Compare the best 75 image tagging models and try 73 of them on your own images, free in the Roboflow Playground. 27 are open-weight, so you can self-host them for free under their licenses.
75 models · 27 open-weight · 73 free to try · prices synced Sep 21, 2026
We haven't benchmarked image tagging yet; scores and rankings appear on this site only where we've measured them. Until then, compare the models below, and for fixed categories in production expect a model fine-tuned on your own data to win.
27 models with downloadable weights you can self-host under their licenses (MIT, Apache 2.0, and Modified MIT). 25 run live in the Playground through hosted APIs, so self-hosting is optional.
| Actions | ||||
|---|---|---|---|---|
GLM 5.3 FlashZ.ai | 320B total, 18B active | MIT | Aug 2026 | |
Qwen3.8 27BQwen | 27.78B | Apache 2.0 | Aug 2026 | |
Muse Glimmer 30BMeta | 29.6B | Apache 2.0 | Aug 2026 | |
Kimi K3Moonshot AI | 2.8T | Modified MIT | Jul 2026 | |
Qwen3.6 27BQwen | 27B | Apache 2.0 | Apr 2026 | |
Qwen3.6 35B A3BQwen | 35B total, 3B active | Apache 2.0 | Apr 2026 | |
Gemma 4 26B A4BGoogle | 25.2B | Apache 2.0 | Apr 2026 | |
Gemma 4 31BGoogle | 31B | Apache 2.0 | Apr 2026 | |
Qwen3.5 9bQwen | 9B | Apache 2.0 | Mar 2026 | |
| 122B | Apache 2.0 | Feb 2026 | ||
Qwen3.5 35B A3BQwen | 35B | Apache 2.0 | Feb 2026 | |
Qwen3.5-27BQwen | 27B | Apache 2.0 | Feb 2026 | |
| 397B | Apache 2.0 | Feb 2026 | ||
Kimi K2.5Moonshot AI | 1T | Modified MIT | Jan 2026 | |
| 8.8B | Apache 2.0 | Oct 2025 | ||
| 31B | Apache 2.0 | Oct 2025 | ||
| 235B | Apache 2.0 | Sep 2025 | ||
Llama 4 MaverickMeta | 400B | Custom | Apr 2025 | |
Llama 4 ScoutMeta | 109B | Custom | Apr 2025 | |
Mistral Small 3.1 24BMistral | 24B | Apache 2.0 | Mar 2025 | |
Gemma 3 12BGoogle | 12B | Custom | Mar 2025 | |
Gemma 3 27BGoogle | — | Custom | Mar 2025 | |
Gemma 3 4BGoogle | 4B | Custom | Mar 2025 | |
| 7B | Apache 2.0 | Jan 2025 | ||
Pixtral 12BMistral | 12B | Apache 2.0 | Sep 2024 | |
SigLIPGoogle | 200M-900M | Apache 2.0 | Mar 2023 | |
CLIPOpenAI | — | MIT | Feb 2021 |
48 proprietary models where the weights aren't downloadable: access is through each provider's API and billed by them. Try all of them free in the Playground.
| Actions | |||||
|---|---|---|---|---|---|
GPT-6 AstraOpenAI | $10.00 | $50.00 | 1.1M | Sep 2026 | |
Gemini 3.8 FlashGoogle | $0.75 | $3.75 | 1.0M | Sep 2026 | |
Muse Spark 1.3Meta | $1.25 | $4.25 | 1.0M | Sep 2026 | |
Claude Fable 5.1Anthropic | $10.00 | $50.00 | 1M | Sep 2026 | |
Qwen3.8 FlashQwen | $0.15 | $0.47 | 1M | Aug 2026 | |
Gemini 3.7 FlashGoogle | $0.75 | $3.75 | 1.0M | Aug 2026 | |
Grok 4.6SpaceXAI | $2.00 | $6.00 | 500K | Aug 2026 | |
Muse Spark 1.2Meta | $1.25 | $4.25 | 1.0M | Aug 2026 | |
Qwen3.8 MaxQwen | — | — | 984K | Aug 2026 | |
Qwen3.7 FlashQwen | $0.030 | $0.13 | 1M | Jul 2026 | |
Gemini 3.5 Flash-LiteGoogle | $0.30 | $2.50 | 1.0M | Jul 2026 | |
Gemini 3.6 FlashGoogle | $0.75 | $3.75 | 1M | Jul 2026 | |
GPT-5.6 LunaOpenAI | $0.20 | $1.20 | 1.5M | Jul 2026 | |
GPT-5.6 SolOpenAI | $2.00 | $10.00 | 1.5M | Jul 2026 | |
GPT-5.6 TerraOpenAI | $2.00 | $12.00 | 1.1M | Jul 2026 | |
Muse Spark 1.1Meta | $1.25 | $4.25 | 1.0M | Jul 2026 | |
Grok 4.5SpaceXAI | $2.00 | $6.00 | 500K | Jul 2026 | |
Claude Sonnet 5Anthropic | $2.00 | $10.00 | 1M | Jun 2026 | |
Claude Fable 5Anthropic | $10.00 | $50.00 | 1M | Jun 2026 | |
Claude Opus 4.8Anthropic | $5.00 | $25.00 | 1M | May 2026 | |
Gemini 3.5 FlashGoogle | $1.50 | $9.00 | 1.0M | May 2026 | |
GPT-5.5OpenAI | $5.00 | $30.00 | 1M | Apr 2026 | |
Claude Opus 4.7Anthropic | $5.00 | $25.00 | 1M | Apr 2026 | |
Qwen3.6 FlashQwen | $0.19 | $1.13 | 1M | Apr 2026 | |
Qwen3.6 PlusQwen | $0.33 | $1.95 | 1M | Apr 2026 | |
GLM 5V TurboZ.ai | $1.20 | $4.00 | 200K | Apr 2026 | |
GPT-5.4 MiniOpenAI | $0.75 | $4.50 | 400K | Mar 2026 | |
GPT-5.4 NanoOpenAI | $0.20 | $1.25 | 400K | Mar 2026 | |
GPT-5.4OpenAI | $2.50 | $15.00 | 1.1M | Mar 2026 | |
Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.50 | 1M | Mar 2026 | |
Gemini 3.1 ProGoogle | $2.00 | $12.00 | 1M | Feb 2026 | |
Claude Sonnet 4.6Anthropic | $3.00 | $15.00 | 1M | Feb 2026 | |
Claude Opus 4.6 Anthropic | $5.00 | $25.00 | 1M | Feb 2026 | |
Gemini 3 FlashGoogle | $0.50 | $3.00 | 1M | Dec 2025 | |
GPT-5.2OpenAI | $1.75 | $14.00 | 400K | Dec 2025 | |
Claude Opus 4.5Anthropic | $5.00 | $25.00 | 200K | Nov 2025 | |
GPT-5.1OpenAI | $1.25 | $10.00 | 196K | Nov 2025 | |
Claude Haiku 4.5Anthropic | $1.00 | $5.00 | 200K | Oct 2025 | |
Claude Sonnet 4.5Anthropic | $3.00 | $15.00 | 200K | Sep 2025 | |
Mistral Medium 3.1Mistral | $0.40 | $2.00 | 128K | Aug 2025 | |
GPT-5OpenAI | $1.25 | $10.00 | — | Aug 2025 | |
GPT-5 MiniOpenAI | $0.25 | $2.00 | 400K | Aug 2025 | |
GPT-5 NanoOpenAI | $0.050 | $0.40 | 400K | Aug 2025 | |
Gemini 2.5 Flash-LiteGoogle | $0.10 | $0.40 | 1M | Jul 2025 | |
Gemini 2.5 FlashGoogle | $0.30 | $2.50 | 1M | Jul 2025 | |
Grok 4SpaceXAI | — | — | — | Jul 2025 | |
Gemini 2.5 ProGoogle | $1.25 | $10.00 | 1M | Jun 2025 | |
Qwen VL MaxQwen | — | — | — | Feb 2025 |
Tagging assigns many keywords per image, and the choice hinges on one question: is your tag vocabulary open-ended or fixed?
CLIP-style models score any tag text against an image, so your vocabulary can be whatever you want it to be at query time, and VLMs will simply write a keyword list from a prompt. This suits digital asset management and photo search, where the useful tags differ per library and evolve over time.
When tags come from a controlled vocabulary (product attributes, content categories), a trained multi-label classifier with tuned per-tag thresholds is more consistent, far cheaper per image, and easier to evaluate: precision and recall per tag against a fixed list. Zero-shot approaches drift on synonyms and borderline cases that a trained model learns to call consistently.
The bottom line: Open, evolving vocabularies favor CLIP-style or VLM tagging; a fixed taxonomy at volume favors a trained multi-label classifier with calibrated thresholds.
Image tagging is the task of assigning multiple descriptive keywords to an image, such as "beach", "sunset", and "people", rather than forcing a single category. Technically it is multi-label prediction: the model scores each candidate tag independently (a sigmoid per tag instead of one softmax), and CLIP-style embedding models can tag against an open vocabulary by matching the image to arbitrary tag texts. Precision and recall are evaluated per tag because a photo legitimately carries many. Tagging feeds digital asset management, photo library search, e-commerce attribute enrichment, and metadata generation at scale. This page lists 75 image tagging models, including 27 open-weight options you can self-host; 73 of them run live in the Playground so you can test them on your own images.
It depends on your task and constraints. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model. Compare the image tagging models on this page and try them on your own images to see which fits.
Yes. 27 of the 75 image tagging models here are open-weight (for example GLM 5.3 Flash, Qwen3.8 27B, and Muse Glimmer 30B), free to self-host under their licenses (MIT, Apache 2.0, and Modified MIT).
Yes. You can run 73 of them in the Roboflow Playground for free. Upload an image and compare the models' output side by side, no setup required.
This page lists all 75 image tagging models in the Roboflow Playground catalog: 27 open-weight models you can self-host and 48 proprietary models accessed through provider APIs; 73 of them run live in the Roboflow Playground on your own images. Compare licenses, parameters, API prices, and release dates side by side, or open any model page for full details.