multimodal

Vision-language variant of NVIDIA Nemotron Nano 8B with multimodal capabilities.

Pricing not tracked / 1M tokens

1 route

Mistral Large 3 675B Instruct is MistralAI's Mistral Large model. It offers a 128K-token context window and scores 70.2 on τ-bench.

$0.500 in / $1.50 out / 1M tokens

6 routes · 1 batch · 3 cache

Qwen3.5-9B is Alibaba's Qwen3.5 model with multimodal text and image input. It offers a 256K-token context window with weights openly available for self-hosting.

$0.100 in / $0.150 out / 1M tokens

5 routes

Llama Guard 3 11B Vision is Meta's Llama Guard model. Weights are openly available for self-hosting.

No tracked provider route

Xiaomi MiMo-V2.5 is the lower-cost native omnimodal sibling in the MiMo-V2.5 series. OpenRouter describes it as supporting text, image, audio, and video inputs with text output, Pro-level agentic performance at roughly half the inference cost, and improved multimodal perception over MiMo-V2-Omni. Xiaomi's official April 22 release page highlights MiMo-V2.5 alongside MiMo-V2.5-Pro in benchmark data and says the V2.5 series will be open-sourced soon; no public weights/license were verified at research time.

$0.140 in / $0.280 out / 1M tokens

2 routes · 2 cache

Xiaomi MiMo-V2.6-Flash is Xiaomi MiMo's September 21, 2026 efficiency-balanced open-weights MoE (309B total / 15B active), sibling of MiMo-V2.6-Pro. First-party HF checkpoint XiaomiMiMo/MiMo-V2.6-Flash-RL (MIT; ungated; 1M context) is the released Flash RL weights; product/API id is mimo-v2.6-flash. First-party news: the series comprises two native fully multimodal models (Pro and Flash); Flash comprehensively outperformed MiMo-V2.5-Pro. Product card: full-modality high-intelligence low-cost reasoning for high-frequency and large-scale professional workflows; context 1M; max output 128K; input text, image, video, and audio. Overseas API pricing (pay-as-you-go): $0.0028 cache-hit / $0.14 cache-miss input and $0.28 output per 1M tokens; batch $0.0014 / $0.07 / $0.14. Sparse MoE MiMoV2ForCausalLM; 48 layers (39 SWA / 9 GA); 256 routed experts / 8 activated per token; hybrid SWA+GA backbone; native omnimodal (text/image/video/audio); 681M MiMo ViT vision encoder; 5-layer SWA MTP/DFlash speculative decoder.

$0.140 in / $0.280 out / 1M tokens

2 routes · 1 batch · 2 cache

Xiaomi MiMo-V2.6-Pro is Xiaomi MiMo's September 21, 2026 flagship open-weights MoE (1.02T total / 42B active), succeeding proprietary MiMo-V2.5-Pro. First-party HF checkpoint XiaomiMiMo/MiMo-V2.6-Pro-RL (MIT; ungated; 1M context) is the released Pro RL weights; product/API id is mimo-v2.6-pro. HF README: native omnimodal + long-horizon agents; You Only RL Once mixed RL across coding/agents/visual/cybersecurity. Official product page (mimo.mi.com) and @XiaomiMiMo announce open-sourcing of Pro and Flash with tech report. Overseas API pricing matches V2.5-Pro: $0.0036 cache-hit / $0.435 cache-miss input and $0.87 output per 1M tokens (pay-as-you-go). Sparse MoE MiMoV2ForCausalLM; 70 layers (60 SWA / 10 GA); 384 routed experts / 8 activated per token; hybrid SWA+GA backbone; native omnimodal (text/image/video/audio); 681M MiMo ViT vision encoder; MTP blocks.

$0.435 in / $0.870 out / 1M tokens

2 routes · 1 batch · 2 cache

Kimi K3 is Moonshot AI's 2.8-trillion-parameter flagship multimodal model for long-horizon coding, knowledge work, deep reasoning, and agentic workflows. It uses Kimi Delta Attention, Attention Residuals, and a sparse MoE design (16 of 896 experts active), supports a 1,048,576-token context window, text/image/video input, always-on reasoning, ToolCalls, strict JSON Schema structured output, automatic context caching, and partial mode through Moonshot's OpenAI-compatible API.

$3.00 in / $15.00 out / 1M tokens

3 routes · 2 cache

SenseNova V6 is SenseTime's latest large model with advanced multimodal reasoning and text generation at low cost. Features multimodal long chain-of-thought reasoning and reinforcement learning enhancements.

Pricing not tracked / 1M tokens

1 route

Step-2 is StepFun's Step model with multimodal text and image input. It offers a 256K-token context window.

Pricing not tracked / 1M tokens

1 route

SenseNova-U1-A3B is SenseTime's open-source multimodal MoE model released April 28, 2026. ~3B activated parameters (MoE backbone). Shares the NEO-Unify architecture with SenseNova-U1-8B: no visual encoder or VAE, native unified text-and-image representation. Apache 2.0 license. HuggingFace: OpenSenseNova/SenseNova-U1-A3B-MoT. Source: https://github.com/OpenSenseNova/SenseNova-U1

No tracked provider route

Holo3.1-35B-A3B is H Company's flagship open-weights 35B (3B active) sparse MoE computer-use VLM released June 1, 2026 under Apache 2.0. Achieves 79.3% on AndroidWorld and >25% improvement on the Holotab harness over Holo3. Supports native function-calling, FP8/NVFP4 quantization for DGX Spark, and local self-hosting.

$0.250 in / $1.80 out / 1M tokens

1 route

GLM-5.3-Flash is Z.ai's first native multimodal model in the GLM-5 series. It is a 320B-total / 18B-active Mixture-of-Experts model with a 1M-token context window and 131,072 max output tokens, supporting image, video, and file input plus function calling, tool use, structured outputs, reasoning, and prompt caching. MIT open weights are ungated on Hugging Face at zai-org/GLM-5.3-Flash. Official API model ID: glm-5.3-flash. The same model was previously tested anonymously as ox-alpha; that name is not a separate catalog slug.

$0.150 in / $0.500 out / 1M tokens

2 routes · 2 cache

Holo3.1-9B is H Company's 9B-parameter open-weights computer-use VLM released June 1, 2026 under Apache 2.0. Part of the Holo3.1 family. Achieves 71% on AndroidWorld. Supports native function-calling and structured JSON output for web, desktop, and mobile agent workflows.

No tracked provider route

Holo3.1-4B is H Company's 4B-parameter open-weights computer-use VLM released June 1, 2026 under Apache 2.0. Part of the Holo3.1 family. Achieves 71% on AndroidWorld (up from 58% for Holo3). Supports native function-calling, web/desktop/mobile environments, and local deployment via quantized checkpoints.

No tracked provider route

Holo3.1-0.8B is H Company's smallest 0.8B-parameter open-weights computer-use VLM, released June 1, 2026 under Apache 2.0. Part of the Holo3.1 family spanning 0.8B-35B. Fine-tuned from Qwen3.5-0.8B. Supports native function-calling and structured JSON output for local/edge deployment.

No tracked provider route

Phi-3 Vision is a sophisticated multimodal AI model from Microsoft, designed to adeptly integrate language and vision capabilities. Unlike traditional language models, it processes both text and images and can perform tasks such as optical character recognition, chart analysis, and image interpretation. Its architecture features an image encoder, a text-image connector, a projector for mapping image features, and the Phi-3 Mini language model. Despite its relatively small size of 4.2 billion parameters, it competes with larger models and suits devices with limited computational power. Phi-3 Vision's ability to handle up to 128K tokens supports complex multimodal reasoning. It draws upon high-quality and synthetic data for training while incorporating essential safety measures.

$0.200 in / $0.200 out / 1M tokens

3 routes

Holo3-122B-A10B is H Company's flagship 122B (10B active) sparse MoE computer-use VLM. Released March 31, 2026, available via the H Company API only (no public open weights). Achieves 78.85% on OSWorld-Verified - SOTA at launch. Paid-tier API access at $0.40/$3.00 per 1M input/output tokens.

$0.400 in / $3.00 out / 1M tokens

1 route

Seedance 1.5 Pro is ByteDance Seed's joint audio-video generation model for text- and image-driven video with synchronized sound. Its Volcengine route remains live while scheduled for retirement.

No tracked provider route

Amazon Nova Premier is Amazon's most capable standard Bedrock Nova understanding model for complex reasoning, agentic workflows, and model distillation. It supports a 1M-token context window, text/image/video inputs, text output, reasoning, tool calling, and prompt caching; use it as the standard Bedrock Nova frontier pick instead of Nova 2 Omni early-access Forge checkpoints.

$2.50 in / $12.50 out / 1M tokens

2 routes · 1 batch · 2 cache

Nova Pro is Amazon's Nova model. It offers a 300K-token context window.

$0.800 in / $3.20 out / 1M tokens

2 routes

Reka Edge is Reka's Reka model with multimodal text and image input. It offers a 64K-token context window.

$0.100 in / $0.100 out / 1M tokens

2 routes

Seedance 2.0 Mini is the separately addressable compact Volcengine surface for ByteDance's multimodal joint audio-video generation family.

Pricing not tracked / 1M tokens

1 route

Nova Lite is Amazon's Nova model. It offers a 300K-token context window.

$0.060 in / $0.240 out / 1M tokens

2 routes

Seedance 2.0 Fast is the separately addressable speed-optimized Volcengine surface for ByteDance's multimodal joint audio-video generation family.

Pricing not tracked / 1M tokens

1 route

21B multimodal model from Reka. State-of-the-art for 21B class, supports text/image/video

$0.800 in / $2.00 out / 1M tokens

1 route

Kimi K2.5 is Moonshot AI's Kimi model focused on code generation and software engineering. It offers a 256K-token context window and scores 87.9 on GPQA.

$0.440 in / $2.00 out / 1M tokens

7 routes · 1 cache

Instruction-tuned 11B Llama 3.2 Vision model for image reasoning, visual question answering, document understanding, and captioning. NVIDIA NIM lists text plus image input, text output, and a 128K context window for the Llama 3.2 Vision collection.

$0.200 in / $0.200 out / 1M tokens

4 routes

Hy4 is Tencent Hy's flagship large language model, released November 4, 2026 as the successor to Hy4 preview. It is the first Hy model with vision input, and Tencent serves it on Tencent Cloud, OpenRouter and in its CodeBuddy, WorkBuddy, Yuanbao and ima products. Tencent says it plans to open-source the weights, with vLLM and SGLang support and a system card at that time; as of release the model is API-only.

$0.834 in / $2.50 out / 1M tokens

3 routes · 1 cache

joey-1 is a 2B open-weight decision model from Base Labs, Baseten's research lab, released October 29, 2026. It is a fine-tune of Qwen3.5-2B that turns a state and typed questions into calibrated probabilities for choice, yes/no and score answers in a single forward pass, without generating free-form text, for routing, classification and rubric scoring. It accepts text and images and has a 16,384-token context limit. It is the smallest of Base Labs' three decision models (with elephant-1 and mammoth-1). Weights are on Hugging Face at baselabs/joey-1 under MIT.

$0.010 in / Free out / 1M tokens

3 routes · 1 cache

Particle-1 is Particle AI's model for agentic coding and software engineering, post-trained on DeepSeek V4.1 Flash to finish tasks with fewer tokens. It takes text and images, supports reasoning and tool use, and has a 1,048,576-token context window with up to 131,072 output tokens. Available on the Particle API, OpenRouter and Vercel AI Gateway.

$0.250 in / $1.00 out / 1M tokens

3 routes · 3 cache

GLM-Legal is Z.ai's legal-domain model, built on GLM-5.3-Flash with legal mid-training and reinforcement-learning post-training across legal agent environments. Z.ai reports a 19.2% all-pass rate on the Harvey Legal Agent Benchmark, 12.5 points above its base model, as evaluated by Vals.

$0.370 in / $1.25 out / 1M tokens

3 routes · 3 cache

HeyGen Video is HeyGen's general-purpose video model, built on MiniMax H3 and post-trained by HeyGen. It generates 5-15 s clips with their own dialogue, ambience and sound-effects track from text, a first-frame image, or image/video references, at 480p to 2K.

Pricing not tracked / 1M tokens

3 routes

HeyGen Voice is HeyGen's text-to-speech model (API id heygen-voice-1), supporting public, instant and professional cloned voices. Announced 9 Oct 2026.

$30.00 in / - out / 1M tokens

3 routes

Qwen3.6-Plus is Alibaba Cloud's GA Qwen3.6 flagship for long-context reasoning, coding, tool use, and multimodal workflows. DashScope lists it with a 1M-token context window, structured output support, and standard public token pricing.

$0.325 in / $1.95 out / 1M tokens

3 routes · 2 cache

Nemotron-Nano-12B-v2-VL is NVIDIA AI's Nemotron Nano 2 model with multimodal text and image input. It was released 2025-10-28.

$0.200 in / $0.600 out / 1M tokens

3 routes

Instruction-tuned 90B Llama 3.2 Vision model for higher-capability image reasoning, visual question answering, visual grounding, and captioning. NVIDIA NIM lists text plus image input, text output, and a 128K context window for the Llama 3.2 Vision collection.

$0.150 in / $0.450 out / 1M tokens

3 routes

Kling 4.0 Flash is Kuaishou's fast, lower-cost video generation model in the Kling 4.0 series, first shown alongside Kling 4.0 on October 6, 2026 and made fully available on the Kling AI website and API on November 4, 2026. It does text-to-video, image-to-video, omni reference and video editing, producing 3 to 20-second clips at 720p in 8-bit SDR.

Pricing not tracked / 1M tokens

2 routes

LongCat-2.5 is Meituan's native multimodal model for long-horizon agentic tasks, released November 2, 2026. It is a mixture-of-experts model with 1.6 trillion total parameters and about 48 billion activated per token, built on LongCat-2.0 with stronger native visual understanding and agentic coding, with W4A4 inference optimized for domestic AI accelerators. It accepts text and image input. It is served on the LongCat API Platform as LongCat-2.5; Meituan lists Hugging Face and GitHub releases as coming soon.

Pricing not tracked / 1M tokens

2 routes

SFX v3 is ElevenLabs' sound effects model, announced October 29, 2026. It generates sound effects from a text prompt and supports seamless looping. It is available in ElevenCreative and on the ElevenLabs API as eleven_text_to_sound_v3 through the same Sound Effects API as v2, and on fal for clips up to 30 seconds.

Pricing not tracked / 1M tokens

2 routes

AssemblyAI-TTS-1 is AssemblyAI's first text-to-speech model, built for voice agents. It streams natural speech with about 90 ms latency, supports English, Spanish, French, German, Italian and Portuguese.

$15.00 in / - out / 1M tokens

2 routes

Nemotron 3.5 Transcribe is NVIDIA's open-weight, promptable speech model: a mixture-of-experts model with 34B total and 4.3B active parameters (including the audio encoder) that does transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding in one checkpoint. It handles recordings up to one hour (65,536-token context) and is released under the OpenMDW 1.1 license for commercial or non-commercial use.

Pricing not tracked / 1M tokens

2 routes

d1.1 is Liquid AI's decision model and the default hosted model on the Liquid Decisions API. Like d1, it reads text and images plus typed questions and returns calibrated probabilities instead of generated text. API-only, proprietary.

$0.020 in / Free out / 1M tokens

2 routes

Kimi K3.1 Pro is the first model in Moonshot AI's K3.1 series, a post-trained version of Kimi K3. It has a 1,048,576-token context window, always-on reasoning with low, high and max effort, image and video input, tool calling and strict JSON Schema structured output. Released 2026-10-23 on Kimi.ai, Kimi Work, Kimi Code and the Kimi API; Moonshot says full weights will follow by 2026-11-04.

$2.00 in / $10.00 out / 1M tokens

2 routes · 2 cache

Kimi K3.1 Pro Highspeed is the high-speed variant of Moonshot AI's Kimi K3.1 Pro, offered on the Kimi API with the same 1,048,576-token context window. It keeps always-on reasoning with low, high and max effort, image and video input, tool calling and strict JSON Schema structured output, at double the K3.1 Pro token price. Released 2026-10-23 alongside K3.1 Pro.

$4.00 in / $20.00 out / 1M tokens

2 routes · 2 cache

Ideogram Vector 1.0 is Ideogram's first vector model. It generates clean, editable SVGs with smooth gradients and sharp typography from a text prompt (optionally with reference images), or converts an existing image into a scalable vector. Live in the Ideogram app and API (POST /v2/svg/generate/ideogram-vector-1 and /v2/svg/vectorize/ideogram-vector-1) and on fal.

Pricing not tracked / 1M tokens

2 routes

HeyGen Voice Turbo (API id heygen-voice-1-turbo) is the faster HeyGen Voice text-to-speech model for public and instant voices; a shared-capacity Turbo Free variant is free until 30 Nov 2026.

$4.00 in / - out / 1M tokens

2 routes

Drex Max is Nace.AI's flagship multimodal decision model for computer use: from screens, images, charts and video it scores typed questions (yes/no, multiple choice) instead of generating text. API-only; 262K-token context.

$0.060 in / Free out / 1M tokens

2 routes

MOSS-Image SFT is the supervised fine-tuned release of MOSS-Image Base from the OpenMOSS team at MOSI AI. It keeps the 5B diffusion transformer and adds cleaner text grouping and layout for natural-language, tag or JSON-layout prompts, with Chinese and English text rendering. It is the checkpoint served on fal. Apache 2.0.

Pricing not tracked / 1M tokens

2 routes

OmniHuman 2.0 is ByteDance's audio-driven avatar video model, offered through BytePlus. From one image and a speech, music or dialogue track (plus optional text prompts for motion and camera), it generates lip-synced video with expressions, gestures and multi-person scenes at native 720p, for 30 to 300 seconds in a single take.

Pricing not tracked / 1M tokens

2 routes

Qwen3.8-Max is a 2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. It autonomously codes and delivers complete projects spanning 10+ days, handles hundreds of specialized tasks across legal, financial, design, and other professional domains, and produces production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. The public Hugging Face checkpoint (Qwen3.8-2.4T-A95B) is text-only under the Qwen3.8-Max License; the hosted qwen3.8-max API adds vision, optional non-thinking mode, 1M context, tools, structured outputs, and prompt caching on the same model ID.

$2.00 in / $6.00 out / 1M tokens

2 routes · 2 cache

ERNIE 4.5 is Baidu AI's ERNIE model. It offers an 8K-token context window.

$1.20 in / $1.20 out / 1M tokens

2 routes

Idol is Sperid Labs' open-weight image-to-3D model, announced October 29, 2026. A 3D diffusion transformer pre-trained from scratch, it generates a complete 3D object as a Gaussian splat from a single image, with a GLB point-cloud preview, and runs on consumer GPUs. It has 0.66B parameters and can generate each object at several levels of detail, from 32,768 to 1,048,576 Gaussians. Weights are on Hugging Face at speridlabs/idol under Apache 2.0.

Pricing not tracked / 1M tokens

1 route

Phonic-1 is Phonic's speech-to-speech model for agentic voice tasks, released October 29, 2026. It hears the caller's audio directly and answers in natural speech, and can call tools while the caller is still talking. It is available through Phonic's API under the model ID phonic-1.

Pricing not tracked / 1M tokens

1 route

Pika H3 Flex is Pika's open-weight omni video model family, released October 29, 2026 and post-trained by the Pika team on MiniMax H3 down to six-step generation. It makes 5 to 15 second videos with synchronized audio from text, images, or video and audio references. Open weights on Hugging Face (LoRA adapters plus Diffusers-format MiniMax H3 base components, under the MiniMax H3 Community License) run natively at 480p and 768p; the Pika API also upscales to 1080p, 2K and 4K and can return five separate audio stems.

Pricing not tracked / 1M tokens

1 route

Riverflow 2.6 Pro is Sourceful's flagship image generation and editing model, released October 29, 2026 as the upgrade to Riverflow 2.5 Pro. It generates and edits product and campaign images from text and reference images, supports 1K, 2K and 4K output with more than 46 million size combinations, and has visual reasoning built in. It is available in the Riverflow app, MCP and API.

Pricing not tracked / 1M tokens

1 route

SubQ Snap 1.1 is Subquadratic's second decision model and the default model on the SubQ Decisions API. Like SubQ Snap, it reads text and images and returns probabilities over named choice, yes/no or score answers instead of generated text, with a native 384K-token context. Released 2026-10-22 in public preview (model ID subq-snap-1.1). Not a chat model.

$0.040 in / Free out / 1M tokens

1 route

MOSS-Image Base is the open 5B diffusion-transformer text-to-image base model from the OpenMOSS team at MOSI AI. It takes natural-language prompts of up to 4K tokens, tag sequences or JSON layouts that place text and objects, renders Chinese and English text, and is meant as a foundation for fine-tuning. Apache 2.0.

Pricing not tracked / 1M tokens

1 route

Kling 4.0 is Kuaishou's next-generation native multimodal video model, first shown by Kling AI in creator posts on October 10, 2026, detailed in the Kling 4.0 release overview on October 14 and made fully available in the Kling AI app and platform on October 15. It improves stability for complex motion and consistency across characters and scenes, generates synchronized audio, voices and dialogue, and supports text-, image- and reference-to-video plus video editing at 720p and 1080p, with 4K/1080p 10-bit HDR output listed as coming soon. On fal it runs in the playground and fal Agent at $0.157 per second at 720p and $0.235 per second at 1080p, with API access listed as coming soon; Kling opened Kling 4.0 API applications on October 21.

Pricing not tracked / 1M tokens

1 route

GLiDE (Generalized Lightweight Decision Engine) is Fastino Labs' decision model. Given a state (text, JSON or images) and named choice, yes/no or score questions, it returns a probability for every option instead of generated text. Post-trained from Qwen3.8-27B. Served on the Fastino API; weights on Hugging Face under the Fastino Community License.

$0.040 in / Free out / 1M tokens

1 route

Moondream Parakeet Ultra is a speech-to-text model from Moondream (M87 Labs), released September 22, 2026 with Parakeet Redux. It is a post-trained version of NVIDIA's parakeet-tdt-0.6b-v3 with the same architecture, tokenizer and 0.6B parameters, keeping full-precision weights. Weights are on Hugging Face under CC BY 4.0, and Prime Intellect, which acquired Moondream, serves it on OpenRouter.

Pricing not tracked / 1M tokens

1 route

Cosmos 3 Nano is NVIDIA's 16B-parameter omnimodel optimized for efficient inference on workstation-grade hardware (NVIDIA RTX PRO 6000). Architecture: dual-tower Mixture-of-Transformers with an 8B autoregressive Reasoner and an 8B diffusion-based Generator. The Reasoner supports up to 256K tokens of context for vision-language reasoning; the Generator produces video up to 720p at variable frame rates (default 189 frames). Natively handles text, image, video, audio (48kHz stereo), and robot action trajectories across 10+ robot embodiments including Franka Panda, UR, Google robot, and UMI. BF16 precision only. Available as open weights on Hugging Face and via the Cosmos 3 Reasoner NIM (NIM_MODEL_SIZE=nano). Intended for real-time robotics inference and edge-adjacent deployment. Robot action input/output is preserved in this description because the model schema does not have a dedicated action modality field.

Pricing not tracked / 1M tokens

1 route

Cosmos 3 Super is NVIDIA's flagship 64B-parameter omnimodel for physical AI, designed for large-scale synthetic data generation and high-fidelity simulation on NVIDIA Hopper and Blackwell datacenter GPUs. Architecture: dual-tower Mixture-of-Transformers with a 32B autoregressive Reasoner and a 32B diffusion-based Generator. Supports 256K token reasoning context, 720p video generation at variable frame rates, and 10+ robot embodiment action domains. Ranked #1 among open models on Physics-IQ, PAI-Bench, R-Bench, RoboLab, RoboArena, VANTAGE-Bench, and TAR (Computex 2026). Training data: 1.3B data points across 393 datasets (2024-2026). Inference performance (vLLM-Omni): ~55s for 50-step video on 8xH200. Available as open weights on Hugging Face and via Cosmos 3 Reasoner NIM (NIM_MODEL_SIZE=super).

Pricing not tracked / 1M tokens

1 route

Perceptron Mk1 is a closed-source vision-language model for image and video understanding, OCR, object detection, captioning, video QA, and embodied reasoning. Perceptron documents Mk1 with 32K context, reasoning support, and standard pricing of $0.15 per 1M input tokens and $1.50 per 1M output tokens.

$0.150 in / $1.50 out / 1M tokens

1 route

Seedance 2.0 is ByteDance Seed's flagship joint audio-video generation model. It accepts text, image, audio and video references and generates controllable, synchronized audiovisual output.

Pricing not tracked / 1M tokens

1 route

GPT-5 Image Mini is a cost-effective image generation model that combines GPT-5 Mini's language capabilities with image generation at 400K context.

$2.50 in / $2.00 out / 1M tokens

1 route · 1 cache

SEA-LION V4 27B Instruct is AI Singapore's Gemma 3 27B-based regional language model for Southeast Asian language tasks. It extends the SEA-LION line with continued pretraining and post-training for Burmese, Indonesian, Khmer, Lao, Malay, Mandarin, Tagalog, Tamil, Thai, Vietnamese, and English workloads, and is available through Cloudflare Workers AI.

$0.351 in / $0.555 out / 1M tokens

1 route

Baidu ERNIE X1 advanced model with enhanced reasoning for enterprise applications.

$0.300 in / $1.18 out / 1M tokens

1 route

MiniMax-01 combines MiniMax-Text-01 and MiniMax-VL-01, pairing a 456B-total-parameter MoE language model with multimodal understanding for long-context text generation and vision-language tasks.

$0.200 in / $1.10 out / 1M tokens

1 route

GLM-4V 9B is Tsinghua Knowledge Engineering Group (THUDM)'s GLM-4 model with multimodal text and image input. It offers a 128K-token context window and scores 48.3 on MMMU.

$0.050 in / $0.250 out / 1M tokens

1 route

PaliGemma 3B 896 is a versatile and lightweight vision-language model developed by Google, designed to process and integrate both images and text. Inspired by the PaLI-3 model, it employs components like the SigLIP vision model and the Gemma-2B language model, featuring a linear projection layer for seamless integration of visual and textual inputs. Capable of handling tasks such as image captioning, visual question answering, object detection, and segmentation, it supports multilingual text processing. Despite requiring task-specific fine-tuning for optimal performance, PaliGemma highlights strong capabilities across various vision-language applications, although it may encounter challenges with contextual understanding, biases, and computational demands 124.

Pricing not tracked / 1M tokens

1 route

Reka's frontier-class multimodal model for complex tasks. Approaches OpenAI/Google/Anthropic frontier models

$2.00 in / $6.00 out / 1M tokens

1 route

DeepSeek-VL 7B is an open-source vision-language model engineered for robust real-world applications. With its general multimodal understanding capabilities, it can process logical diagrams, web pages, formulas, scientific literature, natural images, and complex scenarios involving embodied intelligence. The model features a hybrid vision encoder that integrates SigLIP-L and SAM-B, allowing it to handle high-resolution (1024 x 1024) image inputs. Built on the DeepSeek-LLM-7b-base foundation, it is pre-trained on roughly 2 trillion text tokens and further trained on approximately 400 billion vision-language tokens. A standout variant, DeepSeek-VL-7b-chat, is specially optimized for conversational tasks, enhancing both performance and user experience by addressing the limitations of existing open-source multimodal models.

$0.050 in / $0.250 out / 1M tokens

1 route

Original LLaVA (Large Language-and-Vision Assistant) 13B model. Multimodal vision+language model combining a vision encoder with a language model for visual understanding tasks.

Pricing not tracked / 1M tokens

1 route

Smaug-Audio-Decisions-0.7B is Abacus.AI's 744M open-weight audio decision model, released November 2, 2026 alongside Smaug-Decisions. A fine-tune of Google's EmbeddingGemma 2 with its audio tower, it answers a typed question about an audio clip with a probability per option from one forward pass; both models ship inside one iOS and Android app. Weights are on Hugging Face at abacusai/Smaug-Audio-Decisions-0.7B under Apache 2.0.

No tracked provider route

Smaug-Decisions is Abacus.AI's open-weight 4B decision model, released November 2, 2026. A full fine-tune of Google's Gemma 4 E4B-it, it answers a question about audio, an image or text with a probability per option from one forward pass, without decoding. Weights are on Hugging Face at abacusai/Smaug-Decisions under Apache 2.0, with a LiteRT build for phones.

No tracked provider route

SenseNova-Loop-9B-Preview is SenseTime's open-source looped multimodal model, released October 30, 2026 for long-context and agentic workflows. It reuses a shared transformer block in loops with manifold-constrained hyper-connection (mHC) residual streams to scale compute depth rather than parameter count, and its decoder groups three linear-attention layers with one full-attention layer. It takes text and images and writes text. Weights are on Hugging Face under Apache 2.0.

No tracked provider route

Canva Brush is Canva's first vision-language model for design, built by Canva Research and unveiled on October 29, 2026. It understands a design's layout and styling and makes the requested edits, from one line of copy to every slide in a deck, through an agentic loop that writes and runs code to adjust design elements and then inspects the page to guide its next step. Everything it changes stays editable. At launch it powers supported design edits in Canva AI for Canva Pro subscribers, with wider availability promised. It has no public API or published weights.

No tracked provider route

d1-2B is Liquid AI's open decision model built on LFM3-VL-2B. It reads text and images and answers yes/no, multiple-choice and scale questions with calibrated probabilities in a single forward pass, without generating tokens. It replaces d1-3B with a third fewer parameters. 128K-token context; open weights under the LFM Open License v1.0.

No tracked provider route

d1-Omni-2B is Liquid AI's open decision model built on LFM3-Omni-2B. It takes the same yes/no, multiple-choice and scale questions as d1-2B over text, images and audio, returning calibrated probabilities in one forward pass, so voice requests can be routed or checked. 128K-token context; open weights under the LFM Open License v1.0.

No tracked provider route