same production quality tier.","context_window":5000,"max_output_tokens":null,"pricing":{"mode":"per-char","input":0,"output":0,"per_kchar_usd":0.14},"pricing_mode":"per-char","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"cheap","quality_tier":"strong","tier":"cheap","capability":"tts","release_stage":"stable","recommended_for":["audio","tts","voice","multilingual","cheap"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-speech-turbo","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Speech Turbo","description":"MiniMax low-latency voice. Multilingual, ~2.2× cheaper than ElevenLabs Flash v2.5. Best for bulk TTS, real-time voice agents, conversational AI.","context_window":5000,"max_output_tokens":null,"pricing":{"mode":"per-char","input":0,"output":0,"per_kchar_usd":0.09},"pricing_mode":"per-char","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"efficient","tier":"cheap","capability":"tts","release_stage":"stable","recommended_for":["audio","tts","voice","fast","cheap","bulk"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-music","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Music","description":"Lyrics-driven music generation. Music-2.0 family. Up to 5 minutes per call, ~90× cheaper than ElevenLabs Music for non-hero use cases.","context_window":2000,"max_output_tokens":null,"pricing":{"mode":"per-song","input":0,"output":0,"per_song_usd":0.045},"pricing_mode":"per-song","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"cheap","quality_tier":"strong","tier":"cheap","capability":"music","release_stage":"stable","recommended_for":["audio","music","soundtrack","cheap","bulk"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-music-pro","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Music Pro","description":"Music-2.6 (latest pro family). Higher fidelity than Music-2.0, richer arrangements. Still ~19× cheaper than ElevenLabs Music for production-tier output.","context_window":2000,"max_output_tokens":null,"pricing":{"mode":"per-song","input":0,"output":0,"per_song_usd":0.21},"pricing_mode":"per-song","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"balanced","quality_tier":"frontier-open","tier":"fast","capability":"music","release_stage":"stable","recommended_for":["audio","music","soundtrack","premium"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-voice-clone","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Voice Clone","description":"Clone a voice from a 10s-5min reference recording. Returns a voice_id usable in /v1/audio/speech with any MiniMax HD/Turbo SKU. Flat one-time charge per cloned voice.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-call","input":0,"output":0,"per_call_usd":2.1},"pricing_mode":"per-call","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["audio"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["audio","voice","clone","custom"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-voice-design","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Voice Design","description":"Generate a synthesized voice profile from a natural-language description (no reference audio needed). Returns a voice_id usable in /v1/audio/speech with any MiniMax HD/Turbo SKU. Flat one-time charge per designed voice.","context_window":1000,"max_output_tokens":null,"pricing":{"mode":"per-call","input":0,"output":0,"per_call_usd":4.2},"pricing_mode":"per-call","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["audio"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"premium","quality_tier":"frontier-open","tier":null,"capability":null,"release_stage":"stable","recommended_for":["audio","voice","design","custom"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"gpt-image-2","object":"model","created":0,"owned_by":"openai","name":"GPT Image 2","description":"OpenAI's flagship image model (Apr 2026). Near-perfect text-in-image (multilingual), reasoning-augmented composition, photorealism. Quality tiers low/medium/high — picker default medium. 1024×1024 / 1024×1536 / 1536×1024 / 2048×2048.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.081},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":true,"input_modalities":["text","image"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"medium","cost_tier":"balanced","quality_tier":"frontier-open","tier":"quality","capability":null,"release_stage":"stable","recommended_for":["image","text-in-image","photo","logo"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"minimax-image-01","object":"model","created":0,"owned_by":"minimax","name":"MiniMax Image 01","description":"Sub-cent image generation. Cheapest tier on Kyma — $0.005 per image flat regardless of resolution. 5 aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4). Best for high-volume / budget workflows.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-image","input":0,"output":0,"per_image_usd":0.005},"pricing_mode":"per-image","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text"],"output_modalities":["image"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"fast","cost_tier":"cheap","quality_tier":"strong","tier":"cheap","capability":null,"release_stage":"stable","recommended_for":["image","cheap","bulk","budget"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"hailuo-02-512p","object":"model","created":0,"owned_by":"minimax","name":"Hailuo 02 (512p)","description":"MiniMax Hailuo 02 at 512p — cheapest video tier on Kyma. Flat $0.140 per clip (6s or 10s). T2V or I2V via image_url. Best for social shorts, rapid iteration, budget motion.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-video","input":0,"output":0,"per_video_usd":0.14},"pricing_mode":"per-video","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"cheap","quality_tier":"strong","tier":"cheap","capability":null,"release_stage":"stable","recommended_for":["video","cheap","social","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"hailuo-02-768p","object":"model","created":0,"owned_by":"minimax","name":"Hailuo 02 (768p)","description":"Hailuo 02 at 768p — mid tier balanced quality vs cost. Flat $0.420 per clip. T2V or I2V via image_url.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-video","input":0,"output":0,"per_video_usd":0.42},"pricing_mode":"per-video","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"balanced","quality_tier":"strong","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["video","balanced","brand","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true},{"id":"hailuo-02-1080p","object":"model","created":0,"owned_by":"minimax","name":"Hailuo 02 (1080p)","description":"Hailuo 02 at 1080p — premium tier, full HD output. Flat $0.780 per clip. T2V or I2V via image_url.","context_window":null,"max_output_tokens":null,"pricing":{"mode":"per-video","input":0,"output":0,"per_video_usd":0.78},"pricing_mode":"per-video","supports_caching":false,"supports_tools":false,"supports_structured_outputs":false,"supports_reasoning":false,"supports_vision":false,"input_modalities":["text","image"],"output_modalities":["video"],"supported_parameters":["temperature","top_p","max_tokens","stream","tools","response_format","structured_outputs","prompt_caching"],"latency_tier":"slow","cost_tier":"premium","quality_tier":"frontier-open","tier":"fast","capability":null,"release_stage":"stable","recommended_for":["video","premium","hero","i2v"],"gateway_output_limit":null,"output_limit_source":"upstream_model","max_tokens_passthrough":true}],"aliases":{"best":"qwen-3.6-plus","fast":"qwen-3-32b","code":"qwen-3-coder","cheap":"gemini-2.5-flash","long-context":"gemini-2.5-flash","vision":"gemma-4-31b","reasoning":"deepseek-r1","agent":"kimi-k2.6","best-agent":"kimi-k2.6","balanced":"llama-3.3-70b","glm-flagship":"glm-5.1","search":"sonar","transcribe":"whisper-v3-turbo","transcribe-quality":"gpt-4o-mini-transcribe-2025-12-15","audio-understand":"gemini-3-flash-audio"},"_backend":"cloudflare-workers"}