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 120B ×
| Model | Provider | Your cost/mo, $ | Input, $ | Output, $ | Context |
|---|---|---|---|---|---|
| OpenAI: gpt-oss-120b | kilo | $0.0466 | $0.027 | $0.098 | 131K |
| OpenAI: gpt-oss-120b (batch) | openrouter | $0.0568 | $0.0296 | $0.14 | 131K |
| GPT OSS 120B | requesty via Runware | $0.06 | $0.032 | $0.14 | 131K |
| GPT OSS 120B | orcarouter | $0.064 | $0.03 | $0.17 | 131K |
| OpenAI: gpt-oss-120b | trustedrouter | $0.06752 | $0.03165 | $0.18 | 131K |
| GPT-OSS 120B | abacus | $0.071 | $0.037 | $0.17 | 128K |
| GPT OSS 120B | deepinfra | $0.071 | $0.037 | $0.17 | 131K |
| GPT OSS 120B | edenai via DeepInfra | $0.071 | $0.037 | $0.17 | 131K |
| OpenAI: GPT OSS 120B | fastrouter | $0.071 | $0.037 | $0.17 | 131K |
| GPT OSS 120B | huggingface | $0.071 | $0.037 | $0.17 | 131K |
| OpenAI GPT-OSS 120b | helicone | $0.072 | $0.04 | $0.16 | 131K |
| GPT OSS 120B | kenari | $0.07333 | $0.03474 | $0.19 | 128K |
| GPT OSS 120B | edenai via FlexAI | $0.10 | $0.05 | $0.25 | 131K |
| GPT OSS 120B | novita | $0.10 | $0.05 | $0.25 | 131K |
| GPT-OSS-120B | synthetic | $0.12 | $0.10 | $0.10 | 131K |
| GPT OSS 120B | siliconflow | $0.14 | $0.05 | $0.45 | — |
| GPT OSS 120B | google-vertex | $0.16 | $0.09 | $0.36 | — |
| GPT OSS 120B | cortecs | $0.18 | $0.08943 | $0.45 | 131K |
| GPT OSS 120B | edenai via OVHcloud | $0.18 | $0.09 | $0.47 | 131K |
| gpt-oss-120b | ovhcloud | $0.18 | $0.09 | $0.47 | 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.