ElevenLabs: Eleven Multilingual v2 Eleven Multilingual v2 50% off Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request limit. by elevenlabs Oct 7, 2026 $40/M characters Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request limit. ElevenLabs: Eleven Flash v2.5 Eleven Flash v2.5 50% off Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit. by elevenlabs Oct 7, 2026 $20/M characters Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit. ElevenLabs: Eleven v3 Conversational Eleven v3 Conversational 50% off Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request limit. by elevenlabs Oct 7, 2026 $20/M characters Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request limit. ElevenLabs: Eleven v4 Turbo Eleven v4 Turbo 50% off Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages and a 10,000-character request limit. by elevenlabs Oct 7, 2026 $20/M characters Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages and a 10,000-character request limit. ElevenLabs: Eleven v3 Eleven v3 50% off Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit. by elevenlabs Oct 7, 2026 $40/M characters Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit. ElevenLabs: Eleven v4 Eleven v4 50% off Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character request limit. by elevenlabs Oct 7, 2026 $40/M characters Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character request limit. OpenAI: GPT-6 Luna Decisions GPT-6 Luna Decisions 6.33B tokens GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question ( noul ), a probability for every option plus the most likely one ( choice ), or a probability for every level of an ordered rubric plus the expected score ( score ). It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content. by openai Oct 6, 2026 1.05M context $0.10 /M input tokens $0 /M output tokens GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question ( noul ), a probability for every option plus the most likely one ( choice ), or a probability for every level of an ordered rubric plus the expected score ( score ). It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content. SpaceXAI: Grok Imagine Video 1.5 Lite Grok Imagine Video 1.5 Lite 4 hours Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from Grok Imagine Video 1.5 . It supports text-to-video and image-to-video, trading some quality for speed and price. 1080p output is rendered at 720p and upscaled. by x-ai Oct 6, 2026 from $0.02/second Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXAI, distilled from Grok Imagine Video 1.5 . It supports text-to-video and image-to-video, trading some quality for speed and price. 1080p output is rendered at 720p and upscaled. Google: Nano Banana 2.1 Nano Banana 2.1 243M tokens Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter . by google Oct 6, 2026 66K context $1.50 /M input tokens $30 /M output tokens Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter . Mistral: Mistral Large 4 Mistral Large 4 50% off 30.1B tokens Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up to 256K output tokens, and supports tool calling and structured outputs. by mistralai Oct 6, 2026 524K context $0.68 /M input tokens $2.09 /M output tokens Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up to 256K output tokens, and supports tool calling and structured outputs.

Tencent: Hy Image 3.5 Preview Hy Image 3.5 Preview 121M tokens Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images per request and producing output up to 4K. Built on the 80B mixture-of-experts Hy Image 3.0 base, it is particularly strong at subject consistency across edits, prompt-faithful composition, and rendering Chinese and English text inside images. by tencent Oct 5, 2026 100K context $1.60/M tokens Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images per request and producing output up to 4K. Built on the 80B mixture-of-experts Hy Image 3.0 base, it is particularly strong at subject consistency across edits, prompt-faithful composition, and rendering Chinese and English text inside images. inclusionAI: Ling 3.1 Flash Ling 3.1 Flash 365B tokens Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. by inclusionai Oct 2, 2026 262K context $0 /M input tokens $0 /M output tokens Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. ByteDance Seed: Seedream 5.0 Flash Seedream 5.0 Flash 995M 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. Perplexity: Decider V1 27B Decider V1 27B 8.63B tokens Legal (#40) SEO (#42) Trivia (#33) Decider V1 27B is a decision model from Perplexity. Instead of generating text, it reads content passed as state and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question ( noul ), a probability for every option plus the most likely one ( choice ), or a probability for every level of an ordered rubric plus the expected score ( score ). It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 128 questions about the same content. On OpenRouter it currently accepts text and JSON state ; image inputs are not yet supported. by perplexity Oct 1, 2026 262K context $0.04 /M input tokens $0 /M output tokens Decider V1 27B is a decision model from Perplexity. Instead of generating text, it reads content passed as state and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question ( noul ), a probability for every option plus the most likely one ( choice ), or a probability for every level of an ordered rubric plus the expected score ( score ). It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 128 questions about the same content. On OpenRouter it currently accepts text and JSON state ; image inputs are not yet supported. Black Forest Labs: FLUX.3 Image FLUX.3 Image 50% off 238M 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 8.15B 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) 192B 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. Cloudflare: Clef Flash Clef Flash 4.93B tokens Trivia (#6) Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately. by cloudflare Oct 1, 2026 66K context $0.09 /M input tokens $0 /M output tokens Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately. Cloudflare: Clef Clef 3.64B tokens Trivia (#9) Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for classification, routing, scoring, guardrails, and agentic control flow through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately. by cloudflare Oct 1, 2026 66K context $0.24 /M input tokens $0 /M output tokens Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for classification, routing, scoring, guardrails, and agentic control flow through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately. Microsoft AI: MAI-Voice-2.1-Flash MAI-Voice-2.1-Flash 2.4M 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 .