ASCA06
MODEL DECISION PAGE

AI MODEL ATLAS · DECISION PAGE

Vision-language models

Models whose architecture declares image input plus text output.

OBJECT IDasca:openrouter-model-page-vision-language-models@2026-08-27.v1
FETCHED
STATUSREPRODUCIBLE SNAPSHOT

Vision-language models

Filter input_modalities for image and output_modalities for text; derived_cost_usd = prompt + completion USD per 1M text tokens; request price is reported separately and excluded.

OBSERVED MODELS · 10 SHOWN

Comparable fields from one dated catalog snapshot

RANK ≠ QUALITY
Rank / orderModelInput / 1MOutput / 1MRequestContextToolsStructuredDerived cost / basis
140Nex AGI: Nex-N2-Mini$0.025$0.10$0.00262.14KYesYes$0.125 · $ per 1M input + 1M output text tokens
204Google: Gemma 3 4B$0.05$0.10$0.00131.07KNoYes$0.15 · $ per 1M input + 1M output text tokens
50Qwen: Qwen3.7 Flash$0.03$0.13$0.001MYesNo$0.16 · $ per 1M input + 1M output text tokens
131Google: Gemma 3 12B$0.05$0.15$0.00131.07KYesYes$0.20 · $ per 1M input + 1M output text tokens
183Mistral: Ministral 3 3B 2512$0.10$0.10$0.00131.07KYesYes$0.20 · $ per 1M input + 1M output text tokens
341Reka Edge$0.10$0.10$0.0016.38KYesYes$0.20 · $ per 1M input + 1M output text tokens
202OpenAI: GPT-5 Nano (batch)$0.025$0.20$0.00400KYesYes$0.225 · $ per 1M input + 1M output text tokens
219Google: Gemini 2.5 Flash Lite (batch)$0.05$0.20$0.001.05MYesYes$0.25 · $ per 1M input + 1M output text tokens
373OpenAI: GPT-4.1 Nano (batch)$0.05$0.20$0.001.05MYesYes$0.25 · $ per 1M input + 1M output text tokens
100Qwen: Qwen3.5-9B$0.10$0.15$0.00262.14KYesYes$0.25 · $ per 1M input + 1M output text tokens

Prices are listed USD per token converted to USD per 1M tokens. Request fee is a separate listed field; it is not included in derived text-token cost. A free listing means zero listed token price in this snapshot, not unlimited access.

  • Observed range: 238 matching catalog records; 10 shown.
  • Bias: Architecture declaration and catalog bias.
  • Limitation: Modalities do not specify image resolution, video support, visual quality, or successful task performance.
  • Confidence: high for the recorded response and stated transformation.

DOWNLOAD · VERIFY · CITE

Keep the snapshot and object ID with the decision.

Parent model atlas

Filter input_modalities for image and output_modalities for text; derived_cost_usd = prompt + completion USD per 1M text tokens; request price is reported separately and excluded.asca:openrouter-model-page-vision-language-models@2026-08-27.v1