Deepseek Prover V1.5 RL
DeepSeek develops Deepseek Prover V 1.5 RL, an open-source language model optimized for theorem proving in Lean 4. It is genuinely best at formal mathematical languages, achieving state-of-the-art results on the miniF2F and ProofNet benchmarks, with a top score of 63.5% on the miniF2F-test set. Notably, the model employs a variant of Monte-Carlo tree search called RMaxTS, which utilizes an intrinsic-reward-driven exploration strategy to generate diverse proof paths, and has 7B parameters.
Input
Output
Context
4K
Max Output
2K
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Resources & Links
More models by DeepSeek
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Deepseek Prover V1.5 RL
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Deepseek Prover V1.5 RL advertises a context window of 4,096 tokens, with a maximum output of 2,048 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. Deepseek Prover V1.5 RL is an open-weight model released under the Other license, so the weights can be downloaded and self-hosted within that license's terms.
Deepseek Prover V1.5 RL accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Deepseek Prover V1.5 RL is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Deepseek Prover V1.5 RL is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
DeepSeek has not published a parameter count for Deepseek Prover V1.5 RL, so the catalog cannot estimate its memory footprint. The capacity planner can size it from a parameter count you supply.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Aug 28, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.