Skip to content
Model infoModelsSnapshot: 15 Oct 2026

iFLYTEK / Spark

Spark X2 Flash

Reasoning and coding model with enabled, disabled or automatic thinking and custom tool calls.

Language models (LLMs)
availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
11 of 18 specification fields collected
Context window262.1K262,144 tokens
Maximum output262.1K262,144 tokens
Input billingSee billing notesiFLYTEK
Output billingSee billing notesAccess and billing notes below

Specifications

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

Context / input limit
262,144 tokensSource for Context / input limit (opens in a new tab)

The API sets an upper max_tokens of 262,144 and defaults to 256K minus input length; context is shared.

Maximum output
262,144 tokensSource for Maximum output (opens in a new tab)

Parameter ceiling, not 262,144 output tokens in addition to an input context. Available output depends on prompt length.

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
SupportedSource for Tool calling (opens in a new tab)

Supports automatic, none, required, forced-function and allowed-tools policies; web search and function tools cannot be sent together.

Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Asynchronous JSONL batch requests, completed within 24 hours; listed at 30% of realtime charges.

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)

Token Plan publishes cache-hit metering; support and prices must be scoped to that endpoint.

Supported reasoning efforts
enabled, disabled, autoSource for Supported reasoning efforts (opens in a new tab)

Mode selection, not low/medium/high reasoning effort.

Published price
CNY 1–2 / 1M tokens; direction split unverifiedSource for Published price (opens in a new tab)

Do not infer which end of the displayed range is input or output.

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-x
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://spark-api-open.xf-yun.com/agent/v1/chat/completionsSource for API endpoint URL (opens in a new tab)

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-x
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://spark-api-open.xf-yun.com/anthropic/agent/v1/messagesSource for API endpoint URL (opens in a new tab)

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-x
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://spark-api-open.xf-yun.com/v1/batchesSource for API endpoint URL (opens in a new tab)
Batch limits
100 MB file; at most 50,000 lines; each request body at most 6 KB; one model per fileSource for Batch limits (opens in a new tab)
completionWindow
24 hours; requests unfinished at expiry failSource for completionWindow (opens in a new tab)
Usage metering
30% of applicable realtime costSource for Usage metering (opens in a new tab)

No unverified currency amount is calculated from this multiplier.

fileRetention
Uploads: 48 hours; generated result files: 30 daysSource for fileRetention (opens in a new tab)

File retention is not an inference-cache lifetime.

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
xsparkx2flash
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: 100 input points; 20 cache-hit points; 200 output points; 200 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
xsparkx2flash
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: 100 input points; 20 cache-hit points; 200 output points; 200 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-x
Not verified
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.

iFLYTEK

spark-x
Not verified
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.

iFLYTEK

spark-x
Not verified
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.

iFLYTEK

xsparkx2flash
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
20 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

xsparkx2flash
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
20 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