Compare flagship and efficient AI models for journalism — context windows, indicative token pricing, and newsroom workflow tags. Sources refresh from OpenRouter and Groq.
Could not refresh Groq prices from groq.com/pricing (Could not parse any pricing rows from Groq pricing page (markup may have changed).). Groq rows use bundled catalog fallback until the next sync.
Showing 21 of 48 in this view
API / route id
gpt-oss-120b
Open-weight workhorse when you self-host or run on fast inference (e.g. Groq).
API / route id
muse-glimmer-30b
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.
API / route id
muse-spark-1.2
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context window. Modality: text+image+file+audio+video->text. Inputs: text, image, video, file, audio. Outputs: text
API / route id
qwen3-coder-next
Open-weight coding specialist for CI, scrapers, CMS integrations, and internal bots.
API / route id
gpt-5-chat
Low-latency conversational UX — alerts, briefs, and interactive assistants.
API / route id
muse-spark-1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context... Modality: text+image+file+audio+video->text. Inputs: text, image, video, file, audio. Outputs: text
API / route id
claude-opus-5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... Modality: text+image+file->text. Inputs: text, image, file. Outputs: text
API / route id
whisper-large-v3
Whisper Large v3 is OpenAI's most advanced and capable speech recognition model, delivering state-of-the-art accuracy across a wide range of audio conditions and languages. This flagship model excels at handling challenging audio scenarios including background noise, accents, and technical terminology.
API / route id
openai/gpt-oss-120b
Highest intelligence on Groq — complex analysis with very fast tokens/sec.
API / route id
openai/gpt-oss-20b
Fastest throughput for lightweight drafting and realtime tools.
API / route id
whisper-large-v3-turbo
Fast multilingual speech-to-text on Groq — interviews, briefings, and rough-cut transcripts at low cost per audio hour.
API / route id
lightonai/LightOnOCR-2-1B
LightOnOCR-2 is an efficient end-to-end 1B-parameter vision-language model for converting documents (PDFs, scans, images) into clean, naturally ordered text without relying on brittle pipelines.
API / route id
gemma-3-27b-it
Open-weight Google model for self-hosted or budget-conscious pipelines and tooling.
API / route id
flux.2-klein-4b
Fastest, most cost-effective FLUX.2 tier — high-throughput thumbnails, social crops, and batch image generation.
API / route id
kimi-k2.5
Agentic coding and large-repo work — strong for newsroom engineering and data tooling.
API / route id
gpt-5.6
Reasoning model for higher-quality responses on complex tasks.
API / route id
claude-fable-5
Claude Fable 5 is state-of-the-art on nearly all tested benchmarks of AI capability, showing exceptional performance in software engineering, knowledge work, vision, scientific research, and many other areas. The longer and more complex the task, the larger Fable 5’s lead over our other models. Modality: text+image+file->text. Inputs: text, image, file. Outputs: text
API / route id
claude-sonnet-5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels. Modality: text+image+file->text. Inputs: text, image, file. Outputs: text
API / route id
mistral-ocr-latest
Mistral OCR 4 is a document-intelligence model that turns PDFs and other files into structured, richly annotated content instead of plain text. It extracts text with bounding boxes, block types, and confidence scores, enabling better RAG chunking, agentic workflows (like form filling or invoice processing), and robust ingestion/search pipelines across 170 languages.
API / route id
gpt-4o-audio-preview
GPT-4–class audio conversations when quality matters more than Mini pricing.
API / route id
claude-opus-4.8
Model is designed for complex reasoning, advanced coding, and long-running AI workflows. With support for text, images, files, and a 1M-token context window, it excels at autonomous agents, large codebases, building presentations, multi-step problem solving, document creation, data analysis, and other knowledge-intensive tasks that require maintaining coherence across long sessions.
Showing 21 of 48 in this snapshot · 48 total in the live catalog.