Skip to content
Model infoModelsSnapshot: 15 Oct 2026

iFLYTEK / Spark

Spark X2.5

Flagship Spark reasoning model for coding and agent tasks, with more than 200 languages.

Language models (LLMs)
availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
7 of 16 specification fields collected
Context window256KSee specification notes below
Maximum outputNot collectedAwaiting source review
Input billingSee ratesiFLYTEK
Output billingSee ratesPublished units and conditions below

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)

The Token Plan context is documented; the 1M context of open 4B/1.7B releases must not be inherited.

Maximum output
Not collected
Input modalities
TextSource 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
Not collected

Agent capability is advertised and the MaaS interface accepts tools, but a model-specific compatibility guarantee has not been verified.

Structured output
Not collected

MaaS JSON mode explicitly names DeepSeek, GLM, Kimi and Qwen; do not infer Spark support from generic OpenAI compatibility.

Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
More than 200 languagesSource for Languages (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)

A cache-hit token rate is published. Cache TTL, minimum prefix and API controls are not verified.

Access & pricing

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

iFLYTEK

Provider source (opens in a new tab)
API model ID
spark-x2.5
Access
Authenticated native service. Model authorization and the corresponding API credentials are required. No paid inference was performed.
Regions
China-hosted service; endpoint hostname is recorded, but no customer-specific residency or international eligibility guarantee is inferred.
API endpoint URL
POST https://maas-api.cn-huabei-1.xf-yun.com/v2/chat/completionsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text tokensInput1CN¥1.601M tokens
Text tokensOutput1CN¥6.001M tokens
Prompt cacheCached input1CN¥0.241M tokens

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.
Pricing source (opens in a new tab)

Data & enterprise terms

The LLM API service agreement reserves provider IP and keeps input/output ownership with the user or original rights holder. The consumer SparkDesk privacy policy is not treated as an API no-training or zero-retention contract.

Read the service policy (opens in a new tab)

iFLYTEK

Provider source (opens in a new tab)
API model ID
spark-x2.5
Access
Authenticated native service. Model authorization and the corresponding API credentials are required. No paid inference was performed.
Regions
China-hosted service; endpoint hostname is recorded, but no customer-specific residency or international eligibility guarantee is inferred.
API endpoint URL
POST https://maas-api.cn-huabei-1.xf-yun.com/v1/responsesSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text tokensInput1CN¥1.601M tokens
Text tokensOutput1CN¥6.001M tokens
Prompt cacheCached input1CN¥0.241M tokens

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.
Pricing source (opens in a new tab)

Data & enterprise terms

The LLM API service agreement reserves provider IP and keeps input/output ownership with the user or original rights holder. The consumer SparkDesk privacy policy is not treated as an API no-training or zero-retention contract.

Read the service policy (opens in a new tab)

iFLYTEK

Provider source (opens in a new tab)
API model ID
spark-x2.5
Access
Authenticated native service. Model authorization and the corresponding API credentials are required. No paid inference was performed.
Regions
China-hosted service; endpoint hostname is recorded, but no customer-specific residency or international eligibility guarantee is inferred.
API endpoint URL
POST https://maas-api.cn-huabei-1.xf-yun.com/anthropic/v1/messagesSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text tokensInput1CN¥1.601M tokens
Text tokensOutput1CN¥6.001M tokens
Prompt cacheCached input1CN¥0.241M tokens

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.
Pricing source (opens in a new tab)

Data & enterprise terms

The LLM API service agreement reserves provider IP and keeps input/output ownership with the user or original rights holder. The consumer SparkDesk privacy policy is not treated as an API no-training or zero-retention contract.

Read the service policy (opens in a new tab)

iFLYTEK

Provider source (opens in a new tab)
API model ID
spark-x2.5
Access
Requires a Token Plan subscription and its dedicated key; this key is separate from standard inference credentials.
Regions
China-hosted service; endpoint hostname is recorded, but no customer-specific residency or international eligibility guarantee is inferred.
API endpoint URL
https://maas-token-api.cn-huabei-1.xf-yun.com/v2Source for API endpoint URL (opens in a new tab)
Usage metering
Per 1M tokens: 320 input points; 48 cache-hit points; 1200 output points; 1200 thinking pointsSource for Usage metering (opens in a new tab)

Plan points are not yuan, dollars or API token balances.

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

Data & enterprise terms

The LLM API service agreement reserves provider IP and keeps input/output ownership with the user or original rights holder. The consumer SparkDesk privacy policy is not treated as an API no-training or zero-retention contract.

Read the service policy (opens in a new tab)

iFLYTEK

Provider source (opens in a new tab)
API model ID
spark-x2.5
Access
Requires a Token Plan subscription and its dedicated key; this key is separate from standard inference credentials.
Regions
China-hosted service; endpoint hostname is recorded, but no customer-specific residency or international eligibility guarantee is inferred.
API endpoint URL
https://maas-token-api.cn-huabei-1.xf-yun.com/anthropicSource for API endpoint URL (opens in a new tab)
Usage metering
Per 1M tokens: 320 input points; 48 cache-hit points; 1200 output points; 1200 thinking pointsSource for Usage metering (opens in a new tab)

Plan points are not yuan, dollars or API token balances.

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

Data & enterprise terms

The LLM API service agreement reserves provider IP and keeps input/output ownership with the user or original rights holder. The consumer SparkDesk privacy policy is not treated as an API no-training or zero-retention contract.

Read the service policy (opens in a new tab)

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.

iFLYTEK

spark-x2.5
Documented
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
CNY 0.24 per 1M cache-hit tokens during the published promotionSource for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected

Cache minimum, retention time, activation controls and write/storage fees have not been verified.

Cache reads, writes & storage
ChargeApplies toRate / unit
Cached input1Prompt cacheCN¥0.24 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.

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

Caching reviewed 12 Oct 2026

iFLYTEK

spark-x2.5
Documented
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
CNY 0.24 per 1M cache-hit tokens during the published promotionSource for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected

Cache minimum, retention time, activation controls and write/storage fees have not been verified.

Cache reads, writes & storage
ChargeApplies toRate / unit
Cached input1Prompt cacheCN¥0.24 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.

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

Caching reviewed 12 Oct 2026

iFLYTEK

spark-x2.5
Documented
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
CNY 0.24 per 1M cache-hit tokens during the published promotionSource for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected

Cache minimum, retention time, activation controls and write/storage fees have not been verified.

Cache reads, writes & storage
ChargeApplies toRate / unit
Cached input1Prompt cacheCN¥0.24 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Limited-time 50%-off quote published on the native Spark API catalog. CNY, not USD. Promotion end date and account eligibility are not verified.

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

Caching reviewed 12 Oct 2026

iFLYTEK

spark-x2.5
Documented
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
48 points per 1M cached input tokensSource for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected

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

Caching reviewed 12 Oct 2026

iFLYTEK

spark-x2.5
Documented
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
48 points per 1M cached input tokensSource for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected

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

Caching reviewed 12 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 closed-weight native Spark service: the provider documents this named service behind authenticated API access and reserves service IP in its LLM API terms. This is distinct from the explicitly released XHToken 4B/1.7B weights and the third-party open models hosted by MaaS. API or SDK source availability is not model-weight availability.

Classification evidence (opens in a new tab)

Sources reviewed