Every model on One API, with its price and measured speed

59 models from 8 providers answered our test calls on 22 November 2026. One key calls all of them.

Get an API key

The catalogue in numbers

Models we could call
59
our probe of 22 November 2026 · measured by us
Providers
8
gateway.plungeai.com
Lowest input price
$0.037 per million tokens
gateway.plungeai.com
Largest context window
2,000,000 tokens
gateway.plungeai.com
Posted below the list price
3
gateway.plungeai.com
Measured on
22 November 2026
our probe · measured by us

By ability

By provider

All models

Every model on One API that answered our probe, by provider
ModelInput, $ per 1MOutput, $ per 1MContext, tokensFirst tokenTokens a second
anthropic/claude-fable-5.1$10$501,000,0002,458 ms571.4
anthropic/claude-haiku-5-5$0.1$0.51,000,0001,013 ms749.2
anthropic/claude-opus-5.5$4$201,000,0001,003 ms252
anthropic/claude-sonnet-5.5$2$101,000,0001,545 ms186.6
cerebras/gpt-oss-120b$0.35$0.75131,072462 msnot measured
cerebras/qwen-3.8-27b$0.99$1.49131,072917 msnot measured
deepinfra/deepseek-ai/DeepSeek-V4.1-Flash$0.2$0.61,048,576489 ms202.3
deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo$0.1$0.32131,0722,169 ms9.2
deepinfra/openai/gpt-oss-120b$0.037$0.17131,0721,192 ms11.1
deepseek/deepseek-v4.1-flash$0.25$0.751,048,576426 ms189.3
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-2.5-flash-lite$0.1$0.41,048,576531 ms90.6
google/gemini-2.5-pro$1.25$102,000,0002,228 msnot measured
google/gemini-3-flash-preview$0.5$31,000,0001,377 msnot measured
google/gemini-3-pro-image$2$1265,5363,980 ms239.9
google/gemini-3.1-flash-image$0.5$3131,0721,228 ms302.2
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
google/gemini-3.1-pro-preview$2$121,048,5764,342 msnot measured
google/gemini-3.5-flash$1.5$91,000,0002,069 msnot measured
google/gemini-3.5-flash-lite$0.3$2.51,048,576850 ms715.2
google/gemini-3.6-flash$0.75$3.751,048,5761,713 msnot measured
google/gemini-3.8-flash$0.825$4.1251,048,5762,820 msnot measured
google/gemini-embedding-001$0.15n/a2,048362 msn/a
google/gemini-embedding-2$0.2n/a8,192391 msn/a
google/gemini-robotics-er-2-preview$1$5131,0721,282 msnot measured
google/gemma-4-26b-a4b-it$0.0675$0.225262,144982 msnot measured
google/gemma-4-31b-it$0.2$0.4262,1441,103 msnot measured
groq/openai/gpt-oss-120b$0.15$0.6131,072378 ms217.2
groq/openai/gpt-oss-20b$0.075$0.3131,072359 msnot measured
groq/qwen/qwen3.8-27b$0.8$4131,072171 ms655.7
meta-llama/llama-3.3-70b-instruct$0.125$0.4131,0721,988 ms6.9
openai/gpt-4.1$2$81,000,000551 ms296.5
openai/gpt-4.1-mini$0.4$1.61,000,000857 ms132.1
openai/gpt-4o$2.5$10128,000506 ms224.5
openai/gpt-4o-mini$0.15$0.6128,000827 ms72.1
openai/gpt-5$1.25$10400,0004,725 ms167.3
openai/gpt-5-mini$0.25$2400,0004,164 ms124.6
openai/gpt-5-nano$0.05$0.4400,0002,712 ms235.4
openai/gpt-5-search-api$1.25$10400,0001,232 ms234.5
openai/gpt-5.2$1.75$14400,000597 ms120.6
openai/gpt-5.4$2.5$15400,000757 ms175.6
openai/gpt-5.4-mini$0.75$4.5400,000575 ms269.3
openai/gpt-5.4-nano$0.2$1.25400,000451 ms159.3
openai/gpt-5.5$5$30400,0001,328 ms122.5
openai/gpt-5.6-luna$0.2$1.21,000,000797 ms220
openai/gpt-5.6-sol$4$201,000,0001,047 ms245.3
openai/gpt-5.6-terra$2$121,000,000845 ms222.1
openai/gpt-6-astra$10$501,050,0001,408 ms186.7
openai/gpt-6-luna$0.1$0.51,050,000995 ms179.1
openai/gpt-6.1-sol$2$101,050,0001,298 ms183.2
openai/gpt-6.1-terra$1$51,050,0001,134 ms94.8
openai/gpt-6.2-astra$8$401,050,0001,292 ms94.5
openai/gpt-oss-120b$0.0463$0.2125131,0721,060 ms11.2
openai/o3$2$8200,0002,050 ms229.2
openai/text-embedding-3-large$0.13n/a8,191455 msn/a
openai/text-embedding-3-small$0.02n/a8,191374 msn/a

Latest changes

Every change

How we measure, and how One API compares

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