Providers / qwen/qwen3-235b-a22b-2507
qwen/qwen3-235b-a22b-2507 as each provider declares it
3 of the 7 endpoints declare at least one material setting that differs from the official reference. Declared values, not measured behaviour.
Reference. Context 262,144 tokens, from Qwen/Qwen3-235B-A22B-Instruct-2507 config.json at ac9c66cc9b (max_position_embeddings). Quantization: bf16, plus an official FP8 release (Qwen/Qwen3-235B-A22B-Instruct-2507-FP8).
Provider rows: OpenRouter providers page, the endpoint JSON. Read 2026-10-19.
Endpoints
| Provider | Quantization | Context | Max output | Tools / reasoning | Differs from the reference |
|---|---|---|---|---|---|
| DeepInfra deepinfra/fp8 | fp8 (official) | 262,144 | 16,384 | yes / n/a | none declared |
| GMICloud gmicloud/fp8 | fp8 (official) | 262,144 | 235,929 | yes / n/a | none declared |
| Google google-vertex/us-south1 | none (not declared) | 262,144 | 16,384 | yes / n/a | none declared |
| Google google-vertex/us-south1 | none (not declared) | 262,144 | 16,384 | no / n/a | declares no tools parameter; the official model supports tool calling |
| Nebius nebius/fp8 | fp8 (official) | 262,144 | 235,929 | yes / n/a | none declared |
| Parasail parasail/fp8 | fp8 (official) | 131,072 | 117,964 | yes / n/a | declares a 131,072-token context; the reference config says 262,144 (50%) |
| Venice venice/fp8 | fp8 (official) | 128,000 | 16,384 | yes / n/a | declares a 128,000-token context; the reference config says 262,144 (49%) |
Changes since tracking began
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.