Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the Pareto family.
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.
No provider description is available for this model yet.
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
No provider description is available for this model yet.
No provider description is available for this model yet.
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.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| ScaleDown: Extractscaledown/extract | 1M | $0.04 | — | — | |||
| ScaleDown: Summarizescaledown/summarize | 1M | $0.04 | — | — | |||
| Meta: Muse Wondermeta/muse-wonder | Meta |
1.04858M | $4 | $20 | — | ||
| deepseek-v4.1-flash-fastcoralbricks/deepseek-v4.1-flash-fast | 1.04858M | $0.01 | $1.2 | — | |||
| deepseek-v4.1-flash-fast-fp4coralbricks/deepseek-v4.1-flash-fast-fp4 | 1.04858M | $0.01 | $1.2 | — | |||
| deepseek-v4.1-flashcoralbricks/deepseek-v4.1-flash | 1.04858M | $0.01 | $1.2 | — | |||
| computer-use-preview-2025-03-11openai/computer-use-preview-2025-03-11 | OpenAI |
8.192K | $3 | $12 | — | ||
| gemini-robotics-er-2-previewvertex_ai/gemini-robotics-er-2-preview | 131.072K | $1 | $5 | — | |||
| gemini-robotics-er-2-previewvertex_ai-language-models/gemini-robotics-er-2-preview | 131.072K | $1 | $5 | — | |||
| claude-fable-5-5azure_ai/claude-fable-5-5 | 1M | $10 | $50 | — | |||
| Google: Gemini 4 Argon (batch)google/gemini-4-argon:batch | Google |
1.04858M | $1 | $5 | — | ||
| deepseek-v4.1-flashtencent/deepseek-v4.1-flash | Tencent |
1M | $0.3 | $1.2 | — | ||
| glm-5.3-flashxtencent/glm-5.3-flashx | Tencent |
1M | $0.37 | $1.25 | — | ||
| glm-5.3-flashtencent/glm-5.3-flash | Tencent |
1M | $0.15 | $0.5 | — | ||
| gemini-4-argongemini/gemini-4-argon | 1.04858M | $2 | $10 | — | |||
| gemini-4-argonvertex_ai/gemini-4-argon | 1.04858M | $2 | $10 | — | |||
| gemini-4-argon-cyber-permissivevertex_ai/gemini-4-argon-cyber-permissive | 1.04858M | $4 | $20 | — | |||
| gemini-4-argongithub_copilot/gemini-4-argon | Github_Copilot |
200K | $2 | $10 | — | ||
| Pareto Latest~unbiased/pareto-latest | 1.04858M | $0.8 | $3.2 | — | |||
| Pareto 26.9unbiased/pareto-26.9 | 262.144K | $2.5 | $7.5 | — | |||
| DeepSeek-V4.1-flashscx-ai/deepseek-v4.1-flash | 1M | $0.15 | $0.6 | — | |||
| NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | NVIDIA |
262.144K | $0.15 | $0.5 | — | ||
| NVIDIA: Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:free | NVIDIA |
1M | Free | Free | — | ||
| nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GBnvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB | NVIDIA |
Not documented | — | — | — | ||
| Qwen/Qwen3-VL-235B-A22B-Instructinferenceapis/qwen/qwen3-vl-235b-a22b-instruct | 262.144K | $0.26 | $1.15 | — | |||
| qwen3-vlinferenceapis/qwen3-vl | 262.144K | $0.26 | $1.15 | — | |||
| qwen3-vl-235binferenceapis/qwen3-vl-235b | 262.144K | $0.26 | $1.15 | — | |||
| nvidia/NVIDIA-Nemotron-3.5-Super-VLtogether_ai/nvidia/nvidia-nemotron-3.5-super-vl | 262.144K | $0.15 | $0.5 | — | |||
| accounts/fireworks/models/muse-spark-openfireworks_ai/accounts/fireworks/models/muse-spark-open | Fireworks_Ai |
1.04858M | $1.25 | $4.25 | — | ||
| jp.amazon.nova-2-lite-v1:0bedrock_converse/jp.amazon.nova-2-lite-v1:0 | 1M | $0.396 | $3.311 | — | |||
| deepseek-ai/deepseek-v4.1-flash-maasvertex_ai-deepseek_models/deepseek-ai/deepseek-v4.1-flash-maas | 1.04858M | — | — | — | |||
| Moondream: Moondream 3 Previewmoondream/moondream3-preview | 32K | $0.3 | $2.5 | — | |||
| Moondream: Moondream 3.1moondream/moondream3.1-9b-a2b | 32K | $0.3 | $2.5 | — | |||
| claude-opus-5-5-fastazure_ai/claude-opus-5-5-fast | 1M | $8 | $40 | — | |||
| meta-models/muse-spark-openbaseten/meta-models/muse-spark-open | Baseten |
1.04858M | $1.25 | $4.25 | — | ||
| nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12Bbaseten/nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b | Baseten |
1.04858M | $0.2 | $0.5 | — | ||
| nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12Bwandb/nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b | Wandb |
1.049M | $0.15 | $0.75 | — | ||
| Elorian: Glimpseelorian/glimpse | 262.144K | $0.6 | $3 | — | |||
| Qwen: Qwen3.7 Plus (batch)qwen/qwen3.7-plus:batch | Alibaba Qwen |
262.144K | $0.23 | $0.92 | — | ||
| deepseek-ai/DeepSeek-V4.1-Flashdeepinfra/deepseek-ai/deepseek-v4.1-flash | Deepinfra |
1.04858M | $0.14 | $0.42 | — | ||
| deepseek-ai/DeepSeek-V4.1-Flash-1017deepinfra/deepseek-ai/deepseek-v4.1-flash-1017 | Deepinfra |
1.04858M | $0.14 | $0.42 | — | ||
| Pareto 26.10unbiased/pareto-26.10 | 1.04858M | $0.8 | $3.2 | — | |||
| deepseek-ai/DeepSeek-V4.1-Flash-1017baseten/deepseek-ai/deepseek-v4.1-flash-1017 | Baseten |
1.04858M | $0.3 | $1.2 | — | ||
| deepseek-ai/DeepSeek-V4.1-Flash-1017-Fastbaseten/deepseek-ai/deepseek-v4.1-flash-1017-fast | Baseten |
1.04858M | $0.6 | $2.4 | — | ||
| accounts/fireworks/models/deepseek-v4p1-flash-1017fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017 | Fireworks_Ai |
1.04858M | $0.3 | $1.2 | — | ||
| claude-sonnet-4.6github_copilot/claude-sonnet-4.6 | Github_Copilot |
200K | $3 | $15 | — | ||
| grok-4.5github_copilot/grok-4.5 | Github_Copilot |
500K | $2 | $6 | — | ||
| grok-4.6github_copilot/grok-4.6 | Github_Copilot |
500K | $2 | $6 | — | ||
| grok-4.7github_copilot/grok-4.7 | Github_Copilot |
500K | $2 | $6 | — | ||
| MiniMax: MiniMax M3.1 Flash (free)minimax/minimax-m3.1-flash:free | MiniMax |
1M | Free | Free | — |