Inference
EN
ByteDance

Seed 2.1 Turbo

Seed 2.1 Turbo is a reasoning model from ByteDance in the Seed 2.1 family. 9 benchmarks count toward its index, in 4 categories.

  • Closed weights
  • Reasoning
  • Input: text · image · video
  • Released 2026-06
RankedEnough results for an index.
IndexAll categories, out of 100.57.4±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.37/sMedian 67/s
First tokenSeconds to the first output token.2.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.50Median $0.60
Output / 1MUS dollars per 1M output tokens.$2.50Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
bytedance-seed/seed-2-1-turbo
Max outputMaximum output tokens per request.
236K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
Volcengine ArkMaker$0.445$2.23256K
OpenRouterRouter$0.50$2.50262K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted60.7—
CodingCode writing and repair.1 counted57.6—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.6 counted59.342 / 84
KnowledgeFacts and expert knowledge.1 counted52.4—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
ERQAMultimodal71.3%4 / 18
Massive Multi-discipline Multimodal Understanding ProMultimodal80.1%15 / 53
MathVisionMultimodal90.1%8 / 24
CharXiv ReasoningMultimodal82.5%23 / 49
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate DisciplinesKnowledge67.4%11 / 22
NL2RepoCoding43.7%20 / 36
Terminal-Bench 2.1 · BenchLMAgentic67.6%54 / 86
BabyVisionMultimodal62.9%7 / 11
ZeroBenchMultimodal11.0%10 / 10
Video-MMEMultimodal89.0%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reusemodels.devMIT

History

5 releases
Index58.8 → 57.4
23 Oct 202612 Nov 2026
Output / 1M$2.50 → $2.50
23 Oct 202612 Nov 2026

Questions

How much does Seed 2.1 Turbo cost?
$0.50 per 1M input tokens, $2.50 per 1M output tokens.
How good is Seed 2.1 Turbo?
Its index is 57.4 out of 100. That is place 90 of 283 ranked models.
What is Seed 2.1 Turbo best at?
Multimodal: 59.3 out of 100, place 42 of 84.
How fast is Seed 2.1 Turbo?
37 output tokens per second, 2.6 s to the first token.
What is the context window of Seed 2.1 Turbo?
262K tokens.
Is Seed 2.1 Turbo open source?
No. Its weights are not published.
When was Seed 2.1 Turbo released?
June 2026.

Badge

Seed 2.1 Turbo on Inference360: place 90 of 283, index 57.4
HTML
<a href="https://inference360.ai/models/seed-2-1-turbo"><img src="https://inference360.ai/badges/seed-2-1-turbo.svg" alt="Seed 2.1 Turbo on Inference360: place 90 of 283, index 57.4" height="20"></a>
Markdown
[![Seed 2.1 Turbo on Inference360: place 90 of 283, index 57.4](https://inference360.ai/badges/seed-2-1-turbo.svg)](https://inference360.ai/models/seed-2-1-turbo)

Compare with

Seed 2.1 Pro60.1dots3-note Preview63.4

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from ByteDance

All models
Seed 2.1 Pro60.1SeedRealtimeUnrankedSeed 2.0 CodeUnrankedSeed-2.0-LiteUnrankedSeed-2.0-MiniUnranked