Skip to main content

ByteDanceLanguage modelDeprecated

Seed 1.6

Seed 1.6 has no overall index value yet because there are too few independent benchmark results.

Intelligencenot ranked yet

n/aOverall indexhigher is better

Speednot measured

n/ano measurement yet

PriceRank 31 of 95

Input $0.25 · Output $2

$0.69per 1M tokenslower is better

ContextRank 76 of 102

256Ktokens at once≈ 380 A4 pages

PopularityRank 629 of 875

13out of 100same as last month

Summary

It is fairly cheap: $0.69 per 1M tokens (input and output blended); a typical model costs $1.56.

Seed 1.6 is ByteDance’s multimodal deep-thinking model with 230B total parameters, 23B active parameters, and 256K tokens of context. Its technical description highlights adaptive thinking time, AdaCoT, and GUI-agent use. The model can therefore vary the amount of internal planning between a direct answer and a more involved task.

Seed 1.6 is proprietary and API-only. Images and video are supported on the input side, while output remains text. There is no released checkpoint for local experiments, so the documented access path is BytePlus or the Volcano interface.

See for yourself: one prompt, one attempt

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Seed 1.6

Seed 1.6: SVG short test

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Oct 14, 2026 · $0.0011

Test details
Test run
Oct 14, 2026
Provider
seed/fp8
API model
bytedance-seed/seed-1.6
Output
525 tokens
Reasoning
API reports 0 reasoning tokens
Cost of the attempt
$0.0011
Test round
43b8c5c46830
Earlier tests
Seed 1.6: Pelican on a bicycle
A community classic for free-form SVG drawing.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Oct 1, 2026 · 68 s · $0.0066

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
bytedance-seed/seed-1.6
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,288 tokens
Cost of the attempt
$0.0066
Response time
67.6 s
API model reported in response
bytedance-seed/seed-1.6
Pinned endpoint
Seed | bytedance-seed/seed-1.6-20250625
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Task origin: Simon Willison

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 10 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AEGIS FSD accuracy (Show measurement, test conditions, and source)
Source value
41.31
Score
41.31
Metric
single-choice classification accuracy (ACC)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS FSD macro-F1 (Show measurement, test conditions, and source)
Source value
35.38
Score
35.38
Metric
class-balanced macro-F1 (M-F1)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS TAR accuracy (Show measurement, test conditions, and source)
Source value
77.23
Score
77.23
Metric
single-choice classification accuracy (ACC)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS TAR macro-F1 (Show measurement, test conditions, and source)
Source value
76.9
Score
76.9
Metric
class-balanced macro-F1 (M-F1)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS MC accuracy (Show measurement, test conditions, and source)
Source value
50.05
Score
50.05
Metric
single-choice classification accuracy (ACC)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS MC macro-F1 (Show measurement, test conditions, and source)
Source value
37.08
Score
37.08
Metric
class-balanced macro-F1 (M-F1)
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics task result, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS TP region-level Correct Localization Accuracy (Show measurement, test conditions, and source)
Source value
36.38
Score
36.38
Metric
sample-level region localization accuracy (CLA); coverage threshold τ=0.5
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. CLA requires at least 50% coverage of every ground-truth region. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics localization metric, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS TP Over Localization Rate (Show measurement, test conditions, and source)
Source value
0.28
Score
0.28
Metric
percentage of samples with over-localized regions (OLR); lower is better
Unit
%
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers
Category
multimodal
Direction
Lower is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS evaluated image forensics on high-resolution PNGs with minimal task-specific prompts. OLR counts cases meeting the paper's over-localization condition; lower is better. Serving mode, immutable revision, and request date are not reported. Per-task denominators, temperature, and other decoding settings are unavailable. The 8,210-sample dataset total is not treated as this metric's N.
Context
This is an AEGIS academic-image-forensics over-localization rate, where lower is better, not a general model-quality score. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
AEGIS Normalized Forensic Index (Show measurement, test conditions, and source)
Source value
41.73
Score
41.73
Metric
paper-defined 0-100 composite of FSD-F1, TAR-F1, MC-F1, CLA, with OLR penalty
Unit
points
Benchmark version
AEGIS Table 2; ACL 2026 Long Papers; default OLR exponent γ=0.5
Category
multimodal
Direction
Higher is better
Source type
independent-evaluator
Evaluator
AEGIS, ACL 2026, Table 2
Status
active
Retrieved at
2026-10-16
Methodology
Independent evaluation. Exact Table 2 model label Doubao-Seed-1.6, distinct from the Doubao-Seed-1.6-thinking row. Mapped only at the unversioned name/API-alias level to profile seed-1-6. Appendix B.1 names the Volcano Engine API; Appendix B.2 links the exact official route https://console.volcengine.com/ark/model/detail?Id=doubao-seed-1-6. AEGIS NFI is a paper-defined 0-100 composite: the harmonic mean of FSD-F1, TAR-F1, MC-F1, and CLA, multiplied by an over-localization penalty (1-OLR)^γ with default γ=0.5. The paper says higher NFI indicates stronger balanced performance on its image-forensics tasks. This composite is not a general model-quality index. The paper does not identify serving mode, immutable revision, or evaluation request date. Per-task denominators are not published; the 8,210-sample dataset total is not treated as this metric's N.
Context
This is the authors' AEGIS-specific composite, not a broad model-quality score or an index comparable across unrelated benchmarks. The paper names the Seed 1.6 API route but does not disclose serving mode, request date, or immutable backend revision. It is not attributed to the separate Thinking or Adaptive CoT rows, or to the dated seed-1-6-250915 API revision.
Source AEGIS, ACL 2026, Table 2
The Aggregate ByteDance rating, Seed-1.6 (Show measurement, test conditions, and source)
Source value
1673
Score
1673
Metric
The Aggregate model-level composite rating
Unit
rating
Benchmark version
The Aggregate ByteDance company table, snapshot 2026-10-19
Category
model-level composite rating
Direction
Higher is better
Source type
independent-evaluator
Evaluator
The Aggregate, ByteDance company rating table
Status
active
Retrieved at
2026-10-24
Methodology
Independent evaluation. The Aggregate's independent ByteDance company table lists the exact model as API-accessible and reports a model-level composite rating. The evaluator's separately documented methodology describes a composite of public leaderboard and benchmark-report observations using hierarchical continuous-response IRT, with an Elo-like scale centered around 1500. The captured page is the 2026-10-19 daily snapshot; this is a point in an existing rating series, not a new experiment.
Context
The source displays ±7 beside the rating, but the retained current-page excerpt does not define that term. It is not encoded as a 95% confidence interval. No task sample N is stated in the captured table.
Source The Aggregate, ByteDance company rating table

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

Gemini 4 Argon92
GPT-6 Astra78
Claude Haiku 5.577
Qwen3.5 4B76
GPT-573
GPT-6 Sol72
Qwen3.5 0.8B72
Qwen3.5 2B71
Qwen 3.8 27B70
Claude Opus 5.570
DeepSeek V4.1 Flash 101768
Qwen 3.8 Max 090268
Kimi K368
DeepSeek-V4-Flash65
GPT-5.6 Terra64
Claude Sonnet 563
DiffusionGemma 26B A4B IT63
Claude Opus 562
Qwen 3.8 Flash62
Seed 1.613

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 5, 2026

Seed 1.6Sonar Reasoning ProMiniMax-M2.5-highspeedSeed 2.0 MiniGPT-6.1 Terra

All specifications

Architecture

Parameters
230B
Source: Parameters
Active parameters
23B
Source: Active parameters

Input and output

Context window
256,000 tokens
Source: Context window
Reasoning mode
Deep thinking can be disabled with the thinking parameter. The documentation names seed-1-6-250915 and seed-1-6-250615. (retrieved 2026-09-22)
Source: Reasoning mode

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Weights
Proprietary
Source: Weights
Access
API
Source: Access
Release
Jun 15, 2025
Source: Release
License
proprietary BytePlus terms
Source: License

API

API model ID
seed-1-6-250915
Source: API model ID

Further details

Notes
Multimodal deep-thinking model with a 256K context window; 230B total parameters, 23B active (MoE).
Source: Notes

Prices

Shutdown announced for November 11, 2026. Rates last verified on September 19, 2026.

Choose a price view

1 offer, prices in US dollars per 1M tokens, blended from 3 parts input and 1 part output.

ProviderInputOutputCache readBlended
ByteDancedirect$0.25$2$0.05$0.69
ByteDanceabove 128,000 context tokensdirect$0.50$4n/a$1.38

Cache prices come from the direct tariff; OpenRouter does not report them for the other providers. Direct price according to the developer, checked Sep 19, 2026. Open the LLM price index

Unchanged since tracking began on Aug 24, 2026.

InputOutput

$0$1$2$3Aug 24, 2026Oct 19, 2026
Daily observed price in the LLM price index in US dollars per 1M tokens. The index uses a market price from several sources, which can differ from the developer's direct price.

Not included in any subscription in Germany.

All plans in the AI subscription comparison

Frequently asked questions about Seed 1.6

How much does Seed 1.6 cost?

Through the API $0.25 per 1M input tokens and $2 output. That is fairly cheap.

Prices from Oct 19, 2026

Output price since tracking beganDollars per 1M tokens · lower is better

Aug 24, 2026Oct 19, 2026

Unchanged since tracking began on Aug 24, 2026.

How large is the context window of Seed 1.6?

256,000 tokens. That is how much text Seed 1.6 reads at once, about 380 A4 pages.

Page count as a rule of thumb from Artificial Analysis

Context windowTokens the model reads at once · higher is better
Kimi K2.6262K
Qwen 3.8 27B262K
Kimi K2.7 Code262K
Kimi K2.5262K
Kimi K2 Thinking262K
Mistral Medium 3.5262K
Seed 1.6Rank 76 of 102256K

Can I run Seed 1.6 locally?

No. ByteDance does not publish the weights.

Stated by ByteDance

Open weights
no
License
proprietary BytePlus terms
Parameters
230B
active per token
23B

Where can I use Seed 1.6?

Through the API. Subscription access is not documented in the available plan data.

Through the API

$0.25 input, $2 output per 1M tokens, unchanged since Aug 24, 2026.

Sources and data date

Show all 14 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Price

Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.

Source: Pricing · API pricing (retrieved October 26, 2026)
Input

Documented modalities. Retrieved October 26, 2026.

Source: Model documentation · Input (Model documentation)
Output

Documented modalities. Retrieved October 26, 2026.

Source: Model documentation · Input (Model documentation)
Research statusResearch date September 8, 2026. 8 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources

parameters-billions

Original wording

No exact value located in the checked primary model card/API documentation.

Not found in the inspected sources

active-parameters-billions

Original wording

No exact value located in the checked primary model card/API documentation.

Not found in the inspected sources

knowledge-cutoff

Original wording

No exact value located in the checked primary model card/API documentation.

Unresolved

official-variant-table-attribution

Note

AEGIS reports a separate Doubao-Seed-1.6 table row and links it to the official Volcano Engine route doubao-seed-1-6. The new values are therefore attributed to profile seed-1-6 only at this unversioned name/API-alias level. Other official benchmark tables that explicitly identify Base, Thinking, or Adaptive CoT remain unmapped to this profile. AEGIS does not publish the serving mode, request date, or immutable backend revision. The measurement is therefore not established as a result for API revision seed-1-6-250915 or any specific Base, Thinking, or Adaptive CoT variant.

Unresolved

AA benchmark rows

Original wording

No exact Artificial Analysis model page located in the checked public sitemap.

Unresolved

serving-snapshot

Note

The paper names Doubao-Seed-1.6, says the Doubao models were accessed through Volcano Engine API, and links the exact official plain-model route. It does not report serving mode, evaluation request date, or immutable serving revision. The alias-level result is attached only to profile seed-1-6; it is not transferred to distinct Thinking or Adaptive CoT variants or identified as dated API revision seed-1-6-250915.

Not published

evaluation-denominator

Note

The paper gives 8,210 as the total curated AEGIS dataset size but does not publish the per-task valid/evaluated sample count for the plain Seed 1.6 rows. No per-row sample count or confidence interval is assigned.

Additional sourceModel metadata · ByteDance Seed 1.6 technical overview · Editorial description reviewed October 2, 2026
Additional sourceContext window data (retrieved September 22, 2026) · BytePlus Seed 1.6 documentation · Editorial description reviewed October 2, 2026
Additional sourceAEGIS, ACL 2026, Table 2 (retrieved October 16, 2026)
Additional sourceThe Aggregate, ByteDance company rating table (retrieved October 24, 2026)
Additional sourceModel metadata (retrieved September 8, 2026)
Additional sourceByteDance Seed 1.6 model page · Editorial description reviewed October 2, 2026
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0