This catalogue entry is an alias: a name that points at another model rather than a model of its own. Its serving contract is listed below; the identity evidence lives on the record of the model it serves.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Not measured yet | we measured it |
| How its API is set up | Set up identically to 1 other listing, field for field | api_e653bdf4 |
| How much it can read and write | Reads up to 1,048,576 tokens at onceOpenRouter's listing shows 943,718 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. DeepSeek's own API reference caps max_tokens at 384K, 393,216 tokens, for deepseek-flash and deepseek-v4-pro. | its own listing |
| Whether it thinks before answering | Reasons when asked to, at max, high, low, high by default | its own listing |
This model always redirects to the latest model in the DeepSeek V4 Flash family.
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
defaults: {}
