Every model, one price list. 81 models from 14 developers. Per million tokens, in US dollars.
GET https://api.uplinkswitch.com/v1/catalog returns this list as JSON, no key needed.
Images, video, speech and 3D are priced per image, second or generation: see the media models.
Pricing by family: Claude · GPT · Gemini · Grok · DeepSeek · Kimi · GLM · Qwen · MiniMax · MiMo
Model comparisons · LLM API price index · Uncensored LLM API · OpenRouter alternative
What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
Model
Input / M
Cached / M
Output / M
Call it with
Anthropic · 12
OpenAI · 13
Google · 12
Gemini 3.5 Flashgemini-3.5-flash · also gemini-3.5-flash-extra-low, gemini-3.5-flash-high, gemini-3.5-flash-low
$0.90
$5.40
xAI · 5
DeepSeek · 8
Moonshot AI · 4
Qwen · 3
Z.ai · 8
MiniMax · 4
Meta · 2
Tencent · 2
NVIDIA · 3
Xiaomi · 4
Independent · 1
Up to 95% under list. Volume pricing: contact us.
Once all customers together pass 100M tokens on a model in a month, everyone gets a 3% co-op discount on it. 6% past 1B, 10% past 10B.