Open MoE flagship with million-token context for coding and long agent runs
https://api.ollama.com deepseek-v4-pro | Benchmark | Score | Metric | Date |
|---|---|---|---|
| SWE-Bench Verified | 80.6 | resolved | Not listed |
| Artificial Analysis Coding Agent Index | 50.1 | average pass@1 | Not listed |
| SWE-Atlas Codebase QnA | 67.8 | pass@1 | Not listed |
| SWE-Bench Pro | 18 | pass@1 | Not listed |
deepseek-v4-pro is listed for chat workloads and supports a 128K context window.
Use the comparison and availability sections before choosing this listing, because it is not currently marked as free.
We found 2 provider listings for deepseek-v4-pro. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | deepseek-v4-pro | Paid | 128K | OpenAI-style | Session/weekly limits (unpublished) |
| | deepseek-ai/DeepSeek-V4-Pro | Free tier | 8K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| deepseek-ai/DeepSeek-V4-Pro | ModelScope | 8K | Free tier |
| minimax-m3 | Ollama Cloud | 1.0M | Free tier |
| gpt-oss:20b | Ollama Cloud | 131K | Free tier |
| nemotron-3-ultra | Ollama Cloud | 262K | Free tier |
| gpt-oss:120b-cloud | Ollama Cloud | 128K | Check provider |
deepseek-v4-pro is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
deepseek-v4-pro is not currently marked as free on Ollama Cloud.
The model ID shown in this catalog is deepseek-v4-pro.
The listed free tier limit is Session/weekly limits (unpublished). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 131K output tokens.
Flagship DeepSeek model for coding, reasoning, and agentic work
For API keys, setup steps, and provider-level limits, see the Ollama Cloud provider page.