Price per million input and output tokens of 300+ language models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek...) via OpenRouter, with context window and the est…
Repair broken JSON, typical of LLM output: strips ```json fences, comments and surrounding text, trailing commas, single quotes, unquoted keys, Python True/None and uncl…
Price per million input and output tokens of 300+ language models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek...) via OpenRouter, with context window and the est…
Read any public web page or PDF and get its main content as clean, LLM-ready markdown (headings, lists, links, tables, code) plus metadata: title, description, author, d…
Vision Pro "View Stream" does nothing? Check whether the headset is Jamf (MDM) managed. Apple Immersive Video Utility shows "View Stream" but selecting it does nothing,…
Check Python packages from PyPI before you pip install or bump versions. Send {"packages":["requests==2.25.0","flask>=2.0"]} or {"requirements":"<requirements.txt text>"…
o4-mini: OpenAI o4 Mini chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.55/2.2, Standard 1.1/4.4, Fast 2.0/8.0; pick with service_tier. P…
o3: OpenAI o3 chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 1.0/4.0, Standard 2.0/8.0, Fast 3.5/14.0; pick with service_tier. Plus $0.000…
o3-mini: OpenAI o3 Mini chat completions, paid per call in USDC. Per 1M tokens in/out: Standard (default) 1.1/4.4; pick with service_tier. Plus $0.0005 (Base) or $0.0005…
OpenAI's newest model. gpt-6.1-sol: OpenAI GPT 6.1 Sol (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 1.0/5.0, Stand…
gpt-6.1-sol-long: OpenAI GPT 6.1 Sol (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.0/7.5, Standard 4.0/15.0, Fast…
gpt-6-sol: OpenAI GPT 6 Sol (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 1.0/5.0, Standard 2.0/10.0, Fast 4.0/20.0…
gpt-6-sol-long: OpenAI GPT 6 Sol (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.0/7.5, Standard 4.0/15.0, Fast 8.0/…
gpt-6-luna: OpenAI GPT 6 Luna (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.05/0.25, Standard 0.1/0.5, Fast 0.2/1…
gpt-6-luna-long: OpenAI GPT 6 Luna (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.1/0.375, Standard 0.2/0.75, Fast…
gpt-6-astra: OpenAI GPT 6 Astra (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 5.0/25.0, Standard 10.0/50.0, Fast 20…
gpt-5: OpenAI GPT 5 chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.625/5.0, Standard 1.25/10.0, Fast 2.5/20.0; pick with service_tier. P…
gpt-5.6-terra: OpenAI GPT 5.6 Terra (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 1.0/6.0, Standard 2.0/12.0, Fast…
gpt-5.6-terra-long: OpenAI GPT 5.6 Terra (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.0/9.0, Standard 4.0/18.0, F…
gpt-5.6-sol: OpenAI GPT 5.6 Sol (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.0/10.0, Standard 4.0/20.0, Fast 8.0…
gpt-5.6-sol-long: OpenAI GPT 5.6 Sol (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 4.0/15.0, Standard 8.0/30.0, Fast…
gpt-5.6-luna: OpenAI GPT 5.6 Luna (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.1/0.6, Standard 0.2/1.2, Fast 0.4…
gpt-5.6-luna-long: OpenAI GPT 5.6 Luna (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.2/0.9, Standard 0.4/1.8, Fast…
gpt-5.5: OpenAI GPT 5.5 (<=272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.5/15.0, Standard 5.0/30.0, Fast 12.5/75.0;…
