Model rankings
Cost leaderboard
Ranked by documented input price per million tokens, lowest first.
Top models
Cost ranking
| Rank | Model | Creator | Input / 1M | Context | Last verified |
|---|---|---|---|---|---|
| 1 | Whisper Large v3 Turbo | OpenAI | $0.002 | 448 | Jul 30, 2026 |
| 2 | Whisper 3 Large | OpenAI | $0.002 | 448 | Jul 30, 2026 |
| 3 | inclusionAI: Ling-2.6-flash | Inclusionai | $0.01 | 262.144K | Jul 30, 2026 |
| 4 | IBM: Granite 4.0 Micro | IBM | $0.017 | 131K | Jul 30, 2026 |
| 5 | Mistral: Mistral Nemo | Mistral AI | $0.019 | 131.072K | Jul 30, 2026 |
| 6 | Sarvam 30B | Sarvam | $0.02 | 128K | Jul 30, 2026 |
| 7 | Nex AGI: Nex-N2-Mini | Nex Agi | $0.025 | 262.144K | Jul 30, 2026 |
| 8 | OpenAI: GPT-5 Nano (batch) | OpenAI | $0.025 | 400K | Jul 30, 2026 |
| 9 | Meta: Llama 3.2 1B Instruct | Meta | $0.027 | 60K | Jul 30, 2026 |
| 10 | GPT OSS 120B | OpenAI | $0.03 | 131.072K | Jul 30, 2026 |
| 11 | GPT OSS 20B | OpenAI | $0.03 | 131.072K | Jul 30, 2026 |
| 12 | Qwen: Qwen3.7 Flash | Alibaba Qwen | $0.03 | 1M | Jul 30, 2026 |
| 13 | Amazon: Nova Micro 1.0 | Amazon | $0.035 | 128K | Jul 30, 2026 |
| 14 | Command R7B | Cohere | $0.037 | 128K | Jul 30, 2026 |
| 15 | Command R7B Arabic | Cohere | $0.037 | 128K | Jul 30, 2026 |
| 16 | Sao10K: Llama 3 8B Lunaris | Sao10K | $0.04 | 8.192K | Jul 30, 2026 |
| 17 | GLM-4.7-Flash | Zhipu AI | $0.04 | 200K | Jul 30, 2026 |
| 18 | Nemotron Nano 9B v2 | NVIDIA | $0.04 | 131.072K | Jul 30, 2026 |
| 19 | Sarvam 105B | Sarvam | $0.04 | 131.072K | Jul 30, 2026 |
| 20 | Qwen3.5 9B | Alibaba Qwen | $0.04 | 262.144K | Jul 30, 2026 |
| 21 | Qwen: Qwen3 30B A3B Instruct 2507 | Alibaba Qwen | $0.048 | 128K | Jul 30, 2026 |
| 22 | IBM: Granite 4.1 8B | IBM | $0.05 | 131.072K | Jul 30, 2026 |
| 23 | Google: Gemma 3 4B | $0.05 | 131.072K | Jul 30, 2026 | |
| 24 | Google: Gemma 3 12B | $0.05 | 131.072K | Jul 30, 2026 | |
| 25 | Mistral: Mistral Small 3 | Mistral AI | $0.05 | 32.768K | Jul 30, 2026 |
| 26 | Meta: Llama 3.2 3B Instruct | Meta | $0.05 | 131.072K | Jul 30, 2026 |
| 27 | Meta: Llama 3.1 8B Instruct | Meta | $0.05 | 131.072K | Jul 30, 2026 |
| 28 | Google: Gemini 2.5 Flash Lite (batch) | $0.05 | 1.04858M | Jul 30, 2026 | |
| 29 | Nemotron 3 Nano 30B A3B | NVIDIA | $0.05 | 262.144K | Jul 30, 2026 |
| 30 | GPT-5 Nano | OpenAI | $0.05 | 400K | Jul 30, 2026 |
| 31 | Qwen Flash | Alibaba Qwen | $0.05 | 1M | Jul 30, 2026 |
| 32 | Qwen Turbo | Alibaba Qwen | $0.05 | 1M | Jul 30, 2026 |
| 33 | Laguna XS 2.1 | Poolside | $0.06 | 262.144K | Jul 30, 2026 |
| 34 | Gemma 4 26B A4B IT | $0.06 | 262.144K | Jul 30, 2026 | |
| 35 | Z.ai: GLM 4.7 Flash | Z Ai | $0.06 | 202.752K | Jul 30, 2026 |
| 36 | Google: Gemma 3n 4B | $0.06 | 32.768K | Jul 30, 2026 | |
| 37 | Amazon: Nova Lite 1.0 | Amazon | $0.06 | 300K | Jul 30, 2026 |
| 38 | MythoMax 13B | Gryphe | $0.06 | 4.096K | Jul 30, 2026 |
| 39 | Hy3 preview | Tencent | $0.063 | 256K | Jul 30, 2026 |
| 40 | Qwen: Qwen3.5-Flash | Alibaba Qwen | $0.065 | 1M | Jul 30, 2026 |
| 41 | Qwen: Qwen3 Coder 30B A3B Instruct | Alibaba Qwen | $0.07 | 160K | Jul 30, 2026 |
| 42 | Microsoft: Phi 4 | Microsoft | $0.07 | 16.384K | Jul 30, 2026 |
| 43 | GLM-4.7-FlashX | Zhipu AI | $0.07 | 200K | Jul 30, 2026 |
| 44 | Qwen-Omni Turbo | Alibaba Qwen | $0.07 | 32.768K | Jul 30, 2026 |
| 45 | inclusionAI: Ring-2.6-1T | Inclusionai | $0.075 | 262.144K | Jul 30, 2026 |
| 46 | inclusionAI: Ling-2.6-1T | Inclusionai | $0.075 | 262.144K | Jul 30, 2026 |
| 47 | ByteDance Seed: Seed 1.6 Flash | Bytedance Seed | $0.075 | 262.144K | Jul 30, 2026 |
| 48 | OpenAI: gpt-oss-safeguard-20b | OpenAI | $0.075 | 131.072K | Jul 30, 2026 |
| 49 | Gemini 2.0 Flash-Lite | $0.075 | 1.04858M | Jul 30, 2026 | |
| 50 | Qwen: Qwen3 32B | Alibaba Qwen | $0.08 | 40.96K | Jul 30, 2026 |
| 51 | Google: Gemma 3 27B | $0.08 | 131.072K | Jul 30, 2026 | |
| 52 | Qwen: Qwen3 235B A22B Instruct 2507 | Alibaba Qwen | $0.09 | 262.144K | Jul 30, 2026 |
| 53 | OpenAI: GPT-5.6 Luna Pro | OpenAI | $0.1 | 1.05M | Jul 30, 2026 |
| 54 | Reka Edge | Rekaai | $0.1 | 16.384K | Jul 30, 2026 |
| 55 | Qwen: Qwen3.5-9B | Alibaba Qwen | $0.1 | 262.144K | Jul 30, 2026 |
| 56 | ByteDance Seed: Seed-2.0-Mini | Bytedance Seed | $0.1 | 262.144K | Jul 30, 2026 |
| 57 | Mistral: Ministral 3 3B 2512 | Mistral AI | $0.1 | 131.072K | Jul 30, 2026 |
| 58 | Mistral: Voxtral Small 24B 2507 | Mistral AI | $0.1 | 32K | Jul 30, 2026 |
| 59 | Qwen: Qwen3 Next 80B A3B Instruct | Alibaba Qwen | $0.1 | 262.144K | Jul 30, 2026 |
| 60 | ByteDance: UI-TARS 7B | Bytedance | $0.1 | 128K | Jul 30, 2026 |
| 61 | Mistral: Mistral Small 3.2 24B | Mistral AI | $0.1 | 131.072K | Jul 30, 2026 |
| 62 | Meta: Llama 4 Scout | Meta | $0.1 | 327.68K | Jul 30, 2026 |
| 63 | Reka Flash 3 | Rekaai | $0.1 | 65.536K | Jul 30, 2026 |
| 64 | Qwen: Qwen2.5 7B Instruct | Alibaba Qwen | $0.1 | 32.768K | Jul 30, 2026 |
| 65 | OpenAI: GPT-5.4 Nano (batch) | OpenAI | $0.1 | 400K | Jul 30, 2026 |
| 66 | Gemma 4 31B IT | $0.1 | 262.144K | Jul 30, 2026 | |
| 67 | Step 3.5 Flash | StepFun | $0.1 | 256K | Jul 30, 2026 |
| 68 | Llama 3.3 Nemotron Super 49B v1.5 | NVIDIA | $0.1 | 131.072K | Jul 30, 2026 |
| 69 | Gemini 2.5 Flash-Lite | $0.1 | 1.04858M | Jul 30, 2026 | |
| 70 | GPT-4.1 nano | OpenAI | $0.1 | 1.04758M | Jul 30, 2026 |
| 71 | Devstral Small | Mistral AI | $0.1 | 128K | Jul 30, 2026 |
| 72 | Mistral Small 3.2 | Mistral AI | $0.1 | 128K | Jul 30, 2026 |
| 73 | Gemini 2.0 Flash | $0.1 | 1.04858M | Jul 30, 2026 | |
| 74 | Gemma 4 E2B IT | $0.1 | 131.072K | Jul 30, 2026 | |
| 75 | Step 3.5 Flash 2603 | StepFun | $0.1 | 256K | Jul 30, 2026 |
| 76 | Laguna S 2.1 | Poolside | $0.1 | 1.04858M | Jul 30, 2026 |
| 77 | Qwen: Qwen3 VL 32B Instruct | Alibaba Qwen | $0.104 | 131.072K | Jul 30, 2026 |
| 78 | Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | $0.105 | 256K | Jul 30, 2026 |
| 79 | Qwen: Qwen3 VL 8B Instruct | Alibaba Qwen | $0.117 | 131.072K | Jul 30, 2026 |
| 80 | Qwen: Qwen3 8B | Alibaba Qwen | $0.117 | 131.072K | Jul 30, 2026 |
| 81 | Qwen: Qwen3 Coder Next | Alibaba Qwen | $0.12 | 262.144K | Jul 30, 2026 |
| 82 | Qwen: Qwen3 30B A3B | Alibaba Qwen | $0.12 | 40.96K | Jul 30, 2026 |
| 83 | Llama 4 Maverick 17B Instruct | Meta | $0.124 | 1M | Jul 30, 2026 |
| 84 | Google: Gemini 3.1 Flash Lite (batch) | $0.125 | 1.04858M | Jul 30, 2026 | |
| 85 | OpenAI: GPT-5 Mini (batch) | OpenAI | $0.125 | 400K | Jul 30, 2026 |
| 86 | Nous: Hermes 4 70B | Nousresearch | $0.13 | 131.072K | Jul 30, 2026 |
| 87 | Z.ai: GLM 4.5 Air | Z Ai | $0.13 | 131.072K | Jul 30, 2026 |
| 88 | Meta: Llama 3.3 70B Instruct | Meta | $0.13 | 131.072K | Jul 30, 2026 |
| 89 | Llama-3.3-70B-Instruct | Meta | $0.13 | 128K | Jul 30, 2026 |
| 90 | Hy3 | Tencent | $0.132 | 256K | Jul 30, 2026 |
| 91 | Qwen: Qwen3.6 35B A3B | Alibaba Qwen | $0.14 | 262.144K | Jul 30, 2026 |
| 92 | DeepSeek V4 Flash | DeepSeek | $0.14 | 1M | Jul 30, 2026 |
| 93 | MiMo-V2.5 | Xiaomi | $0.14 | 1.04858M | Jul 30, 2026 |
| 94 | Qwen: Qwen3.5-35B-A3B | Alibaba Qwen | $0.14 | 262.144K | Jul 30, 2026 |
| 95 | GPT-5.2 Codex | OpenAI | $0.14 | 400K | Jul 30, 2026 |
| 96 | Tencent: Hunyuan A13B Instruct | Tencent | $0.14 | 131.072K | Jul 30, 2026 |
| 97 | DeepSeek Chat | DeepSeek | $0.14 | 1M | Jul 30, 2026 |
| 98 | MiMo-V2-Omni | Xiaomi | $0.14 | 262.144K | Jul 30, 2026 |
| 99 | MiMo-V2-Flash | Xiaomi | $0.14 | 262.144K | Jul 30, 2026 |
| 100 | DeepSeek Reasoner | DeepSeek | $0.14 | 1M | Jul 30, 2026 |