New1M contextAdjustable thinking

Google · Frontier reasoning

Gemini 4 Argon

Google’s most capable Gemini model, built for software engineering and knowledge work, with a 1M-token context window and adjustable thinking levels.

View modelSee docs

AI Models

230 models ready to compare

muse-wonder-1.0 logo

Meta: Muse Wonder 1.0

meta

Muse Wonder 1.0 is Meta's frontier multimodal reasoning and agentic AI model developed by Meta Superintelligence Labs. It is designed for complex software engineering, long-running autonomous workflows, professional knowledge work, and advanced computer use. The model supports a 1,048,576-token context window, text, image, audio, video and PDF understanding, tool calling, structured outputs, search grounding, and configurable reasoning effort from minimal to max. It introduces Active Memory for retaining relevant information across conversations and Active Focus for sustaining multi-step tasks, recovering from errors, delegating to sub-agents and verifying results. Muse Wonder is optimized for coding, financial analysis, legal research, healthcare reasoning, browser automation, desktop interaction and agent orchestration.

Input Cost:$4.000 / 1M tokens
Output Cost:$20.000 / 1M tokens
Context Length:1M
gemini-omni-1.1-flash logo

Google: Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google's high-performance multimodal video generation and editing model designed for fast, conversational video creation and cinematic control. It supports text-to-video, image-to-video, video-to-video editing, natural-language conversational editing, video extension, first-and-last-frame interpolation, and resolution upscaling. The model combines multimodal understanding with generative video capabilities to produce coherent, controllable video with synchronized audio. It supports a 1,048,576-token context window and generates videos lasting 3 to 10 seconds at 24 FPS, with output resolutions ranging from 360p to 4K. It is suitable for filmmaking, advertising, animation, social media content, creative production, and iterative video editing workflows.

Video generation:$0.1028 / second
Pricing options:4 tiers
gemini-omni-flash-preview logo

Google: Gemini Omni Flash

Gemini Omni Flash is Google's multimodal video generation and editing model designed for fast, conversational video creation. It supports text-to-video, image-to-video, video-to-video editing, video extension, keyframe interpolation, resolution upscaling, and natural-language iterative editing through the Gemini Interactions API. The model generates videos with synchronized audio and supports a 1,048,576-token context window. It can generate videos lasting 3 to 10 seconds at 24 FPS, with supported output resolutions ranging from 360p to 4K. It is suitable for advertising, filmmaking, animation, social media production, and creative video workflows.

Video generation:$0.1028 / second
Pricing options:4 tiers
claude-haiku-5-5 logo

Anthropic: Claude Haiku 5.5

anthropic

Claude Haiku 5.5 is Anthropic's fastest, cheapest, and most capable Haiku-class model, designed for high-volume, latency-sensitive, and cost-sensitive workloads. It is optimized for classification, extraction, routing, summarization, database queries, live customer support, browser use, subagent workflows, and lightweight coding tasks. The model supports a 1M-token context window, up to 128K output tokens, adaptive thinking with configurable effort, vision, tool use, computer use, and agentic workflows. Haiku 5.5 is particularly suited to applications requiring high throughput and low latency while retaining strong reasoning, coding, computer-use, and knowledge-work capabilities.

Input Cost:$0.500 / 1M tokens
Output Cost:$2.500 / 1M tokens
Context Length:1M
inclusionai/ling-3.1-flash logo

InclusionAI: Ling 3.1 Flash

novita

Ling 3.1 Flash is InclusionAI's large-scale hybrid reasoning Mixture-of-Experts model designed for coding, agentic workflows, professional knowledge work, long-context analysis, finance, healthcare, and complex multi-step tasks. It contains approximately 560 billion total parameters while activating about 25 billion parameters per token, enabling high model capacity with more efficient inference. The model supports hybrid reasoning, tool calling, long documents, large codebases, extended task histories, and multi-step agent execution. It is optimized for software engineering, terminal-based agents, workflow automation, financial analysis, research, healthcare reasoning, and other tool-intensive professional applications.

New
Input Cost:$0.300 / 1M tokens
Output Cost:$0.900 / 1M tokens
Context Length:256K
together/Tev1-4B-experimental logo

Together AI: Tev1 4B Experimental

together_ai

Tev1-4B-experimental is Together AI's experimental decision model built by supervised fine-tuning Qwen3.5-4B for structured classification and routing tasks. Given an application state, a question, and between 2 and 24 labeled options, the model selects exactly one option rather than producing a conventional free-form response. It is designed for fast decision-making workloads such as intent classification, request routing, policy checks, moderation, workflow automation, and other closed-set decisions. Tev1 is inspired by Jev-style decision models but retains Qwen's standard autoregressive next-token language-model head, allowing it to run through conventional chat-completions infrastructure. Together AI publishes the training recipe and evaluation tooling, making the model useful both as a production decision model and as a reference for building custom classifiers.

New
Input Cost:$0.042 / 1M tokens
Output Cost:$0.000 / 1M tokens
Context Length:32K

AI Model Catalog

One API. 200+ models. No infrastructure management. Browse the full catalog below and start making inference calls in minutes.

200+

Models available

From frontier LLMs to specialised vision and audio models, all accessible through one unified endpoint.

<500ms

Median latency

Custom CUDA kernel optimisation and intelligent multi-cloud routing keep time-to-first-token consistently low.

80%

Average cost reduction

Teams migrating from direct cloud GPU billing to OneInfer's subscription model typically cut inference spend by 60-80%.

1 line

To switch models

Swap from GPT-4o to Llama 3, or from Whisper to a custom ASR model, with a single parameter change.

Text and Language Models

OneInfer hosts the full range of major large language models including GPT-4o, Claude 3, Llama 3, Mistral, Gemma, and dozens of fine-tuned variants. Every text model is available through the same chat completions API endpoint, with per-token pricing that scales linearly and no cold-start penalty. For production workloads requiring consistent throughput, dedicated endpoints isolate your traffic from shared capacity and guarantee SLA-backed response times.

Vision and Multimodal Models

Vision-language models like GPT-4V, LLaVA, and CogVLM are available for image understanding, document analysis, and visual question answering. Image generation models including Stable Diffusion XL, FLUX, and DALL-E 3 are exposed via a standardised image generation endpoint. All vision models accept base64-encoded or URL-referenced images, and the response format is consistent across providers so switching models requires no code changes beyond the model identifier.

Audio and Speech Models

Speech-to-text models including Whisper large-v3, Distil-Whisper, and provider-specific ASR models are accessible for transcription, translation, and voice activity detection. Text-to-speech synthesis is available with multiple voice options and sample rates. All audio models accept standard audio formats — MP3, WAV, FLAC, and OGG — and return structured JSON responses with transcripts, timestamps, and confidence scores where supported.

Embedding and Retrieval Models

Embedding models including text-embedding-3-large, Cohere Embed v3, and BGE are available for semantic search, retrieval-augmented generation (RAG), and clustering workloads. OneInfer's embedding endpoint returns normalised vectors in a consistent schema regardless of which provider generates them, so you can benchmark models against each other without rewriting your vector store integration. Batch embedding requests are supported for processing large document corpora efficiently.

How Pricing Works

Every model in the catalog has per-token or per-request pricing shown directly in the catalog below. There are no egress fees, no minimum spend commitments on the pay-as-you-go tier, and no markup for routing across providers. Subscription plans offer a monthly credit allocation at a predictable flat rate, which is how most production teams reduce their AI infrastructure bill by 60% or more versus paying cloud providers directly.

Pricing is updated in real time as providers adjust their rates. The catalog always reflects the current cost, so you can make accurate cost projections before committing to a model. For high-volume workloads, dedicated endpoint pricing is available on request and typically offers a further 20–30% reduction over pay-as-you-go rates.