Status: [LIVE] Endpoints found: https://api-llm-specs.axium-lab.com/v1/models?provider=anthropic&mode=chat https://api-llm-specs.axium-lab.com/v1/models/claude-sonnet-4-5 https://api-llm-specs.axium-lab.com/v1/models?provider=anthropic&mode=chat&sort=input_cost_per_token:desc&fields=id,input_cost_per_token,output_cost_per_token,max_input_tokens&limit=3 Source: https://github.com/axium-lab/llm-specs-api
# llm-specs-api [](https://github.com/axium-lab/llm-specs-api/actions/workflows/ci.yml) [](https://github.com/axium-lab/llm-specs-api/releases) [](https://github.com/axium-lab/llm-specs-api/pkgs/container/llm-specs-api) [](LICENSE) **Every LLM's price, context window and capabilities behind one REST API — and a cost estimator that shows its work.** Picking a model means checking four things at once: what it costs, how much context it takes, what it can do, and whether it is about to be deprecated. That lives in a 1.7 MB JSON file you have to parse yourself. This service reads it once at boot and serves **3,000+ models from 100+ providers** out of memory, with no database — filtered, sorted, compared — and prices a single call down to the exact rate key it used. ```bash curl https://api-llm-specs.axium-lab.com/v1/models/claude-sonnet-4-5 ``` Ask for a model and you get everything the catalog knows about it — every rate, including the ones that only apply past a threshold or to a cache write, plus the context window and the capability flags: ```jsonc { // 29 attributes in total, trimmed here "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_ab