Cheapest models
Ranked by blended API price (75% input + 25% output, USD per 1M tokens). Free promotional listings excluded.
Ranked by blended API price (75% input + 25% output, USD per 1M tokens). Free promotional listings excluded. Source: OpenRouter. Variants (reasoning effort, batch) are folded into one row.
| # | Model | Capability | Reasoning | Coding | Context | $/M | Weights | Released |
|---|---|---|---|---|---|---|---|---|
| 51 | UI-TARS 7BByteDance | — | — | — | 128K | $0.13 | Open | 22 Jul 2025 |
| 52 | Hy-MT2-30B-A3BTencent | — | — | — | 8K | $0.13 | Open | 20 Aug 2026 |
| 53 | Hy-MT2-7BTencent | — | — | — | 8K | $0.13 | Open | 19 Aug 2026 |
| 54 | Qwen3 32BAlibaba (Qwen) | 138.5 | 65.7 | — | 131K | $0.13 | Open | 29 Apr 2025 |
| 55 | GPT-4o-minibatchOpenAI · +1 variant | — | — | — | 128K | $0.13 | — | 18 Jul 2024 |
| 56 | gpt-oss-safeguard-20bOpenAI | — | — | — | 131K | $0.13 | Open | 29 Oct 2025 |
| 57 | Mistral Small 4batchMistral AI · +1 variant | — | — | — | 262K | $0.13 | Open | 16 Mar 2026 |
| 58 | Seed 1.6 FlashByteDance | — | — | — | 262K | $0.13 | — | 23 Dec 2025 |
| 59 | Mistral Small 3.2 24BMistral AI | — | — | — | 256K | $0.13 | Open | 20 Jun 2025 |
| 60 | Gemma 4 26B A4BGoogle | 141.8 | 73.2 | — | 262K | $0.14 | Open | 2 Apr 2026 |
| 61 | GLM 4.7 FlashZ.ai (Zhipu AI) | — | 60.5 | — | 200K | $0.15 | Open | 19 Jan 2026 |
| 62 | Qwen3 14BAlibaba (Qwen) | 138.2 | 63.8 | — | 131K | $0.15 | Open | 29 Apr 2025 |
| 63 | Llama 4 ScoutMeta | 129.6 | 51.8 | — | 1.31M | $0.15 | Open | 5 Apr 2025 |
| 64 | Step 3.5 FlashStepFun | — | — | — | 262K | $0.15 | Open | 29 Jan 2026 |
| 65 | Voxtral Small 24B 2507Mistral AI | — | — | — | 33K | $0.15 | Open | 30 Oct 2025 |
| 66 | Gemma 4 31BGoogle | 142.7 | 75.8 | — | 262K | $0.15 | Open | 2 Apr 2026 |
| 67 | Qwen3 235B A22B Instruct 2507Alibaba (Qwen) | — | — | — | 262K | $0.15 | Open | 21 Jul 2025 |
| 68 | Llama 3.3 70B InstructMeta | — | — | — | 131K | $0.15 | Open | 6 Dec 2024 |
| 69 | Solar Pro 4Upstage | — | — | — | 524K | $0.16 | — | 10 Aug 2026 |
| 70 | DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant | — | — | — | 1.05M | $0.17 | Open | 10 Sep 2026 |
| 71 | Gemma 3 27BGoogle | 130.0 | 47.7 | — | 131K | $0.17 | Open | 12 Mar 2025 |
| 72 | Nemotron 3 SuperNVIDIA | — | — | — | 262K | $0.17 | Open | 11 Mar 2026 |
| 73 | DeepSeek V4 Flash 0423DeepSeek | 146.1 | — | — | 1.05M | $0.17 | Open | 24 Apr 2026 |
| 74 | MiMo-V2.5Xiaomi | — | — | — | 1.05M | $0.17 | Open | 22 Apr 2026 |
| 75 | MiMo-V2.6-FlashNEWXiaomi | — | — | — | 1.05M | $0.17 | Open | 21 Sep 2026 |
| 76 | Seed-2.0-MiniByteDance | — | — | — | 262K | $0.17 | — | 26 Feb 2026 |
| 77 | Llama Guard 4 12BMeta | — | — | — | 164K | $0.18 | Open | 30 Apr 2025 |
| 78 | Ternary Bonsai 2 27BNEWPrismML | — | — | — | 262K | $0.18 | Open | 18 Sep 2026 |
| 79 | Qwen3 VL 32B InstructAlibaba (Qwen) | — | — | — | 131K | $0.18 | Open | 23 Oct 2025 |
| 80 | Ministral 3 14B 2512Mistral AI | — | — | — | 262K | $0.20 | Open | 2 Dec 2025 |
| 81 | Nemotron 3.5 Content SafetyNVIDIA | — | — | — | 131K | $0.20 | Open | 4 Jun 2026 |
| 82 | Qwen3 8BAlibaba (Qwen) | 136.2 | 56.8 | — | 131K | $0.20 | Open | 28 Apr 2025 |
| 83 | Qwen3 VL 8B InstructAlibaba (Qwen) | — | — | — | 262K | $0.20 | Open | 14 Oct 2025 |
| 84 | Codestral 2508batchMistral AI · +1 variant | — | — | — | 256K | $0.23 | — | 1 Aug 2025 |
| 85 | GPT-5.6 LunabatchOpenAI · +1 variant | — | — | — | 1.05M | $0.23 | — | 9 Jul 2026 |
| 86 | GPT-5.6 Luna ProbatchOpenAI · +1 variant | — | — | — | 1.05M | $0.23 | — | 9 Jul 2026 |
| 87 | Qwen3 30B A3BAlibaba (Qwen) | 136.2 | 61.7 | — | 131K | $0.23 | Open | 29 Apr 2025 |
| 88 | Qwen3.8 FlashAlibaba (Qwen) | — | — | — | 1M | $0.23 | Open | 26 Aug 2026 |
| 89 | Qwen3.8 Omni FlashNEWAlibaba (Qwen) | — | — | — | 1M | $0.23 | — | 21 Sep 2026 |
| 90 | Hy3Tencent | — | — | — | 262K | $0.23 | Open | 6 Jul 2026 |
| 91 | GPT-5.4 NanobatchOpenAI · +1 variant | — | — | — | 400K | $0.23 | — | 17 Mar 2026 |
| 92 | Hunyuan A13B InstructTencent | — | — | — | 131K | $0.25 | Open | 8 Jul 2025 |
| 93 | Command R (08-2024)Cohere | — | — | — | 128K | $0.26 | — | 30 Aug 2024 |
| 94 | GPT-4o-mini (2024-07-18)OpenAI | — | — | — | 128K | $0.26 | — | 18 Jul 2024 |
| 95 | Qwen3 VL 30B A3B InstructAlibaba (Qwen) | — | — | — | 262K | $0.26 | Open | 6 Oct 2025 |
| 96 | Solar Pro 3Upstage | — | — | — | 131K | $0.26 | — | 27 Jan 2026 |
| 97 | Gemini 3.1 Flash LitebatchGoogle · +1 variant | — | — | — | 1.05M | $0.28 | — | 7 May 2026 |
| 98 | Hy3 previewTencent | — | — | — | 262K | $0.28 | Open | 22 Apr 2026 |
| 99 | Qwen3 Coder NextAlibaba (Qwen) | — | — | — | 262K | $0.29 | Open | 4 Feb 2026 |
| 100 | SabaMistral AI | — | — | — | 33K | $0.30 | — | 17 Feb 2025 |
— means no published score from that source yet · click a model for every benchmark with its source
New - awaiting independent evaluation
All new models →- Claude Sonnet 5.5Anthropic · 28 Sep 2026 · AA 56 · 1M · $4.00/M
- Qwen3.8 Max PrimeAlibaba (Qwen) · 23 Sep 2026 · 1M · $6.00/M
- GPT-6 SolOpenAI · 22 Sep 2026 · AA 47.5 · 1.05M · $4.00/M
- GPT-6 LunaOpenAI · 22 Sep 2026 · AA 37.3 · 1.05M · $0.20/M
- GPT-6 Sol ProOpenAI · 22 Sep 2026 · 1.05M · $4.00/M
- GPT-6 Luna ProOpenAI · 22 Sep 2026 · 1.05M · $0.20/M
- Claude Opus 5.5Anthropic · 22 Sep 2026 · AA 57.6 · 1M · $8.00/M
- Grok 4.7xAI · 21 Sep 2026 · AA 46.4 · 500K · $3.00/M
Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.
Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research