Changes / Providers
The same model id is not the same configuration at every provider.
24 of the 82 provider endpoints serving 6 open-weight models declare at least one material setting that differs from the official reference (29.3%); 26 of the 71 whose quantization could be compared declare none, so it cannot be checked. Each row below is what a provider declares for one open-weight model, next to the official reference.
By kind (an endpoint can count in several): 17 context, 5 quantization, 16 tools, 0 reasoning, 5 output-cap. First read 2026-10-19, last read 2026-10-19.
| Model | Endpoints | Material difference | Quantization not declared | Reference context |
|---|---|---|---|---|
| openai/gpt-oss-120b | 24 | 6 | 9 | 131,072 |
| openai/gpt-oss-20b | 11 | 2 | 4 | 131,072 |
| moonshotai/kimi-k2.6 | 17 | 3 | 4 | 262,144 |
| qwen/qwen3-235b-a22b-2507 | 7 | 3 | 2 | 262,144 |
| deepseek/deepseek-v3.2 | 12 | 5 | 7 | 163,840 |
| meta-llama/llama-3.3-70b-instruct | 11 | 5 | not compared | 131,072 |
Recent changes
None yet. A row is recorded only when a declared value or the reference moves.
How this is read
Once a day the tracker reads OpenRouter's public endpoint list for each model (one row per provider deployment: declared context length, declared maximum output, declared quantization, and the request parameters it accepts) and the official repository's config.json at its head commit. Both reads are anonymous. A new row is recorded only when either moved, so the history below is a list of real changes.
Every value in the tables is what a provider declares to OpenRouter. No request is sent to any model, so nothing here says how an endpoint behaves: one that declares a 131,072-token context may still cut off earlier, and one that declares the official quantization may still serve something else.
A quantization the provider does not declare cannot be compared, and is counted as undisclosed rather than as matching. A quantization of higher precision than the official weights is shown and not counted as a difference.
Material means one of: a declared context under 95% of the reference config, a declared quantization other than the official release, no tools parameter on a model that supports tool calling, no reasoning control on a model that exposes one, or a reasoning model capped under 8,192 output tokens. A context between 95% and 100% of the reference is listed and not counted as material.
Sampling defaults, chat templates and stop tokens are not in the endpoint metadata and are not compared here. Moonshot's K2 Vendor Verifier (github.com/MoonshotAI/K2-Vendor-Verifier) measures tool-call behaviour across providers for Kimi K2 by sending requests; this page does not.
OpenRouter lists only the providers that serve through it. Nothing here ranks providers, and a provider with no listed difference has not been shown to match the reference, only to declare nothing that differs.