Funktion · 2026-09-28

KI-Modelle mit Vision-Eingabe

Modelle, die Bilder zusammen mit Text akzeptieren — multimodales Verständnis.

Was ist das?

Vision-Sprachmodelle akzeptieren Bildinputs neben oder anstelle von Text.
Die meisten antworten mit Text — es sind multimodale LLMs, keine Bildgeneratoren.

Warum wichtig

Use Cases: Dokumentenverständnis (Scan, PDF, Screenshot), UI-/Code-Review aus Screenshots, Produktfotos, Barrierefreiheit (Alt-Text), Medizin/Satellitenbilder.
Die Abrechnung enthält oft pro Bild zusätzliche Tokenkosten — siehe Offering-Tabellen der Anbieter.

889 Modelle mit dieser Funktion

Modell	Anbieter	Eingabe / 1M	Ausgabe / 1M	Kontext	Hoster
PaddleOCR-VL	novita-ai	$0.020	$0.020	16K	1
DeepSeek OCR 2	DeepSeek	$0.030	$0.030	8K	3
Ling 3.0 Flash VL	openrouter	$0.021	$0.062	262K	1
Llama 3.2 11B Vision Instruct	Meta	$0.055	$0.055	128K	4
Qwen3.5 4B	Alibaba (Qwen)	$0.040	$0.070	262K	3
Gemma 3 4B IT	Google	$0.040	$0.080	131K	10
Model Router	azure	$0.140	Unknown	200K	1
Model Router	azure-cognitive-services	$0.140	Unknown	200K	1
Gemma 3 12B IT	Google	$0.050	$0.100	131K	12
Qwen3.7 Flash	Alibaba (Qwen)	$0.030	$0.130	1M	13
GLM Flash Latest	Z.AI / Zhipu	$0.045	$0.140	1.31M	4
Qwen3.5 9B	Alibaba (Qwen)	$0.040	$0.150	262K	23
nova-micro-v1	cortecs	$0.040	$0.159	128K	1
Ministral 3 3B 2512	Mistral	$0.100	$0.100	131K	4
Nemotron 3.5 Content Safety	NVIDIA	$0.050	$0.150	131K	4
Gemini Embedding 2	Google	$0.200	Unknown	8K	4
Agnes 3.0 Flash	nano-gpt	$0.050	$0.150	524K	1
Space Bunny Alpha	nano-gpt	$0.050	$0.150	1M	1
Reka Edge	kilo	$0.100	$0.100	16K	1
Reka Edge	openrouter	$0.100	$0.100	16K	1
Ministral 3B	llmgateway	$0.100	$0.100	131K	1
Greg 1 Mini	crof	$0.070	$0.150	229K	1
Gemma 3 27B IT	Google	$0.080	$0.160	131K	17
Ling 3.0 Flash VL	nano-gpt	$0.060	$0.180	262K	1
Ling 3.0 Flash VL (DeepInfra)	llmgateway-providers	$0.060	$0.180	131K	1
Ling 3.0 Flash VL	llmgateway	$0.060	$0.180	131K	1
GLM-4.6V-Flash	Z.AI / Zhipu	$0.022	$0.218	128K	6
ministral-3b-2512	cortecs	$0.123	$0.123	256K	1
Gemma 4 26B A4B IT	Google	$0.042	$0.220	262K	22
Gemini-2.0-Flash-Lite	Google	$0.052	$0.210	990K	3
inclusionAI: Ling 3.0 Flash VL	kilo	$0.075	$0.220	262K	1
Ling 3.0 Flash VL	vercel	$0.075	$0.220	256K	1
Ministral 3 8B 2512	Mistral	$0.150	$0.150	262K	4
Gemma 4 12B Instruct	Google	$0.050	$0.250	131K	3
Amazon: Nova Lite 1.0	kilo	$0.060	$0.240	300K	1
Nova Lite 1.0	openrouter	$0.060	$0.240	300K	1
Nova Lite	vercel	$0.060	$0.240	300K	1
Nova Lite (US)	edenai	$0.060	$0.240	300K	1
Nova Lite	edenai	$0.060	$0.240	300K	1
Pixtral 12B	Mistral	$0.150	$0.150	128K	1
Nova Lite (US)	amazon-bedrock	$0.060	$0.240	300K	1
Nova Lite	amazon-bedrock	$0.060	$0.240	300K	1
Ministral 8B	llmgateway	$0.150	$0.150	262K	1
Muse Spark 1.2 Contributor	Meta	$0.100	$0.200	1.05M	6
Muse Spark 1.3 Contributor	Meta	$0.100	$0.200	1.05M	5
Muse Spark 1.3 Contributor	bothub	$0.100	$0.200	1.05M	1
Muse Spark 1.2 Contributor (Meta Contributor)	llmgateway-providers	$0.100	$0.200	1.05M	1
Muse Spark 1.3 Contributor (Meta Contributor)	llmgateway-providers	$0.100	$0.200	1.05M	1
Muse Spark 1.2 Contributor	opencode-go	$0.100	$0.200	1.05M	1
Muse Spark 1.3 Contributor	opencode-go	$0.100	$0.200	1.05M	1
Muse Spark 1.2 Contributor	llmgateway	$0.100	$0.200	1.05M	1
Muse Spark 1.3 Contributor	llmgateway	$0.100	$0.200	1.05M	1
Seed 2.0 Mini	ByteDance (Doubao)	$0.030	$0.280	256K	5
Seed 2.0 Mini (260428) (ByteDance)	ByteDance (Doubao)	$0.030	$0.280	262K	3
Nova Lite (APAC)	amazon-bedrock	$0.063	$0.252	300K	1
Nova Lite (CA)	amazon-bedrock	$0.064	$0.256	300K	1
Qwen-Omni Turbo	Alibaba (Qwen)	$0.070	$0.270	33K	4
Mistral Small 3.2 24B	Mistral	$0.094	$0.250	256K	4
nova-lite-v1	cortecs	$0.069	$0.275	300K	1
Nova Lite (EU)	amazon-bedrock	$0.069	$0.276	300K	1

Top 60 von 889 angezeigt. Im vollständigen Verzeichnis weiter filtern.

Frequently asked questions

How many AI models support Bild-Eingabe?

889 canonical models in our database currently support Bild-Eingabe. The list is regenerated on every data refresh, so it always reflects the latest releases tracked in our catalogue.

What is the cheapest model with Bild-Eingabe?

PaddleOCR-VL from novita-ai is currently the lowest-priced option, at $0.020 per 1M input tokens and $0.020 per 1M output tokens. The full table above is sorted price-ascending.

Which model with Bild-Eingabe has the largest context window?

Llama 4 Scout 17B Instruct (Meta) leads on context at 10M tokens. This may matter if you also need long-document understanding alongside Bild-Eingabe.

Which models are available on the most providers?

Production-readiness usually correlates with how many independent providers host the same weights. The top three by provider count are: Kimi K3 (75), GLM-5.3-Flash (71), DeepSeek V4 Flash (70).

How is Bild-Eingabe different from a regular LLM?

Vision-language models accept image input alongside text. They are multimodal LLMs, not image generators — most reply in text after looking at the image.

How often is this list updated?

Daily. Our data pipeline syncs once a day, regenerates the canonical model list, and rebuilds these pages so newly released models appear within 24 hours.

Top models with this capability

PaddleOCR-VL$0.02 in / $0.02 out
DeepSeek OCR 2$0.03 in / $0.03 out
Ling 3.0 Flash VL$0.02 in / $0.06 out
Llama 3.2 11B Vision Instruct$0.06 in / $0.06 out
Qwen3.5 4B$0.04 in / $0.07 out

Other capabilities

Best-of lists you might also want

Pricing comparisons

Vendors in this list

Zuletzt aktualisiert: 2026-09-28

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.