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: DeepSeek V4.1 Flash 1017 ×

ModelProviderYour cost/mo, $Input, $Output, $Context
DeepSeek V4.1 Flash 1017trustedrouter$0.05697$0.03165$0.13—
DeepSeek V4.1 Flash 1017deepinfra$0.16$0.098$0.29—
DeepSeek: DeepSeek V4.1 Flash 1017fastrouter$0.16$0.098$0.291M
DeepSeek V4.1 Flash 1017requesty via DeepInfra$0.16$0.098$0.291M
DeepSeek-V4.1-Flash-1017meganova$0.16$0.10$0.301M
DeepSeek V4.1 Flash 1017edenai via Alibaba Cloud$0.18$0.0975$0.391M
DeepSeek V4.1 Flash 1017wafer.ai$0.23$0.13$0.501M
DeepSeek V4.1 Flash 1017iteracompute$0.25$0.14$0.55—
DeepSeek V4.1 Flash 1017edenai via Tencent Cloud$0.27$0.15$0.601M
DeepSeek V4.1 Flash 1017inferx$0.27$0.15$0.60—
DeepSeek V4.1 Flash 1017ollama-cloud$0.27$0.15$0.60—
DeepSeek: DeepSeek V4.1 Flash 1017openrouter$0.27$0.15$0.601M
DeepSeek V4.1 Flash 1017runinfra$0.27$0.15$0.60—
DeepSeek V4.1 Flash 1017umans-ai-coding-plan$0.27$0.15$0.601M
DeepSeek V4.1 Flash 1017aihubmix$0.28$0.15$0.621M
DeepSeek V4.1 Flash 1017deepinfra$0.32$0.20$0.601M
DeepSeek V4.1 Flash 1017edenai via DeepInfra$0.32$0.20$0.601M
DeepSeek V4.1 Flash 1017cortecs$0.33$0.20$0.611M
Deepseek V4.1 Flashabacus$0.35$0.22$0.661M
DeepSeek V4.1 Flash 1017aki-io$0.50$0.28$1.12—

All 45 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.