ByteDance / Seed

Seed 2.0 Lite (260428)

Seed 2.0 Lite language-model revision 260428, with documented reasoning and tool calling through ModelArk.

Language models (LLMs)

availableClosed weightsText generation

Official documentation (opens in a new tab)Reviewed 15 Oct 2026
13 of 20 specification fields collected

Input token limit256KSee 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, Video, AudioSource 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: Not collected
Batch processing: Not collected
Fine-tuning: SupportedSource for Fine-tuning (opens in a new tab)
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: 256KSource 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)
Fine-tuning methods: SFT, DPO and GRPO with LoRA or full tuning; deployed tuned limits and prices differ from the base model.Source for Fine-tuning methods (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-260428
Access: ModelArk API access requires an eligible BytePlus account and enabled model. Published quotas are account-dependent.
Regions: Not collected
Service tier: standardSource for Service tier (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
Audio tokens	Input²	$3.75	1M audio tokens
Caching · audio tokens	Cached audio input²	$0.75	1M audio tokens
Caching	Explicit cache storage³	$0.0083	1M tokens/hour
Audio tokens	Input⁴	$7.50	1M audio tokens
Caching · audio tokens	Cached audio input⁴	$1.50	1M audio tokens

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 [0, 128] K prompt tokens; standard inference only.
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.
Prompt length (128, 256] K prompt tokens; standard inference only.

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.

Volcengine Ark (China) · Standard online; other family tariff modes are listed separately and require eligibility.

Provider source (opens in a new tab)

API model ID: doubao-seed-2-0-lite-260428
Access: Native service activation and an eligible Volcengine account/API key required. No inference executed.
Regions: cn-beijing
Context / input limit: 256KSource for Context / input limit (opens in a new tab)
Maximum input tokens: 224KSource for Maximum input tokens (opens in a new tab)
Maximum output: 128KSource for Maximum output (opens in a new tab)
Published chain-of-thought limit: 128KSource for Published chain-of-thought limit (opens in a new tab)
Input modalities: Text, Image, Video, AudioSource 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)
Published request quota: Max RPM: 30000 Max TPM: 5000000Source for Published request quota (opens in a new tab)
Service tier: Standard online; other family tariff modes are listed separately and require eligibility.Source for Service tier (opens in a new tab)
Streaming: Not collected
Batch processing: Not collected
Fine-tuning: Not collected
Configuration discrepancy: Native text input limit is 224K; the international record lists 256K. Preserve the regional contracts.Source for Configuration discrepancy (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
Category	Usage	Rate	Unit
Volcengine Standard online family tariff	Non-audio input · Input length [0, 32] (thousand tokens)¹	CN¥0.60	1M tokens
Volcengine Standard online family tariff	Audio input · Input length [0, 32] (thousand tokens)¹	CN¥9.00	1M tokens
Volcengine Standard online family tariff	Explicit cache storage · Input length [0, 32] (thousand tokens)¹	CN¥0.017	1M tokens/hour
Volcengine Standard online family tariff	Cached non-audio input · Input length [0, 32] (thousand tokens)¹	CN¥0.12	1M tokens
Volcengine Standard online family tariff	Cached audio input · Input length [0, 32] (thousand tokens)¹	CN¥1.80	1M tokens
Volcengine Standard online family tariff	Output · Input length [0, 32] (thousand tokens)¹	CN¥3.60	1M tokens
Volcengine Standard online family tariff	Non-audio input · Input length (32, 128] (thousand tokens)²	CN¥0.90	1M tokens
Volcengine Standard online family tariff	Audio input · Input length (32, 128] (thousand tokens)²	CN¥13.50	1M tokens
Volcengine Standard online family tariff	Explicit cache storage · Input length (32, 128] (thousand tokens)²	CN¥0.017	1M tokens/hour
Volcengine Standard online family tariff	Cached non-audio input · Input length (32, 128] (thousand tokens)²	CN¥0.18	1M tokens
Volcengine Standard online family tariff	Cached audio input · Input length (32, 128] (thousand tokens)²	CN¥2.70	1M tokens
Volcengine Standard online family tariff	Output · Input length (32, 128] (thousand tokens)²	CN¥5.40	1M tokens
Volcengine Standard online family tariff	Non-audio input · Input length (128, 256] (thousand tokens)³	CN¥1.80	1M tokens
Volcengine Standard online family tariff	Audio input · Input length (128, 256] (thousand tokens)³	CN¥27.00	1M tokens
Volcengine Standard online family tariff	Explicit cache storage · Input length (128, 256] (thousand tokens)³	CN¥0.017	1M tokens/hour
Volcengine Standard online family tariff	Cached non-audio input · Input length (128, 256] (thousand tokens)³	CN¥0.36	1M tokens
Volcengine Standard online family tariff	Cached audio input · Input length (128, 256] (thousand tokens)³	CN¥5.40	1M tokens
Volcengine Standard online family tariff	Output · Input length (128, 256] (thousand tokens)³	CN¥10.80	1M tokens
Volcengine Low-latency online family tariff	Non-audio input · Input length [0, 32] (thousand tokens)⁴	CN¥1.20	1M tokens
Volcengine Low-latency online family tariff	Audio input · Input length [0, 32] (thousand tokens)⁴	CN¥18.00	1M tokens
Volcengine Low-latency online family tariff	Cached non-audio input · Input length [0, 32] (thousand tokens)⁴	CN¥0.24	1M tokens
Volcengine Low-latency online family tariff	Cached audio input · Input length [0, 32] (thousand tokens)⁴	CN¥3.60	1M tokens
Volcengine Low-latency online family tariff	Output · Input length [0, 32] (thousand tokens)⁴	CN¥7.20	1M tokens
Volcengine Low-latency online family tariff	Non-audio input · Input length (32, 128] (thousand tokens)⁵	CN¥1.80	1M tokens
Volcengine Low-latency online family tariff	Audio input · Input length (32, 128] (thousand tokens)⁵	CN¥27.00	1M tokens
Volcengine Low-latency online family tariff	Cached non-audio input · Input length (32, 128] (thousand tokens)⁵	CN¥0.36	1M tokens
Volcengine Low-latency online family tariff	Cached audio input · Input length (32, 128] (thousand tokens)⁵	CN¥5.40	1M tokens
Volcengine Low-latency online family tariff	Output · Input length (32, 128] (thousand tokens)⁵	CN¥10.80	1M tokens
Volcengine Low-latency online family tariff	Non-audio input · Input length (128, 256] (thousand tokens)⁶	CN¥3.60	1M tokens
Volcengine Low-latency online family tariff	Audio input · Input length (128, 256] (thousand tokens)⁶	CN¥54.00	1M tokens
Volcengine Low-latency online family tariff	Cached non-audio input · Input length (128, 256] (thousand tokens)⁶	CN¥0.72	1M tokens
Volcengine Low-latency online family tariff	Cached audio input · Input length (128, 256] (thousand tokens)⁶	CN¥10.80	1M tokens
Volcengine Low-latency online family tariff	Output · Input length (128, 256] (thousand tokens)⁶	CN¥21.60	1M tokens
Volcengine Flex online family tariff	Non-audio input · Input length [0, 32] (thousand tokens)⁷	CN¥0.30	1M tokens
Volcengine Flex online family tariff	Audio input · Input length [0, 32] (thousand tokens)⁷	CN¥4.50	1M tokens
Volcengine Flex online family tariff	Cached non-audio input · Input length [0, 32] (thousand tokens)⁷	CN¥0.12	1M tokens
Volcengine Flex online family tariff	Cached audio input · Input length [0, 32] (thousand tokens)⁷	CN¥1.80	1M tokens
Volcengine Flex online family tariff	Output · Input length [0, 32] (thousand tokens)⁷	CN¥1.80	1M tokens
Volcengine Flex online family tariff	Non-audio input · Input length (32, 128] (thousand tokens)⁸	CN¥0.45	1M tokens
Volcengine Flex online family tariff	Audio input · Input length (32, 128] (thousand tokens)⁸	CN¥6.75	1M tokens
Volcengine Flex online family tariff	Cached non-audio input · Input length (32, 128] (thousand tokens)⁸	CN¥0.18	1M tokens
Volcengine Flex online family tariff	Cached audio input · Input length (32, 128] (thousand tokens)⁸	CN¥2.70	1M tokens
Volcengine Flex online family tariff	Output · Input length (32, 128] (thousand tokens)⁸	CN¥2.70	1M tokens
Volcengine Flex online family tariff	Non-audio input · Input length (128, 256] (thousand tokens)⁹	CN¥0.90	1M tokens
Volcengine Flex online family tariff	Audio input · Input length (128, 256] (thousand tokens)⁹	CN¥13.50	1M tokens
Volcengine Flex online family tariff	Cached non-audio input · Input length (128, 256] (thousand tokens)⁹	CN¥0.36	1M tokens
Volcengine Flex online family tariff	Cached audio input · Input length (128, 256] (thousand tokens)⁹	CN¥5.40	1M tokens
Volcengine Flex online family tariff	Output · Input length (128, 256] (thousand tokens)⁹	CN¥5.40	1M tokens
Volcengine Batch inference family tariff	Non-audio input · Input length [0, 32] (thousand tokens)¹⁰	CN¥0.30	1M tokens
Volcengine Batch inference family tariff	Audio input · Input length [0, 32] (thousand tokens)¹⁰	CN¥4.50	1M tokens
Volcengine Batch inference family tariff	Cached non-audio input · Input length [0, 32] (thousand tokens)¹⁰	CN¥0.12	1M tokens
Volcengine Batch inference family tariff	Cached audio input · Input length [0, 32] (thousand tokens)¹⁰	CN¥1.80	1M tokens
Volcengine Batch inference family tariff	Output · Input length [0, 32] (thousand tokens)¹⁰	CN¥1.80	1M tokens
Volcengine Batch inference family tariff	Non-audio input · Input length (32, 128] (thousand tokens)¹¹	CN¥0.45	1M tokens
Volcengine Batch inference family tariff	Audio input · Input length (32, 128] (thousand tokens)¹¹	CN¥6.75	1M tokens
Volcengine Batch inference family tariff	Cached non-audio input · Input length (32, 128] (thousand tokens)¹¹	CN¥0.18	1M tokens
Volcengine Batch inference family tariff	Cached audio input · Input length (32, 128] (thousand tokens)¹¹	CN¥2.70	1M tokens
Volcengine Batch inference family tariff	Output · Input length (32, 128] (thousand tokens)¹¹	CN¥2.70	1M tokens
Volcengine Batch inference family tariff	Non-audio input · Input length (128, 256] (thousand tokens)¹²	CN¥0.90	1M tokens
Volcengine Batch inference family tariff	Audio input · Input length (128, 256] (thousand tokens)¹²	CN¥13.50	1M tokens
Volcengine Batch inference family tariff	Cached non-audio input · Input length (128, 256] (thousand tokens)¹²	CN¥0.36	1M tokens
Volcengine Batch inference family tariff	Cached audio input · Input length (128, 256] (thousand tokens)¹²	CN¥5.40	1M tokens
Volcengine Batch inference family tariff	Output · Input length (128, 256] (thousand tokens)¹²	CN¥5.40	1M tokens

Rate conditions

doubao-seed-2.0-lite, Standard online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Standard online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Standard online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.

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 LAS

Provider source (opens in a new tab)

API model ID: seed-2-0-lite-260428
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 custom LoRA inference

Provider source (opens in a new tab)

API model ID: Not collected
Access: Requires a trained custom model and eligible deployment. The identifier is generated by the account workflow; base-model limits and cache controls are not assumed for the tuned deployment.
Regions: ap-southeast-1 (console workflow)
Fine-tuning: SupportedSource for Fine-tuning (opens in a new tab)
Fine-tuning methods: SFT, DPO and GRPO; LoRA and full-parameter training are listed. Full/LoRA SFT support audio_url and video_url.Source for Fine-tuning methods (opens in a new tab)
Context / input limit: 256KSource for Context / input limit (opens in a new tab)
Maximum output: 32KSource for Maximum output (opens in a new tab)
Published chain-of-thought limit: 32KSource for Published chain-of-thought limit (opens in a new tab)
Published price: Pay-as-you-go LoRA inference: twice the matching base-model rate, using the same context window.Source for Published price (opens in a new tab)
Customization options: Lite model-unit and batch columns are unlisted in this model table; Mini deployment claims are not copied.Source for Customization options (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-260428

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)
Cached audio input³	Caching · audio tokens	$0.75 / 1M audio tokensPricing evidence (opens in a new tab)
Explicit cache storage⁴	Caching	$0.0083 / 1M tokens/hourPricing evidence (opens in a new tab)
Cached audio input⁵	Caching · audio tokens	$1.50 / 1M audio tokensPricing 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 [0, 128] K prompt tokens; standard inference only.
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.
Prompt length (128, 256] K prompt tokens; standard inference only.

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

Caching reviewed 12 Oct 2026

Volcengine Ark (China) · Standard online; other family tariff modes are listed separately and require eligibility.

doubao-seed-2-0-lite-260428

Documented

Support evidence (opens in a new tab)

How it works: Implicit prefix reuse; explicit Responses prefix/session caching.Source for How it works (opens in a new tab)
Minimum reusable input: Implicit: 1,024 tokens. Explicit prefix: 256 tokens; session: no minimum.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh: Implicit retention is dynamic. Explicit expire_at is at most seven days ahead and reuse does not renew it.Source for Lifetime & refresh (opens in a new tab)
How to enable it: Implicit is automatic. Explicit uses store=true, caching.type=enabled and previous_response_id.Source for How to enable it (opens in a new tab)
Usage fields: Reuse matching prefixes or stored conversation history. Implicit hits are not guaranteed.Source for Usage fields (opens in a new tab)
Billing rules: Implicit storage is free; explicit storage costs CNY 0.017 per 1M tokens/hour, rounded to natural hours. Hit-input and output tokens are separate charges.Source for Billing rules (opens in a new tab)
Limits & data boundaries: Explicit cache history allows json_object, not json_schema; prefix creation cannot stream. Maintain thinking settings across reused history.Source for Limits & data boundaries (opens in a new tab)

Cache reads, writes & storage
Charge	Applies to	Rate / unit
Explicit cache storage · Input length [0, 32] (thousand tokens)¹	Volcengine Standard online family tariff	CN¥0.017 / 1M tokens/hourPricing evidence (opens in a new tab)
Cached non-audio input · Input length [0, 32] (thousand tokens)¹	Volcengine Standard online family tariff	CN¥0.12 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length [0, 32] (thousand tokens)¹	Volcengine Standard online family tariff	CN¥1.80 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache storage · Input length (32, 128] (thousand tokens)²	Volcengine Standard online family tariff	CN¥0.017 / 1M tokens/hourPricing evidence (opens in a new tab)
Cached non-audio input · Input length (32, 128] (thousand tokens)²	Volcengine Standard online family tariff	CN¥0.18 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (32, 128] (thousand tokens)²	Volcengine Standard online family tariff	CN¥2.70 / 1M tokensPricing evidence (opens in a new tab)
Explicit cache storage · Input length (128, 256] (thousand tokens)³	Volcengine Standard online family tariff	CN¥0.017 / 1M tokens/hourPricing evidence (opens in a new tab)
Cached non-audio input · Input length (128, 256] (thousand tokens)³	Volcengine Standard online family tariff	CN¥0.36 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (128, 256] (thousand tokens)³	Volcengine Standard online family tariff	CN¥5.40 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length [0, 32] (thousand tokens)⁴	Volcengine Low-latency online family tariff	CN¥0.24 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length [0, 32] (thousand tokens)⁴	Volcengine Low-latency online family tariff	CN¥3.60 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (32, 128] (thousand tokens)⁵	Volcengine Low-latency online family tariff	CN¥0.36 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (32, 128] (thousand tokens)⁵	Volcengine Low-latency online family tariff	CN¥5.40 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (128, 256] (thousand tokens)⁶	Volcengine Low-latency online family tariff	CN¥0.72 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (128, 256] (thousand tokens)⁶	Volcengine Low-latency online family tariff	CN¥10.80 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length [0, 32] (thousand tokens)⁷	Volcengine Flex online family tariff	CN¥0.12 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length [0, 32] (thousand tokens)⁷	Volcengine Flex online family tariff	CN¥1.80 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (32, 128] (thousand tokens)⁸	Volcengine Flex online family tariff	CN¥0.18 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (32, 128] (thousand tokens)⁸	Volcengine Flex online family tariff	CN¥2.70 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (128, 256] (thousand tokens)⁹	Volcengine Flex online family tariff	CN¥0.36 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (128, 256] (thousand tokens)⁹	Volcengine Flex online family tariff	CN¥5.40 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length [0, 32] (thousand tokens)¹⁰	Volcengine Batch inference family tariff	CN¥0.12 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length [0, 32] (thousand tokens)¹⁰	Volcengine Batch inference family tariff	CN¥1.80 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (32, 128] (thousand tokens)¹¹	Volcengine Batch inference family tariff	CN¥0.18 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (32, 128] (thousand tokens)¹¹	Volcengine Batch inference family tariff	CN¥2.70 / 1M tokensPricing evidence (opens in a new tab)
Cached non-audio input · Input length (128, 256] (thousand tokens)¹²	Volcengine Batch inference family tariff	CN¥0.36 / 1M tokensPricing evidence (opens in a new tab)
Cached audio input · Input length (128, 256] (thousand tokens)¹²	Volcengine Batch inference family tariff	CN¥5.40 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

doubao-seed-2.0-lite, Standard online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Standard online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Standard online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Low-latency online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Flex online; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length [0, 32] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length (32, 128] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.
doubao-seed-2.0-lite, Batch inference; request input length (128, 256] thousand tokens determines the whole-request rate. Family schedule does not establish dated-endpoint eligibility for every mode. Explicit storage is extra; Flex allows implicit cache only. Native CNY, no currency conversion.

Observed 15 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 15 Oct 2026

BytePlus LAS

seed-2-0-lite-260428

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 custom LoRA inference

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)

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: Model-specific fine-tuning methods (opens in a new tab)Reviewed 15 Oct 2026

volcengine native model list (opens in a new tab)Reviewed 15 Oct 2026

volcengine native pricing (opens in a new tab)Reviewed 15 Oct 2026

volcengine native cache (opens in a new tab)Reviewed 15 Oct 2026

volcengine native deprecations (opens in a new tab)Reviewed 15 Oct 2026

byteplus seed native brand map (opens in a new tab)Reviewed 15 Oct 2026

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

byteplus finetune overview current (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.

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.

Native Doubao and international Seed/Dola selectors are grouped by provider family, version date and corresponding catalog contracts. This identity grouping is inferred; identical deployed weights across regions are not asserted. Limits, pricing and retirement remain endpoint-specific.

Volcengine text input for doubao-seed-2-0-lite-260428 is 224K; the existing BytePlus input allowance is retained on the model overview. See access details for the selected region.

Check against your workload

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

Read our methodology