Funktion · 2026-11-12

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.

1040 Modelle mit dieser Funktion

Modell	Anbieter	Eingabe / 1M	Ausgabe / 1M	Kontext	Hoster
Qwen3.8 27B	Alibaba (Qwen)	$0.001	$0.001	1.05M	51
PaddleOCR VL	novita-ai	$0.020	$0.020	16K	1
Extract	openrouter	$0.040	Unknown	1M	1
Summarize	openrouter	$0.040	Unknown	1M	1
Gemma 4 26B A4B IT	Google	$0.010	$0.031	262K	23
ScaleDown: Extract	kilo	$0.050	Unknown	1M	1
ScaleDown: Summarize	kilo	$0.050	Unknown	1M	1
DeepSeek OCR 2	DeepSeek	$0.030	$0.030	8K	3
Gemma 3 4B IT	Google	$0.040	$0.050	131K	11
Qwen3.5 9B	Alibaba (Qwen)	$0.040	$0.060	262K	21
Llama-3.2-11B-Vision-Instruct (Deep Infra)	Meta	$0.055	$0.055	131K	4
Qwen3.5 4B	Alibaba (Qwen)	$0.040	$0.070	262K	5
GLM Flash Latest	Z.AI / Zhipu	$0.040	$0.078	1.05M	4
Nex AGI: Nex-N2.5-Mini	kilo	$0.025	$0.100	262K	1
Nex N2.5 Mini	nano-gpt	$0.025	$0.100	262K	1
Nex-N2.5-Mini	openrouter	$0.025	$0.100	262K	1
Model Router	azure-cognitive-services	$0.140	Unknown	200K	1
Model Router	azure	$0.140	Unknown	200K	1
DeepSeek-V4.1-Flash	DeepSeek	$0.030	$0.120	1M	72
DeepSeek V4.1 Flash 1017	DeepSeek	$0.030	$0.120	1.05M	60
Gemma 3 12B IT	Google	$0.050	$0.100	131K	13
Qwen3.7 Flash	Alibaba (Qwen)	$0.030	$0.130	1M	13
Nova Micro 1.0	cortecs	$0.040	$0.159	128K	1
Ministral 3 3B	Mistral	$0.100	$0.100	131K	8
Nemotron 3.5 Content Safety	NVIDIA	$0.050	$0.150	128K	6
Gemini Embedding 2	Google	$0.200	Unknown	8K	5
Reka Edge 2603 (reka-ai)	llmgateway-providers	$0.100	$0.100	16K	1
Reka Edge	kilo	$0.100	$0.100	16K	1
Ministral 3B (latest)	Mistral	$0.100	$0.100	131K	1
Reka Edge 2603	llmgateway	$0.100	$0.100	16K	1
Ministral 3B	llmgateway	$0.100	$0.100	131K	1
Reka Edge	openrouter	$0.100	$0.100	16K	1
Reka Edge 2603	nano-gpt	$0.105	$0.105	16K	1
PrismML: Ternary Bonsai 2 9B	kilo	$0.080	$0.130	262K	1
Ternary Bonsai 2 9B	openrouter	$0.080	$0.130	262K	1
Reka Edge	aimlapi	$0.106	$0.106	16K	1
Qwen-VL OCR	Alibaba (Qwen)	$0.070	$0.160	34K	2
Gemma 3 27B IT	Google	$0.080	$0.160	131K	19
Ling 3.0 Flash VL (DeepInfra)	llmgateway-providers	$0.060	$0.180	131K	1
inclusionAI: Ling 3.0 Flash VL	kilo	$0.060	$0.180	131K	1
Ling 3.0 Flash VL	nano-gpt	$0.060	$0.180	262K	1
Ling 3.0 Flash VL	llmgateway	$0.060	$0.180	131K	1
Coding Xiaomi MiMo-V2.5	aihubmix	$0.080	$0.160	1.05M	1
Ling 3.0 Flash VL	openrouter	$0.060	$0.180	131K	1
GLM-4.6V-Flash	Z.AI / Zhipu	$0.022	$0.218	128K	6
Ministral 3 3B 2512	cortecs	$0.123	$0.123	256K	1
gemini-2.0-flash-lite	Google	$0.052	$0.210	2M	3
Llama Guard 4 12B	Meta	$0.144	$0.144	164K	6
Mistral Small 3.2 24B	Mistral	$0.079	$0.212	256K	5
Ling 3.0 Flash VL	novita-ai	$0.075	$0.220	262K	1
Ling 3.0 Flash VL	vercel	$0.075	$0.220	256K	1
Ministral 3 8B	Mistral	$0.150	$0.150	262K	8
Amazon: Nova Lite 1.0	kilo	$0.060	$0.240	300K	1
Ministral 8B (latest)	Mistral	$0.150	$0.150	262K	1
Pixtral 12B	Mistral	$0.150	$0.150	128K	1
Nova Lite	vercel	$0.060	$0.240	300K	1
Nova Lite (US)	amazon-bedrock	$0.060	$0.240	300K	1
Nova Lite	amazon-bedrock	$0.060	$0.240	300K	1
Nova Lite	edenai	$0.060	$0.240	300K	1
Nova Lite (US)	edenai	$0.060	$0.240	300K	1

Top 60 von 1040 angezeigt. Im vollständigen Verzeichnis weiter filtern.

Frequently asked questions

How many AI models support Bild-Eingabe?

1040 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?

Qwen3.8 27B from Alibaba (Qwen) is currently the lowest-priced option, at $0.001 per 1M input tokens and $0.001 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 (US) (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: GLM-5.3-Flash (92), Kimi K3 (85), DeepSeek-V4.1-Flash (72).

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

Qwen3.8 27B$0.00 in / $0.00 out
PaddleOCR VL$0.02 in / $0.02 out
Extract$0.04 in / $0.00 out
Summarize$0.04 in / $0.00 out
Gemma 4 26B A4B IT$0.01 in / $0.03 out

Other capabilities

Best-of lists you might also want

Pricing comparisons

Vendors in this list

Zuletzt aktualisiert: 2026-11-12

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.