ByteDance / Seed

Seed 2.0 Lite (260228)

Seed 2.0 Lite language-model revision 260228, with documented reasoning and tool calling through ModelArk.

Language models (LLMs)

deprecatedClosed weightsText generation

Official documentation (opens in a new tab)Reviewed 15 Oct 2026
13 of 19 specification fields collected

Input token limit224KSee specification notes below

Maximum output128KSee specification notes below

Input / 1M tokens$0.25BytePlus ModelArk

Output / 1M tokens$2.00USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit: 256KSource for Context / input limit (opens in a new tab)
Maximum output: 128KSource for Maximum output (opens in a new tab)
Input modalities: Text, Image, VideoSource for Input modalities (opens in a new tab)
Output modalities: TextSource for Output modalities (opens in a new tab)
Reasoning: SupportedSource for Reasoning (opens in a new tab)
Tool calling: SupportedSource for Tool calling (opens in a new tab)
Structured output: SupportedSource for Structured output (opens in a new tab)
Streaming: SupportedSource for Streaming (opens in a new tab)
Batch processing: SupportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not collected
Knowledge cutoff: Not collected
Release date: Not collected
Parameters: Not collected
Architecture: Not collected
Languages: Not collected
Context caching: SupportedSource for Context caching (opens in a new tab)
Maximum input tokens: 224KSource for Maximum input tokens (opens in a new tab)
Maximum thinking tokens: 128KSource for Maximum thinking tokens (opens in a new tab)
Published request quota: 30K Max RPM; 1500K Max TPMSource for Published request quota (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

BytePlus ModelArk · standard

Provider source (opens in a new tab)

API model ID: seed-2-0-lite-260228
Access: Existing ModelArk access only under the Dola-alias deprecation notice. Verify the selected regional route; model naming differs between the catalog and lifecycle notice.
Regions: Not collected
Service tier: standardSource for Service tier (opens in a new tab)
Endpoint availability: Related Dola-named release: no new ModelArk endpoints/tuning from September 15; deactivation scheduled November 11, 2026. Catalog retains the older Seed spelling.Source for Endpoint availability (opens in a new tab)

INPUT / 1M TOKENS$0.25

OUTPUT / 1M TOKENS$2.00

standard non-audio rate table. Full prompt length selects the rate for the entire request; thinking tokens count toward output. Finite pricing bounds do not override modality-specific API input limits. Cached input price: $0.05 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input length	Input	Output	Cached input
Prompt length [0, 128] K tokens	$0.25	$2.00	$0.05
Prompt length (128, 256] K tokens	$0.50	$4.00	$0.10

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)

Published billing units · original currency · observed 12 Oct 2026
Category	Usage	Rate	Unit
Caching	Explicit cache storage¹	$0.0083	1M tokens/hour
Caching	Explicit cache storage²	$0.0083	1M tokens/hour

Rate conditions

Prompt length [0, 128] K tokens. Explicit cache only; implicit storage is free. Partial natural hours billed as whole hours. Pricing-table units used; the cache guide uses a different generic unit description.
Prompt length (128, 256] K tokens. Explicit cache only; implicit storage is free. Partial natural hours billed as whole hours. Pricing-table units used; the cache guide uses a different generic unit description.

Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

BytePlus ModelArk · batch

Provider source (opens in a new tab)

API model ID: seed-2-0-lite-260228
Access: Existing ModelArk access only under the Dola-alias deprecation notice. Verify the selected regional route; model naming differs between the catalog and lifecycle notice.
Regions: Not collected
Service tier: batchSource for Service tier (opens in a new tab)
Batch processing: SupportedSource for Batch processing (opens in a new tab)
Endpoint availability: Related Dola-named release: no new ModelArk endpoints/tuning from September 15; deactivation scheduled November 11, 2026. Catalog retains the older Seed spelling.Source for Endpoint availability (opens in a new tab)

INPUT / 1M TOKENS$0.125

OUTPUT / 1M TOKENS$1.00

batch non-audio rate table. Full prompt length selects the rate for the entire request; thinking tokens count toward output. Finite pricing bounds do not override modality-specific API input limits. Cached input price: $0.05 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input length	Input	Output	Cached input
Prompt length [0, 128] K tokens	$0.125	$1.00	$0.05
Prompt length (128, 256] K tokens	$0.25	$2.00	$0.10

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

BytePlus LAS

Provider source (opens in a new tab)

API model ID: seed-2-0-lite-260228
Access: LAS API key required. ModelArk prices, caching, batch service and retirement notices are not inherited without a LAS-specific contract.
Regions: ap-southeast-1
API endpoint URL: POST https://operator.las.ap-southeast-1.bytepluses.com/api/v1/chat/completionsSource for API endpoint URL (opens in a new tab)
Supported input workflows: Documented text, image and video understanding operator.Source for Supported input workflows (opens in a new tab)
Request limits: max_completion_tokens range: 0–64K, including reasoning and answer; cannot be combined with max_tokens.Source for Request limits (opens in a new tab)
Generation mode: Thinking defaults on and can be disabled; tool_choice supports none, auto, required or a named function.Source for Generation mode (opens in a new tab)
Tool calling: SupportedSource for Tool calling (opens in a new tab)
Reasoning: SupportedSource for Reasoning (opens in a new tab)
Configuration discrepancy: The supported-version list and working example use Pro 260328; a single model-field example instead says Pro 260215. The enumerated supported list is preserved.Source for Configuration discrepancy (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

BytePlus ModelArk deprecated Dola alias

Provider source (opens in a new tab)

API model ID: dola-seed-2-0-lite-260228
Access: Existing access only. Do not create new inference endpoints or fine-tuning jobs on this deprecated alias.
Regions: Not collected
Endpoint availability: EOM September 15, 2026; EOS November 11, 2026. Recommended replacement: dola-seed-2-0-lite-260428Source for Endpoint availability (opens in a new tab)
API model selector: Deprecation notice uses dola-seed-2-0-lite-260228; catalog and older access examples use seed-2-0-lite-260228.Source for API model selector (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

BytePlus ModelArk · standard

seed-2-0-lite-260228

Documented

Support evidence (opens in a new tab)

How it works: Implicit: Responses API, Chat API. Explicit: Responses API, Prefix caching, Session caching.Source for How it works (opens in a new tab)
Minimum reusable input: Implicit: 1,024 tokens. Explicit prefix: 256 tokens. Session cache has no minimum stated.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh: Implicit retention is dynamic. Responses explicit caching expires at expire_at, at most 7 days after creation; reuse does not extend expiration.Source for Lifetime & refresh (opens in a new tab)
How to enable it: Implicit caching is automatic. Responses explicit caching requires store=true and caching.type=enabled; reuse the stored response/prefix identifier.Source for How to enable it (opens in a new tab)
Usage fields: Inspect cached_tokens in the response usage details to distinguish hits from uncached input.Source for Usage fields (opens in a new tab)
Billing rules: Cached-input rates depend on prompt length. Implicit storage is free. Explicit storage is billed separately, rounded to natural hours.Source for Billing rules (opens in a new tab)
Limits & data boundaries: Explicit caching replaces implicit caching for that request. The older Context API uses a different, sliding TTL; its default is not copied to Responses caching.Source for Limits & data boundaries (opens in a new tab)

Cache reads, writes & storage
Charge	Applies to	Rate / unit
Cache read¹	Text tokens · Prompt length [0, 128] K tokens	$0.05 / 1M tokensPricing evidence (opens in a new tab)
Cache read¹	Text tokens · Prompt length (128, 256] K tokens	$0.10 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache storage²	Caching	$0.0083 / 1M tokens/hourPricing evidence (opens in a new tab)
Explicit cache storage³	Caching	$0.0083 / 1M tokens/hourPricing evidence (opens in a new tab)

Rate conditions

standard non-audio rate table. Full prompt length selects the rate for the entire request; thinking tokens count toward output. Finite pricing bounds do not override modality-specific API input limits.
Prompt length [0, 128] K tokens. Explicit cache only; implicit storage is free. Partial natural hours billed as whole hours. Pricing-table units used; the cache guide uses a different generic unit description.
Prompt length (128, 256] K tokens. Explicit cache only; implicit storage is free. Partial natural hours billed as whole hours. Pricing-table units used; the cache guide uses a different generic unit description.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

BytePlus ModelArk · batch

seed-2-0-lite-260228

Documented

A cached-input rate is published for this service tier; this does not imply the standard endpoint’s explicit-storage controls.

Support evidence (opens in a new tab)

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Use the cached-input rate for this service tier and prompt-length band.Source for Billing rules (opens in a new tab)
Limits & data boundaries: Not collected

Cache reads, writes & storage
Charge	Applies to	Rate / unit
Cache read¹	Text tokens · Prompt length [0, 128] K tokens	$0.05 / 1M tokensPricing evidence (opens in a new tab)
Cache read¹	Text tokens · Prompt length (128, 256] K tokens	$0.10 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

batch non-audio rate table. Full prompt length selects the rate for the entire request; thinking tokens count toward output. Finite pricing bounds do not override modality-specific API input limits.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

BytePlus LAS

seed-2-0-lite-260228

Not verified

No route-specific cache contract established. Base ModelArk cache behavior is not copied to this integration.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

BytePlus ModelArk deprecated Dola alias

dola-seed-2-0-lite-260228

Not verified

No route-specific cache contract established. Base ModelArk cache behavior is not copied to this integration.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred from the named native hosted API offering and cross-check of ByteDance and ByteDance-Seed public repositories. No matching downloadable checkpoint was found. This is not an explicit published weight-license declaration.

Classification evidence (opens in a new tab)

Lifecycle dates

BytePlus Dola alias deprecation announced8 Sept 2026Source (opens in a new tab)

BytePlus Dola alias closed to new endpoints and tuning15 Sept 2026Source (opens in a new tab)

BytePlus Dola alias service deactivation scheduled11 Nov 2026Source (opens in a new tab)

Sources reviewed

BytePlus: Model IDs, availability, limits and capabilities (opens in a new tab)Reviewed 15 Oct 2026

BytePlus: API pricing and billing units (opens in a new tab)Reviewed 15 Oct 2026

ByteDance official model index (opens in a new tab)Reviewed 15 Oct 2026

ByteDance official public-weight inventory (opens in a new tab)Reviewed 15 Oct 2026

BytePlus: Cache modes, eligibility, lifecycle and billing (opens in a new tab)Reviewed 15 Oct 2026

BytePlus: Streaming API examples (opens in a new tab)Reviewed 15 Oct 2026

byteplus las seed2 current (opens in a new tab)Reviewed 15 Oct 2026

BytePlus model deprecations (opens in a new tab)Reviewed 15 Oct 2026

Model notes

67 reviewed records, including historical and research releases. Remaining model and detail coverage is under review.

Input-limit discrepancy: the text-generation section lists 224K tokens, while visual understanding lists 256K. Confirm the limit for your request type; the table preserves the text-generation value.

The tool-use section names seed-2-0-lite-260215, while the main catalog and pricing name seed-2-0-lite-260228. These identifiers have not been assumed interchangeable. Tool calling is independently listed in this model’s main catalog row.

Release-specific parameter counts, training cutoff dates and data-retention policies are not verified unless a sourced field says otherwise. A date-like API suffix is not treated as a launch date.

Prompt prices use the model-specific rate table. A worked pricing example on the page uses values inconsistent with that table; no example rate overrides the table.

BytePlus uses the Dola-prefixed name in its deprecation notice and the Seed name in other interfaces. Both are shown under this release; deprecation is not an immediate worldwide shutdown, and LAS availability must be checked separately.

Check against your workload

Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.

Read our methodology