Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most AI engineers + agent developers + IDE / chat tool builders have been either (a) hard-coding model metadata (cost / limits / capabilities) per provider in their own config files (high maintenance burden, drifts when providers change pricing or context windows), (b) relying on a single-vendor model registry (OpenRouter, Helicone, Portkey) that locks-in the deployment model and charges per-reque
Who should use it
Who should skip it
Pass on Models.dev: MIT Open-Source Database of AI Model Specs, Pricing, and Capabilities (5,781*, Powers OpenCode + AI SDK) if its scope or audience does not match what your team is building right now.
About this signal
Models.dev: MIT Open-Source Database of AI Model Specs, Pricing, and Capabilities (5,781*, Powers OpenCode + AI SDK) is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-08 and last updated on AUTOFILL_NOW. The current verdict is 'try now' with a Gold tier and easy setup difficulty. The standout signals for Models.dev: MIT Open-Source Database of AI Model Specs, Pricing, and Capabilities (5,781*, Powers OpenCode + AI SDK) are workflow potential (9.3) and practical usefulness (9.0), while maturity (6.7) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned Models.dev: MIT Open-Source Database of AI Model Specs, Pricing, and Capabilities (5,781*, Powers OpenCode + AI SDK) a composite score of 8.6 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 0.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.
Risk explanation
The 5; 781* repo is at active maintenance but the consumer SHOULD note the model specs (cost / context window / modalities) are community-contributed and may drift; the consumer SHOULD verify the live API at https://models.dev/api.json against the vendor's official pricing page before adopting a model for production; the consumer SHOULD note the default branch is `dev`.