OpenRouter 模型 ↗ · 2026-10-02
inclusionai/ling-3.1-flash
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-10-02 收录该模型(收录时间不等于模型正式发布日期);上下文:1,000,000 tokens;输入价:$0.0450/百万 tokens;输出价:$0.1350/百万 tokens;定位(来源描述):Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active…
Full text
inclusionAI: Ling 3.1 Flash
inclusionai/ling-3.1-flash
Model weights
Compare
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Modalities
In / out price
85% off
$0.045 / $0.135per 1M
Context
1.0M
Released
Oct 2, 2026
Compare
Providers
This model is hosted by one provider. OpenRouter forwards every request without routing.
Latency / throughput
85% off
$0.30$0.045$0.90$0.135$0.06$0.0091.22s75 tok/s
100.00%
Provider85% offInput / Output /M
Input $0.045 / Output $0.13585% off
75 tok/s100.00% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.02136/M tokens
Output
$0.1549/M tokens
Ling 3.1 Flash — Price history
Price history
No effective price data for this selection
$0.0214$0.15588.3%100.0%
ProviderInput / Output /M
Token share
Effective in $0.0214 / Effective out $0.155
Token share
100.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
75tok/s
P50, best across providers
Latency
1.22s
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.50%
Availability over the last 3 days
Last 72 hours
Availability 99.50%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.63%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
Benchmark score summary for inclusionAI: Ling 3.1 Flash (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisLing 3.1 Flash 1019 Intelligence Index29.6
Artificial AnalysisLing 3.1 Flash 1019 HLE43.5%
Artificial AnalysisLing 3.1 Flash 1019 AA-LCR82.3%
Artificial AnalysisLing 3.1 Flash 1019 GDPval-AA57.7%
Artificial AnalysisLing 3.1 Flash 1019 CritPt26.0%
Artificial AnalysisLing 3.1 Flash 1019 SciCode56.8%
Artificial AnalysisLing 3.1 Flash 1019 Terminal-Bench 4.032.8%
Artificial AnalysisLing 3.1 Flash 1019 AA-Omniscience Accuracy26.5%
Artificial AnalysisLing 3.1 Flash 1019 AA-Omniscience Non-Hallucination Rate63.7%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
43.1Btokens
2.
pi
There are many coding agents, but this one is yours.
22.6Btokens
3.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
16Btokens
4.
Portkey AI
Control panel for AI apps
12Btokens
5.
omp
new
5.24Btokens
Rest of OpenRouter
3.44B
Top 5 Apps
2.43B
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Frequently asked questions
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Ling 3.1 Flash costs $0.045/M input tokens and $0.135/M output tokens, with separate rates for Cache Read at $0.009/M tokens.
Ling 3.1 Flash has a 1,000,000 token context window. It supports up to 262,144 completion tokens.
Yes. Ling 3.1 Flash accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.
Ling 3.1 Flash is served by 1 provider on OpenRouter: NovitaAI.
Ling 3.2 Flash (free), Ling 3.0 Flash VL, Ling 3.0 Tiny and 1 more are other text models from inclusionAI.
Ling 3.1 Flash was released on October 2, 2026.