Doubao Seed 2.0 Pro
LLM Provider / Model · Cost-effective frontier coding, Codeforces-level competitive programming (3020 rating), AIME math (98.3%), production agentic workflows
At a glance
| Input price | $0.47 |
| Output price | $2.37 |
| Cache price | $0.05 |
| Price tier | Budget |
| Context window | 256K |
| Max output | 32K |
| Context tier | 128K-500K |
| Speed tier | Standard |
| Latency | medium |
| Knowledge cutoff | Nov 2025 |
| Modality | Multimodal (vision) |
| Model ID | doubao-seed-2.0-pro |
| Provider | ByteDance |
| HumanEval | 93% |
| MMLU | 88% |
| SWE-Bench | 77% |
| Benchmark | SWE-bench Verified: high |
| Released | Feb 2026 |
| Hosting | Closed/API |
| Capabilities | Vision, Tool use, Streaming, Structured output, Function calling, Agentic coding, Multilingual |
What Doubao Seed 2.0 Pro does
Vision, Tool use, Streaming, Structured output, Function calling, Agentic coding, Multilingual
Best for
Cost-effective frontier coding, Codeforces-level competitive programming (3020 rating), AIME math (98.3%), production agentic workflows
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include Doubao Seed 2.0 Pro — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Doubao Seed 2.0 Pro is not in the supported model list.
- Kiro's spec mode is tuned for Claude models — Doubao Seed 2.0 Pro may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include Doubao Seed 2.0 Pro — verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Doubao Seed 2.0 Pro is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models — your LLM is Doubao Seed 2.0 Pro.
- Claude Code only works with Claude models — your LLM is Doubao Seed 2.0 Pro.
- Devin uses Cognition's proprietary model internally — your selected Doubao Seed 2.0 Pro will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Doubao Seed 2.0 Pro will be ignored.
- Jules runs Gemini models internally — your selected Doubao Seed 2.0 Pro will be ignored.
- The Claude Code SDK is tuned for Claude models — Doubao Seed 2.0 Pro may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model — your selected Doubao Seed 2.0 Pro will be ignored.
- Replit Agent 3 uses its own model selection internally — your selected Doubao Seed 2.0 Pro will be ignored.
Build a full stack around Doubao Seed 2.0 Pro — Flowpicker shows compatibility warnings before you commit.
Open the stack planner →