Last refreshed 2026-06-29. Next refresh: weekly.
Why use DeepSeek Prover V2 on Novita AI?
Novita AI offers DeepSeek Prover V2 with pay-as-you-go pricing at $0.70/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Compare DeepSeek Prover V2 across 2 providers to find the best fit for your use caseInput / 1M
$0.70
Output / 1M
$2.50
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: deepseek-prover-v2-671bModel ID
deepseek-prover-v2-671bRequest example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "deepseek-prover-v2-671b", not the LLMReference slug "deepseek-prover-v2".
Compare DeepSeek Prover V2 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.56 | $1.68 |
| Novita AI | $0.70 | $2.50 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.70 |
| Output tokens | $2.50 |
Capabilities
Reasoning
About DeepSeek Prover V2
DeepSeek Prover V2 is DeepSeek's DeepSeek Prover model focused on step-by-step reasoning. It offers a 160K-token context window with weights openly available for self-hosting.
Get Started
Model Specs
Released2025-04-30
Parameters671B
Context160k
ArchitectureDecoder Only