259 models on CoreAI support native reasoning — they "think" through a problem step-by-step before answering, which dramatically improves accuracy on math, logic puzzles, competitive coding, and multi-step analysis. Reasoning-capable models are available from Tencent, Inclusionai, Qwen, Z.AI, Meta and more, listed newest-first below.
Reasoning mode trades speed for quality: responses take longer and consume more tokens, but for hard problems the difference is decisive. In CoreAI, models that support thinking show a "Think" chip in chat — tap it to enable deliberate reasoning for that message.
| Model | Provider | Context | Input $/1M | Output $/1M | Capabilities |
|---|---|---|---|---|---|
| Tencent: Hy4 preview | Tencent | 1049K | $0.83 | $2.50 | Reasoning |
| Ling 3.0 Flash Fin (free) | Inclusionai | 262K | $0 | $0 | Reasoning |
| Qwen: Qwen3.8 Flash | Qwen | 1000K | $0.15 | $0.47 | Reasoning, Vision |
| Z.ai: GLM 5.3 Flash | Z-ai | 1049K | $0.07 | $0.25 | Reasoning, Vision |
| Z.ai: GLM 5.3 Flash (batch) | Z-ai | 1049K | $0.15 | $0.50 | Reasoning, Vision |
| Meta: Muse Spark 1.2 Contributor | Meta | 1049K | $0.10 | $0.20 | Reasoning, Vision |
| DeepSeek: DeepSeek V4 Flash Vision Exp | DeepSeek | 1049K | $0.22 | $0.66 | Reasoning, Vision |
| Z.ai: GLM Latest | ~z-ai | 262K | $1.19 | $4.18 | Reasoning |
| Z.ai: GLM 5.3 | Z-ai | 1049K | $1.40 | $4.40 | Reasoning |
| Qwen: Qwen3.8 27B | Qwen | 1000K | $0.42 | $2.55 | Reasoning, Vision |
| Dots Studio: Dots3-Note Preview (free) | Dots-studio | 512K | $0 | $0 | Reasoning, Vision |
| Google: Gemini 3.7 Flash | 1049K | $0.75 | $3.75 | Reasoning, Vision | |
| Google: Gemini 3.7 Flash (batch) | 1049K | $0.19 | $0.94 | Reasoning, Vision | |
| ByteDance Seed: Seed 2.1 Turbo | Bytedance-seed | 262K | $0.50 | $2.50 | Reasoning, Vision |
| Qwen: Qwen3.8 2.4T A95B | Qwen | 1000K | $2 | $6 | Reasoning |
| Qwen: Qwen3.8 2.4T A95B (batch) | Qwen | 1010K | $2.50 | $6.25 | Reasoning |
| ByteDance Seed: Seed-2.0-Code | Bytedance-seed | 262K | $0.50 | $3 | Reasoning, Vision |
| DeepSeek: DeepSeek V4 Pro 0813 | DeepSeek | 1049K | $0.66 | $1.98 | Reasoning |
| DeepSeek: DeepSeek V4 Pro 0813 (batch) | DeepSeek | 1049K | $1.32 | $3.96 | Reasoning |
| SpaceXAI: Grok 4.6 | xAI | 500K | $2 | $6 | Reasoning, Vision |
| LiquidAI: LFM2.5-2.6B (free) | Liquid | 66K | $0 | $0 | Reasoning |
| NVIDIA: Nemotron 3.5 Lightning | NVIDIA | 262K | $0.08 | $0.20 | Reasoning |
| NVIDIA: Nemotron 3.5 Lightning (free) | NVIDIA | 1000K | $0 | $0 | Reasoning |
| Sakana: Sakana Namazu | Sakana | 262K | $0.95 | $4 | Reasoning, Web search, Vision |
| Upstage: Solar Pro 4 | Upstage | 524K | $0.03 | $0.12 | Reasoning |
| Meta: Muse Glimmer 30B | Meta | 131K | $0.30 | $1.20 | Reasoning, Vision |
| Meta: Muse Glimmer 30B (batch) | Meta | 131K | $0.35 | $1.50 | Reasoning, Vision |
| Meta: Muse Spark 1.2 | Meta | 1049K | $1.25 | $4.25 | Reasoning, Vision |
| Qwen: Qwen3.8 Max | Qwen | 1000K | $2 | $6 | Reasoning, Vision |
| DeepSeek V4 Flash Latest | ~deepseek | 1049K | $0.03 | $0.16 | Reasoning |
| DeepSeek: DeepSeek V4 Flash 0731 | DeepSeek | 1049K | $0.07 | $0.18 | Reasoning |
| DeepSeek: DeepSeek V4 Flash 0731 (batch) | DeepSeek | 1049K | $0.14 | $0.28 | Reasoning |
| Thinking Machines: Inkling Small | Thinkingmachines | 524K | $0.45 | $1.20 | Reasoning, Vision |
| Thinking Machines: Inkling Small (batch) | Thinkingmachines | 524K | $0.50 | $1.20 | Reasoning, Vision |
| Thinking Machines: Inkling Small (free) | Thinkingmachines | 1049K | $0 | $0 | Reasoning, Vision |
| Qwen: Qwen3.7 Flash | Qwen | 1000K | $0.03 | $0.13 | Reasoning, Vision |
| Claude Opus 5 (Fast) | Anthropic | 1000K | $10 | $50 | Reasoning, Vision |
| Claude Opus 5 | Anthropic | 1000K | $5 | $25 | Reasoning, Vision |
| Claude Opus 5 (batch) | Anthropic | 1000K | $2.50 | $12.50 | Reasoning, Vision |
| Ling-3.0-flash | Inclusionai | 262K | $0.02 | $0.06 | Reasoning |
| Poolside: Laguna S 2.1 | Poolside | 1049K | $0.09 | $0.18 | Reasoning |
| Poolside: Laguna S 2.1 (free) | Poolside | 262K | $0 | $0 | Reasoning |
| Google: Gemini 3.6 Flash | 1049K | $0.75 | $3.75 | Reasoning, Vision | |
| Google: Gemini 3.6 Flash (batch) | 1049K | $0.38 | $1.88 | Reasoning, Vision | |
| Google: Gemini 3.5 Flash Lite | 1049K | $0.30 | $2.50 | Reasoning, Vision | |
| Google: Gemini 3.5 Flash Lite (batch) | 1049K | $0.15 | $1.25 | Reasoning, Vision | |
| Meituan: LongCat 2.0 | Meituan | 1049K | $0.30 | $1.20 | Reasoning |
| Thinking Machines: Inkling | Thinkingmachines | 524K | $1 | $4.05 | Reasoning, Vision |
| Thinking Machines: Inkling (batch) | Thinkingmachines | 524K | $1 | $4.05 | Reasoning, Vision |
| Thinking Machines: Inkling (free) | Thinkingmachines | 1049K | $0 | $0 | Reasoning, Vision |
Showing the top 50 of 259 models. Browse the full directory →
A reasoning model generates an internal chain of thought before producing its final answer, checking intermediate steps along the way. This makes it far more reliable at math, logic, planning, and debugging than a model that answers in one pass.
Use reasoning for problems with a verifiable right answer: math, code that must compile, data analysis, tricky logic. For casual chat, brainstorming, or writing, a standard model is faster and cheaper with no quality loss.
The thinking step generates additional tokens, so a reasoning response consumes more of your usage allowance than a standard reply from the same model. Many providers also price their dedicated reasoning models at a premium tier.
On CoreAI, reasoning-capable models currently come from Tencent, Inclusionai, Qwen, Z.AI, Meta and others. The list refreshes automatically as providers ship new thinking models.
Chat with GPT-5, Claude, Gemini and hundreds more — all in one app.