LLM List: AI models compared
Browse all LLMs in one comprehensive list: 1,781 large language models and AI models across 214 API providers. Compare token prices, context windows, capabilities, benchmark scores, open-weight availability, and local hardware requirements. Updated every six hours.
Explore the LLM benchmark leaderboard · How prices, benchmarks and model identities are calculated
- Coding Router Low — 1M context; $0.14 input / $0.28 output per 1M tokens
- Coding Router Max — 1M context; $5 input / $30 output per 1M tokens
- Coding Router Medium — 1M context; $0.14 input / $0.28 output per 1M tokens
- Coding Xiaomi MiMo-V2.5 — 1.05M context; $0.08 input / $0.4 output per 1M tokens
- Coding Xiaomi MiMo-V2.5-Pro — 1.05M context; $0.2 input / $0.6 output per 1M tokens
- Cogito v1 Preview Qwen 32B — 128K context; $1.8 input / $1.8 output per 1M tokens
- Cogito v2.1 671B — 164K context; $1.25 input / $1.25 output per 1M tokens
- Cohere Command A (08/2025) — 256K context; $2.5 input / $10 output per 1M tokens
- Cohere Rerank 3.5 by Cohere — 4K context; not published input / not published output per 1M tokens
- Command A by Cohere — 256K context; $2.5 input / $10 output per 1M tokens
- Command A 03-2025 by Cohere — 256K context; $2.5 input / $10 output per 1M tokens
- Command A Plus by Cohere — 128K context; $2.5 input / $10 output per 1M tokens
- Command A Reasoning — 256K context; $0.63 input / $5.05 output per 1M tokens
- Command A Translate — 8K context; $2.5 input / $10 output per 1M tokens
- Command A Vision — 128K context; $2.5 input / $10 output per 1M tokens
- Command R by Cohere — 128K context; $0.15 input / $0.6 output per 1M tokens
- Command R 08-2024 by Cohere — 128K context; $0.15 input / $0.6 output per 1M tokens
- Command R+ by Cohere — 128K context; $2.5 input / $10 output per 1M tokens
- Command R+ 08-2024 by Cohere — 128K context; $2.5 input / $10 output per 1M tokens
- Command R7B by Cohere — 128K context; $0.037 input / $0.15 output per 1M tokens
- Command R7B 12-2024 by Cohere — 128K context; $0.037 input / $0.15 output per 1M tokens
- Command R7B Arabic — 128K context; $0.037 input / $0.15 output per 1M tokens
- Compound — 131K context; not published input / not published output per 1M tokens
- Compound Mini — 131K context; not published input / not published output per 1M tokens
- Cosmos Reason2 8B — 131K context; free input / free output per 1M tokens
- cosmos3-super-reasoner — 256K context; $0.099 input / $0.296 output per 1M tokens
- Custom Model — 128K context; free input / free output per 1M tokens
- Cydonia 24B V4.1 by TheDrummer — 131K context; $0.3 input / $0.5 output per 1M tokens
- Dark Soul — 262K context; $0.12 input / $0.38 output per 1M tokens
- DarkIdol — 262K context; $0.1 input / $0.45 output per 1M tokens
- Deep Research Max Preview (Apr-21-2026) — 131K context; $2 input / $12 output per 1M tokens
- Deep Research Preview (Apr-21-2026) — 131K context; $2 input / $12 output per 1M tokens
- DeepClaude — 128K context; $3 input / $15 output per 1M tokens
- Deepseek 3.2 — 164K context; $0.25 input / $0.8 output per 1M tokens
- DeepSeek Chat by DeepSeek — 1M context; $0.147 input / $0.295 output per 1M tokens
- DeepSeek Chat 0324 — 128K context; $0.2 input / $0.77 output per 1M tokens
- DeepSeek Chat V3.1 by DeepSeek — 164K context; $0.2 input / $0.8 output per 1M tokens
- DeepSeek Latest by DeepSeek — 1.05M context; $1.1 input / $2.5 output per 1M tokens
- DeepSeek OCR by DeepSeek — 8K context; $0.03 input / $0.03 output per 1M tokens
- DeepSeek OCR 2 by DeepSeek — 8K context; $0.03 input / $0.03 output per 1M tokens
- Deepseek Prover V2 671B by DeepSeek — 16K context; $0.7 input / $2.5 output per 1M tokens
- DeepSeek R1 (Turbo) by DeepSeek — 64K context; $0.7 input / $2.5 output per 1M tokens
- DeepSeek R1 0528 by DeepSeek — 164K context; $0.4 input / $1.7 output per 1M tokens
- DeepSeek R1 0528 Qwen3 8B by DeepSeek — 128K context; $0.06 input / $0.09 output per 1M tokens
- Deepseek R1 Cheaper — 128K context; $0.4 input / $1.7 output per 1M tokens
- DeepSeek R1 Distill Llama 70B by DeepSeek — 131K context; $0.03 input / $0.13 output per 1M tokens
- DeepSeek R1 Distill Llama 8B by DeepSeek — 33K context; free input / free output per 1M tokens
- DeepSeek R1 Distill Qwen 1.5B by DeepSeek — 33K context; free input / free output per 1M tokens
- DeepSeek R1 Distill Qwen 14B by DeepSeek — 33K context; $0.15 input / $0.15 output per 1M tokens
- DeepSeek R1 Distill Qwen 32B by DeepSeek — 8K context; $0.3 input / $0.3 output per 1M tokens
- DeepSeek R1 Distill Qwen 7B — 33K context; $0.072 input / $0.144 output per 1M tokens
- DeepSeek R1 Fast — 128K context; $5 input / $6.99 output per 1M tokens
- DeepSeek R1 Llama 70B Abliterated by Huihui AI — 16K context; $0.7 input / $0.7 output per 1M tokens
- DeepSeek R1 Qwen Abliterated by Huihui AI — 16K context; $1.4 input / $1.4 output per 1M tokens
- DeepSeek Reasoner by DeepSeek — 1M context; $0.147 input / $0.295 output per 1M tokens
- DeepSeek TNG R1T2 Chimera — 13K context; $0.3 input / $1.2 output per 1M tokens
- DeepSeek V3 by DeepSeek — 164K context; $0.32 input / $0.89 output per 1M tokens
- DeepSeek V3 (Turbo) by DeepSeek — 64K context; $0.4 input / $1.3 output per 1M tokens
- DeepSeek V3 0324 by DeepSeek — 164K context; $0.2 input / $0.8 output per 1M tokens
- DeepSeek V3.1 by DeepSeek — 164K context; $0.2 input / $0.7 output per 1M tokens
- DeepSeek V3.1 Terminus by DeepSeek — 128K context; $0.25 input / $0.7 output per 1M tokens
- DeepSeek V3.1 Terminus (Thinking) by DeepSeek — 128K context; $0.25 input / $0.7 output per 1M tokens
- DeepSeek V3.1 Thinking by DeepSeek — 128K context; $0.2 input / $0.7 output per 1M tokens
- DeepSeek V3.2 by DeepSeek — 164K context; $0.18 input / $0.35 output per 1M tokens
- DeepSeek V3.2 Exp by DeepSeek — 164K context; $0.22 input / $0.33 output per 1M tokens
- DeepSeek V3.2 Exp Thinking by DeepSeek — 164K context; $0.28 input / $0.42 output per 1M tokens
- DeepSeek V3.2 TEE by DeepSeek — 164K context; $0.5 input / $1 output per 1M tokens
- DeepSeek V3.2 Thinking by DeepSeek — 128K context; $0.28 input / $0.42 output per 1M tokens
- DeepSeek V3/Chat Cheaper — 128K context; $0.1 input / $0.425 output per 1M tokens
- DeepSeek V3/Deepseek Chat — 128K context; $0.1 input / $0.425 output per 1M tokens
- DeepSeek V4 Flash by DeepSeek — 1M context; $0.051 input / $0.104 output per 1M tokens
- DeepSeek V4 Flash (Thinking) by DeepSeek — 1.05M context; $0.14 input / $0.28 output per 1M tokens
- DeepSeek V4 Flash 0423 — 1M context; $0.138 input / $0.275 output per 1M tokens
- DeepSeek V4 Flash 0731 by DeepSeek — 1M context; $0.03 input / $0.1 output per 1M tokens
- DeepSeek V4 Flash 0731 (Thinking) by DeepSeek — 1M context; $0.14 input / $0.28 output per 1M tokens
- DeepSeek V4 Flash 0731 Fast — 1M context; $0.35 input / $0.7 output per 1M tokens
- DeepSeek V4 Flash 0731 TEE by DeepSeek — 1.05M context; $0.44 input / $1.32 output per 1M tokens
- DeepSeek V4 Flash Flex — 1.05M context; $0.091 input / $0.182 output per 1M tokens
- DeepSeek V4 Flash Free — 2K context; free input / free output per 1M tokens
- DeepSeek V4 Flash Latest by DeepSeek — 1.05M context; $0.05 input / $0.16 output per 1M tokens
- DeepSeek V4 Flash TEE — 1.05M context; $0.2 input / $0.4 output per 1M tokens
- DeepSeek V4 Flash Vision Exp by DeepSeek — 1M context; $0.14 input / $0.28 output per 1M tokens
- DeepSeek V4 Pro by DeepSeek — 1M context; $0.348 input / $0.696 output per 1M tokens
- DeepSeek V4 Pro (Thinking) by DeepSeek — 1.05M context; $1.1 input / $2.2 output per 1M tokens
- DeepSeek V4 Pro 0423 by DeepSeek — 1M context; $1.65 input / $3.3 output per 1M tokens
- DeepSeek V4 Pro 0813 by DeepSeek — 1.05M context; $0.35 input / $0.8 output per 1M tokens
- DeepSeek V4 Pro 0813 Thinking by DeepSeek — 1.05M context; $1.1 input / $2.5 output per 1M tokens
- deepseek-ai/DeepSeek-OCR by DeepSeek — 8K context; free input / free output per 1M tokens
- deepseek-ai/DeepSeek-R1 by DeepSeek — 164K context; $0.5 input / $2.18 output per 1M tokens
- deepseek-ai/DeepSeek-V3 by DeepSeek — 164K context; $0.25 input / $1 output per 1M tokens
- deepseek-ai/DeepSeek-V3.1 by DeepSeek — 164K context; $0.27 input / $1 output per 1M tokens
- deepseek-ai/DeepSeek-V3.1-Terminus by DeepSeek — 164K context; $0.27 input / $1 output per 1M tokens
- deepseek-ai/DeepSeek-V3.2 by DeepSeek — 164K context; $0.27 input / $0.42 output per 1M tokens
- deepseek-ai/DeepSeek-V3.2-Exp by DeepSeek — 164K context; $0.27 input / $0.41 output per 1M tokens
- deepseek-ai/DeepSeek-V4-Pro by DeepSeek — 1.05M context; $1.74 input / $3.48 output per 1M tokens
- Deepseek-Math-V2 by DeepSeek — 16K context; not published input / not published output per 1M tokens
- DeepSeek-R1 by DeepSeek — 128K context; $0.4 input / $1.7 output per 1M tokens
- DeepSeek-V3.2 (Non-thinking Mode) by DeepSeek — 128K context; $0.28 input / $0.42 output per 1M tokens
- DeepSeek-V3.2-Speciale by DeepSeek — 128K context; $0.58 input / $1.68 output per 1M tokens
- deepseek-v4-flash-20260731 — not published context; not published input / not published output per 1M tokens