Tool callingStructured outputReasoningImage input

ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows

Context
256K
Released
9mo ago

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Model family
Seed
Type
Language model
Predecessor
—
Successor
—
Released
December 28, 2025
Model ID
bytedance-seed/seed-1-8
Openness
Closed
License
—
Input modalities
text, image
Output modalities
text
Modality
text+image->text
Max output tokens
64K
Hugging Face
—
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
bytedance-seed/seed-1-8
Source family
seed
Last updated
2025-12-28
Model context
256K
Model output limit
64K
Open weights
No
File attachments
Yes
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Temperature control
Yes
Complete source record (JSON)
{
  "id": "bytedance-seed/seed-1-8",
  "name": "Seed 1.8",
  "description": "ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows",
  "family": "seed",
  "last_updated": "2025-12-28",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 256000,
    "output": 64000
  },
  "release_date": "2025-12-28",
  "open_weights": false
}

Infrastructure

Provider availability

All providers
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.