AI Rate CardTools: pick a model by cost
Find the cheapest offer for your monthly workload, count the tokens of a prompt, convert price units.
Cost picker
How many tokens a month you send to the model (input) and get back (output), in millions. For example, a chatbot with 1,000 conversations a day is about 10 M input and 2 M output. Don't know your numbers? Count them below in the token estimator.
Model: GPT OSS 20B ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| GPT OSS 20B | edenai via Greenference | $0.018 | $0.009 | $0.045 | 131K |
| OpenAI: gpt-oss-20b | kilo | $0.018 | $0.01 | $0.04 | 131K |
| OpenAI: gpt-oss-20b | trustedrouter | $0.0195 | $0.01 | $0.04748 | 131K |
| GPT OSS 20B | edenai via FlexAI | $0.04 | $0.02 | $0.10 | 131K |
| OpenAI: gpt-oss-20b (batch) | openrouter | $0.0464 | $0.024 | $0.11 | 131K |
| OpenAI: gpt-oss-20b | openrouter | $0.056 | $0.03 | $0.13 | 131K |
| GPT OSS 20B | deepinfra | $0.058 | $0.03 | $0.14 | 131K |
| GPT OSS 20B | edenai via DeepInfra | $0.058 | $0.03 | $0.14 | 131K |
| OpenAI: GPT OSS 20B | fastrouter | $0.058 | $0.03 | $0.14 | 131K |
| GPT OSS 20B | huggingface | $0.058 | $0.03 | $0.14 | 131K |
| GPT OSS 20B | vercel | $0.058 | $0.03 | $0.14 | 131K |
| GPT OSS 20B | poe | $0.05858 | $0.0303 | $0.14 | 131K |
| GPT OSS 20B | kenari | $0.06451 | $0.03474 | $0.15 | 128K |
| OpenAI: gpt-oss-20b | io-net | $0.0724 | $0.0424 | $0.15 | 64K |
| GPT OSS 20B | siliconflow | $0.076 | $0.04 | $0.18 | — |
| GPT OSS 20B | cortecs | $0.07825 | $0.04472 | $0.17 | 131K |
| gpt-oss-20b | ovhcloud | $0.086 | $0.05 | $0.18 | 131K |
| GPT OSS 20B | aiml | $0.09 | $0.05 | $0.20 | — |
| OpenAI GPT-OSS 20b | helicone | $0.09 | $0.05 | $0.20 | 131K |
| OpenAI: GPT OSS 20B | jiekou | $0.09 | $0.05 | $0.20 | 131K |
Token estimator
Don't know your workload in tokens? Paste an example of your prompt, say how many such requests you make a month and how long an answer is: you get the monthly workload. The button puts it into the picker above and shows the offers.
Price units
Providers quote per token, per 1K or per 1M tokens: the same price in all three.
AI picker
Describe the task in your own words - what the model must do, how fast, the budget, the region - and get a short list of models and providers with the reasons.
Coming soon.