Best Value
ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.
Last updated: 56 min ago (2026-11-18 12:41)Sources and methodology
Ascending price, free models first; for budget-sensitive / high-concurrency workloads.
2. Benchmarks:Intelligence, coding, and agentic indices are sourced directly from Artificial Analysis (artificialanalysis.ai) official benchmark indices.
3. Overall Score Weights:Overall Score = 60% × Intelligence Index + 25% × Coding Index + 15% × Agentic Index. Models without benchmark data are ranked at the end.
4. Referral links:"Try it" buttons marked "Referral" are referral links; ZICQ may earn a commission. Referral relationships never affect rankings or scores.
Statistics for this selection
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
| Metric | inclusionAI: Ling 3.2 Flash (free) Inclusionai | Baidu: ERNIE-5.5-Flash-Preview (free) Baidu | Thinking Machines: Inkling 2 Small (free) Thinkingmachines |
|---|---|---|---|
| Intelligence / Coding / Agentic | — | — | 30.6 / 0.0 / 0.0 |
| Context Window | 1.0M tokens | 1.0M tokens | 1.0M tokens |
| Input / Output Price (1M) | Free | Free | Free |
| Est. Monthly Cost (30d) | $0.00 / mo | $0.00 / mo | $0.00 / mo |
-
#21
Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...
Context 1M$-1000000.00/1M $-1000000.00/1M outExtreme Value -
#22
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
Tools Vision Audio Video Docs Reasoning Structured Image genContext 2M Output ≤ 64K$-1000000.00/1M $-1000000.00/1M outExtreme Value -
#23
Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...
Context 1M$-1000000.00/1M $-1000000.00/1M outExtreme Value -
#24
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...
Tools Reasoning StructuredContext 2M$-1000000.00/1M $-1000000.00/1M outExtreme Value -
#25
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...
Context 128K$-1000000.00/1M $-1000000.00/1M outExtreme Value -
#26
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Tools Reasoning StructuredContext 1.0M Output ≤ 943K$0.01/1M $6.80/1M out cache $0.01/1MExtreme Value -
#27
Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...
Tools Reasoning StructuredContext 262K Output ≤ 250K$0.01/1M $0.04/1M out cache $0.00/1MExtreme Value -
#28
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Tools Reasoning StructuredContext 131K Output ≤ 117K$0.02/1M $0.09/1M out cache $0.01/1MExtreme Value -
#29
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Tools StructuredContext 131K Output ≤ 16K$0.02/1M $0.04/1M outExtreme Value -
#30
*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...
Tools Reasoning StructuredContext 262K Output ≤ 32K$0.02/1M $0.06/1M out cache $0.00/1MExtreme Value -
#31
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Tools Vision Video Reasoning StructuredContext 1.0M Output ≤ 943K$0.02/1M $0.07/1M out cache $0.01/1MExtreme Value -
#32
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Tools Reasoning StructuredContext 131K Output ≤ 117K$0.02/1M $0.11/1M outExtreme Value -
#33
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
Vision Reasoning StructuredContext 262K Output ≤ 235K$0.02/1M $0.10/1M out cache $0.00/1MExtreme Value -
#34
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
Tools Vision Docs Reasoning StructuredContext 400K Output ≤ 128K$0.02/1M $0.20/1M out cache $0.00/1MExtreme Value -
#35
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
Context 60K Output ≤ 54K$0.03/1M $0.20/1M outExtreme Value -
#36
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Tools StructuredContext 131K Output ≤ 16K$0.03/1M $0.03/1M outExtreme Value -
#37
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Tools Reasoning StructuredContext 131K Output ≤ 117K$0.03/1M $0.14/1M outExtreme Value -
#38
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
StructuredContext 128K Output ≤ 8K$0.03/1M $0.15/1M out cache $0.03/1MExtreme Value -
#39
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Tools Vision Video Reasoning StructuredContext 1M Output ≤ 65K$0.03/1M $0.13/1M out cache $0.01/1MExtreme Value -
#40
Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...
Tools Vision Reasoning StructuredContext 1.0M Output ≤ 65K$0.04/1M $0.14/1M out cache $0.00/1MExtreme Value