AI Rate Card

Tools: 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: Qwen3 235B-A22B Instruct 2507 ×

ModelProviderYour cost/mo, $Input, $Output, $Context
Qwen3 235B-A22B Instruct 2507requesty via DeepInfra$0.091$0.071$0.10262K
Qwen3-235B-A22B-Instruct-2507meganova$0.11$0.09$0.10262K
Qwen3 235B-A22B Instruct 2507edenai via TensorX$0.16$0.072$0.46131K
Qwen3 235B-A22B-2507tensorx$0.16$0.072$0.46131K
Qwen3 235B-A22B Instruct 2507deepinfra$0.20$0.09$0.55262K
Qwen3 235B-A22B Instruct 2507edenai via DeepInfra$0.20$0.09$0.55262K
Qwen: Qwen3 235B A22B Instruct 2507fastrouter$0.20$0.09$0.55262K
Qwen3 235B-A22B Instruct 2507huggingface$0.20$0.09$0.55262K
Qwen/Qwen3-235B-A22B-Instruct-2507trustedrouter$0.21$0.09495$0.58262K
Qwen: Qwen3 235B A22B Instruct 2507kilo$0.30$0.14$0.80262K
Qwen: Qwen3 235B A22B Instruct 2507openrouter$0.30$0.14$0.80262K
Qwen3 235B-A22B Instruct 2507jiekou$0.31$0.15$0.80—
Qwen3 235B-A22B Instruct 2507edenai via Nebius$0.32$0.20$0.60262K
Qwen3 235B A22B Instruct 2507nebius$0.32$0.20$0.60262K
Qwen3 235B A22B Instruct 2507 FP8togetherai$0.32$0.20$0.60262K
Qwen3 235B-A22B Instruct 2507cortecs$0.32$0.20$0.60262K
Qwen3 235B-A22B Instruct 2507amazon-bedrock$0.40$0.22$0.88—
Qwen3 235B-A22B Instruct 2507google-vertex$0.40$0.22$0.88—
Qwen3 235B-A22B Instruct 2507edenai via Arkanecloud$0.45$0.25$1.00262K
Qwen3 235B A22B Instruct 2507aihubmix$0.50$0.28$1.12262K

All 25 in Models

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.