Models that read images

33 models we could call on 22 November 2026, cheapest input first.

Get an API key

Vision: cheapest input first

Models that read images on One API, cheapest input first
ModelInput, $ per 1MOutput, $ per 1MContext, tokensFirst tokenTokens a second
openai/gpt-5-nano$0.05$0.4400,0002,712 ms235.4
google/gemini-2.5-flash-lite$0.1$0.41,048,576531 ms90.6
anthropic/claude-haiku-5-5$0.1$0.51,000,0001,013 ms749.2
openai/gpt-4o-mini$0.15$0.6128,000827 ms72.1
openai/gpt-5.4-nano$0.2$1.25400,000451 ms159.3
openai/gpt-5.6-luna$0.2$1.21,000,000797 ms220
deepinfra/deepseek-ai/DeepSeek-V4.1-Flash$0.2$0.61,048,576489 ms202.3
deepseek/deepseek-v4.1-flash$0.25$0.751,048,576426 ms189.3
google/gemini-3.1-flash-lite$0.25$1.51,000,000858 ms739.6
google/gemini-3.1-flash-lite-image$0.25$1.565,536963 ms476.3
google/gemini-3.1-flash-lite-preview$0.25$1.51,048,576793 ms758.8
openai/gpt-5-mini$0.25$2400,0004,164 ms124.6
google/gemini-2.5-flash$0.3$2.51,000,0001,191 msnot measured
google/gemini-2.5-flash-image$0.3$2.532,768724 ms32.6
google/gemini-3.5-flash-lite$0.3$2.51,048,576850 ms715.2
google/gemini-3-flash-preview$0.5$31,000,0001,377 msnot measured
google/gemini-3.1-flash-image$0.5$3131,0721,228 ms302.2
google/gemini-3.6-flash$0.75$3.751,048,5761,713 msnot measured
openai/gpt-5.4-mini$0.75$4.5400,000575 ms269.3
groq/qwen/qwen3.8-27b$0.8$4131,072171 ms655.7
cerebras/qwen-3.8-27b$0.99$1.49131,072917 msnot measured
google/gemini-robotics-er-2-preview$1$5131,0721,282 msnot measured
google/gemini-2.5-pro$1.25$102,000,0002,228 msnot measured
openai/gpt-5$1.25$10400,0004,725 ms167.3
google/gemini-3.5-flash$1.5$91,000,0002,069 msnot measured
openai/gpt-5.2$1.75$14400,000597 ms120.6
google/gemini-3-pro-image$2$1265,5363,980 ms239.9
google/gemini-3.1-pro-preview$2$121,048,5764,342 msnot measured
openai/gpt-5.6-terra$2$121,000,000845 ms222.1
openai/gpt-4o$2.5$10128,000506 ms224.5
openai/gpt-5.4$2.5$15400,000757 ms175.6
openai/gpt-5.6-sol$4$201,000,0001,047 ms245.3
openai/gpt-5.5$5$30400,0001,328 ms122.5

How a model gets on this list

  • A model is listed here when the price feed marks it as accepting images and it answered our probe.
  • The probe sends text only; image input is not measured.

Other lists

How this page is made

Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.

Data checked · Last changed

Get an API key