ByteDance Seed: Seedream 5.0 Flash Seedream 5.0 Flash 31.7M tokens Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive editing workflows that need precise edits at low latency. by bytedance-seed Oct 1, 2026 from $0.018/image Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive editing workflows that need precise edits at low latency. Black Forest Labs: FLUX.3 Image FLUX.3 Image 50% off 11.6M tokens FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers from 768 up to 4K with a selectable aspect ratio. Pricing is a flat per-image rate that scales with the chosen resolution tier. by black-forest-labs Oct 1, 2026 47K context from $0.0205/image FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers from 768 up to 4K with a selectable aspect ratio. Pricing is a flat per-image rate that scales with the chosen resolution tier. LiquidAI: D1 D1 531M tokens D1 is Liquid AI's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, and policy checks that need a fast, scored answer instead of prose. by liquid Oct 1, 2026 66K context $0.04 /M input tokens $0 /M output tokens D1 is Liquid AI's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, and policy checks that need a fast, scored answer instead of prose. Apodex: Apodex 1.1 Mini (free) Apodex 1.1 Mini (free) 11.4B tokens Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results, and is designed for agentic research workflows where answers need to be grounded in evidence. by apodex Oct 1, 2026 262K context $0 /M input tokens $0 /M output tokens Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results, and is designed for agentic research workflows where answers need to be grounded in evidence. Microsoft AI: MAI-Voice-2.1-Flash MAI-Voice-2.1-Flash 133K tokens MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is suited for voice agents, assistants, call centers, and other interactive applications where latency and cost matter most. On OpenRouter, set voice to a full voice ID with the model suffix, such as "en-US-Harper:MAI-Voice-2.1-Flash" . A voice's locale sets the synthesis language. Set response_format to "mp3" or "pcm" (24 kHz mono). Harper and Grant support the agent , customer-call-center , educational , and narrator speaking styles, and many locale voices add emotion styles such as excited , happy , sad , and whispering . The full list of voices is in the supported_voices field of the models API . See the text-to-speech guide . by microsoft Oct 1, 2026 $15/M characters MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is suited for voice agents, assistants, call centers, and other interactive applications where latency and cost matter most. On OpenRouter, set voice to a full voice ID with the model suffix, such as "en-US-Harper:MAI-Voice-2.1-Flash" . A voice's locale sets the synthesis language. Set response_format to "mp3" or "pcm" (24 kHz mono). Harper and Grant support the agent , customer-call-center , educational , and narrator speaking styles, and many locale voices add emotion styles such as excited , happy , sad , and whispering . The full list of voices is in the supported_voices field of the models API . See the text-to-speech guide . Microsoft AI: MAI-Voice-2.1 MAI-Voice-2.1 139K tokens MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is suited for audiobooks, podcasts, lectures, narration, and brand audio where maximum voice quality matters. The model prioritizes naturalness and expressivity over latency-critical generation. On OpenRouter, set voice to a full voice ID with the model suffix, such as "en-US-Harper:MAI-Voice-2.1" . A voice's locale sets the synthesis language. Set response_format to "mp3" or "pcm" (24 kHz mono). Harper and Grant support the agent , customer-call-center , educational , and narrator speaking styles, and many locale voices add emotion styles such as excited , happy , sad , and whispering . The full list of voices is in the supported_voices field of the models API . See the text-to-speech guide . by microsoft Oct 1, 2026 $22/M characters MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is suited for audiobooks, podcasts, lectures, narration, and brand audio where maximum voice quality matters. The model prioritizes naturalness and expressivity over latency-critical generation. On OpenRouter, set voice to a full voice ID with the model suffix, such as "en-US-Harper:MAI-Voice-2.1" . A voice's locale sets the synthesis language. Set response_format to "mp3" or "pcm" (24 kHz mono). Harper and Grant support the agent , customer-call-center , educational , and narrator speaking styles, and many locale voices add emotion styles such as excited , happy , sad , and whispering . The full list of voices is in the supported_voices field of the models API . See the text-to-speech guide . Pareto 26.10 Preview Pareto 26.10 Preview 1.52B tokens Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the next Pareto version and may change without notice; use pareto-26.9 for stable behaviour. by unbiased Oct 1, 2026 1.05M context $0.80 /M input tokens $3.20 /M output tokens Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the next Pareto version and may change without notice; use pareto-26.9 for stable behaviour. HeyGen: Video 1 Video 1 50% off 27 hours HeyGen Video 1 is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text prompt, from a first-frame image, or from a set of image, video, and audio references that the prompt can address directly. It is aimed at short-form business video with a lot of motion in frame: brand moments, product and equipment demos, and training or onboarding content. It is not an avatar product. Unlike HeyGen's Avatar IV and Video Agent, there is no talking-head, script, or lip-sync step; the prompt and references drive the whole scene. by heygen Sep 30, 2026 from $0.01/second HeyGen Video 1 is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text prompt, from a first-frame image, or from a set of image, video, and audio references that the prompt can address directly. It is aimed at short-form business video with a lot of motion in frame: brand moments, product and equipment demos, and training or onboarding content. It is not an avatar product. Unlike HeyGen's Avatar IV and Video Agent, there is no talking-head, script, or lip-sync step; the prompt and references drive the whole scene. Together: Tev1 4B Experimental Tev1 4B Experimental 454M tokens Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24 labeled options. It keeps Qwen's standard next-token head, so it is served through the regular chat completions API rather than a dedicated decisions runtime. Send a system instruction followed by a JSON decision containing state , question , and options . The model returns a single option letter, which application code maps back to the option key. Recommended settings are temperature: 0 , max_tokens: 8 , and thinking disabled. It is intended for routing, classification, and policy checks, not generic chat. Together publishes the full data recipe and training code so teams can fine-tune their own variant. by togethercomputer Sep 30, 2026 33K context $0.042 /M input tokens $0 /M output tokens Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24 labeled options. It keeps Qwen's standard next-token head, so it is served through the regular chat completions API rather than a dedicated decisions runtime. Send a system instruction followed by a JSON decision containing state , question , and options . The model returns a single option letter, which application code maps back to the option key. Recommended settings are temperature: 0 , max_tokens: 8 , and thinking disabled. It is intended for routing, classification, and policy checks, not generic chat. Together publishes the full data recipe and training code so teams can fine-tune their own variant. Inception: Mercury Decide (free) Mercury Decide (free) 1.19B tokens Mercury Decide is Inception's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a calibrated probability taken directly from the model rather than written out as text, so output tokens are free. It makes up to 14 decisions per second and reports how certain it is, so a decision system can run it on every case and escalate the unsure ones to a human. Mercury Decide uses the same /v1/systemone schema as Jev. by inception Sep 30, 2026 33K context $0 /M input tokens $0 /M output tokens Mercury Decide is Inception's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a calibrated probability taken directly from the model rather than written out as text, so output tokens are free. It makes up to 14 decisions per second and reports how certain it is, so a decision system can run it on every case and escalate the unsure ones to a human. Mercury Decide uses the same /v1/systemone schema as Jev.

VoyageAI by MongoDB: rerank-3-lite rerank-3-lite 774M tokens rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86% on long-document evaluations, with code retrieval gains of 2.77% atop voyage-3-large and 2.59% atop voyage-4-large. It matches the retrieval quality of rerank-2.5, and across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 1.44% and Qwen3-Reranker-8B by 2.61%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3-lite supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3-lite here: blog.voyageai.com/2026/09/30/rerank-3 by voyageai Sep 30, 2026 32K context $0.02/M tokens rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86% on long-document evaluations, with code retrieval gains of 2.77% atop voyage-3-large and 2.59% atop voyage-4-large. It matches the retrieval quality of rerank-2.5, and across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 1.44% and Qwen3-Reranker-8B by 2.61%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3-lite supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3-lite here: blog.voyageai.com/2026/09/30/rerank-3 VoyageAI by MongoDB: rerank-3 rerank-3 819M tokens rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations, with code retrieval gains of 2.01% atop voyage-3-large and 1.96% atop voyage-4-large. Across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 2.14% and Qwen3-Reranker-8B by 3.31%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3 supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3 here: blog.voyageai.com/2026/09/30/rerank-3 by voyageai Sep 30, 2026 32K context $0.05/M tokens rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations, with code retrieval gains of 2.01% atop voyage-3-large and 1.96% atop voyage-4-large. Across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 2.14% and Qwen3-Reranker-8B by 3.31%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3 supports instruction following, allowing users to guide relevance scoring through natural language prompts. Learn more about rerank-3 here: blog.voyageai.com/2026/09/30/rerank-3 OpenAI: GPT-6.1 Sol Pro GPT-6.1 Sol Pro 16.3B tokens GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol , served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode by openai Sep 29, 2026 1.05M context $2 /M input tokens $10 /M output tokens GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol , served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode OpenAI: GPT-6.1 Sol GPT-6.1 Sol 327B tokens Academia (#46) Health (#16) Legal (#22) Marketing (#23) SEO (#11) + 4 categories GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks. by openai Sep 29, 2026 1.05M context $2 /M input tokens $10 /M output tokens GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks. Anthropic: Claude Sonnet 5.5 (batch) Claude Sonnet 5.5 (batch) 527M tokens Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor. Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops. by anthropic Sep 28, 2026 1M context $1 /M input tokens $5 /M output tokens Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor. Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops. Anthropic: Claude Sonnet 5.5 Claude Sonnet 5.5 444B tokens Academia (#49) Finance (#25) Legal (#46) Marketing (#45) SEO (#43) + 3 categories Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor. Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops. by anthropic Sep 28, 2026 1M context $2 /M input tokens $10 /M output tokens Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor. Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops. Upstage: Solar Decide Solar Decide 50% off 3.79B tokens Solar Decide is Upstage's structured decision model, served as a System One endpoint on Solar Mini 4. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a calibrated probability taken directly from the model rather than written out as text. Because it generates no prose, each decision takes a single forward pass and output tokens are free. With a 512K context window, an entire document can serve as the state. Solar Decide uses the same /v1/systemone schema as Jev, bringing Solar Mini 4's strong Korean understanding to routing, classification, and policy checks. by upstage Sep 28, 2026 524K context $0.05 /M input tokens $0 /M output tokens Solar Decide is Upstage's structured decision model, served as a System One endpoint on Solar Mini 4. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a calibrated probability taken directly from the model rather than written out as text. Because it generates no prose, each decision takes a single forward pass and output tokens are free. With a 512K context window, an entire document can serve as the state. Solar Decide uses the same /v1/systemone schema as Jev, bringing Solar Mini 4's strong Korean understanding to routing, classification, and policy checks. Respan: Span-01 Span-01 5.12B tokens Span-01 is a behavior scoring model from Respan. It reads a conversation span and returns, for each plain-language behavior you define, the probability that the behavior is present. It is suited for evaluation, guardrails, and monitoring of LLM and agent outputs at scale. It is the higher-accuracy tier of the family. Span-01 Lite is the free, lighter tier. by respan Sep 26, 2026 $0.02 /M input tokens $0 /M output tokens Span-01 is a behavior scoring model from Respan. It reads a conversation span and returns, for each plain-language behavior you define, the probability that the behavior is present. It is suited for evaluation, guardrails, and monitoring of LLM and agent outputs at scale. It is the higher-accuracy tier of the family. Span-01 Lite is the free, lighter tier. Respan: Span-01 Lite Span-01 Lite 24.2B tokens Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy. by respan Sep 26, 2026 $0 /M input tokens $0 /M output tokens Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy. Respan: Span-01 Lite (free) Span-01 Lite (free) 179M tokens Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy. by respan Sep 26, 2026 $0 /M input tokens $0 /M output tokens Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy.