by price
Cheapest AI models (paid)
Lowest cost-per-million-tokens across the catalog. Excludes free models.
What this is
Ranked by capability match + real benchmark scores + live pricing, daily-refreshed. Benchmark sources: Aider Polyglot (coding) and Artificial Analysis Intelligence Index (overall, coding, agentic). Full methodology →
Download this catalog: CSV · JSON (regenerated 2026-09-27), or query it live via the API.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Mistral: Mistral Nemomistralai/mistral-nemo | — | $0.019 | $0.030 | 131,072 | Details → |
| 2 | inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | 39 1/5 | $0.021 | $0.062 | 262,144 | Details → |
| 3 | inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash | 39 1/5 | $0.021 | $0.063 | 262,144 | Details → |
| 4 | Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | — | $0.040 | $0.050 | 8,192 | Details → |
| 5 | OpenAI: gpt-oss-20bopenai/gpt-oss-20b | 24 2/5 | $0.018 | $0.090 | 131,072 | Details → |
| 6 | IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro | — | $0.017 | $0.112 | 131,000 | Details → |
| 7 | Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | 6 1/5 | $0.050 | $0.080 | 131,072 | Details → |
| 8 | Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | 29 1/5 | $0.050 | $0.080 | 32,768 | Details → |
| 9 | OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch | 24 2/5 | $0.024 | $0.112 | 131,072 | Details → |
| 10 | DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | — | $0.047 | $0.094 | 1,048,576 | Details → |
| 11 | Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batch | — | $0.075 | $0.075 | 262,144 | Details → |
| 12 | Google: Gemma 3 4Bgoogle/gemma-3-4b-it | 21 2/5 | $0.050 | $0.100 | 131,072 | Details → |
| 13 | Qwen: Qwen3.7 Flashqwen/qwen3.7-flash | — | $0.030 | $0.130 | 1,000,000 | Details → |
| 14 | OpenAI: gpt-oss-120b (batch)openai/gpt-oss-120b:batch | 39 3/5 | $0.030 | $0.136 | 131,072 | Details → |
| 15 | Amazon: Nova Micro 1.0amazon/nova-micro-v1 | — | $0.035 | $0.140 | 128,000 | Details → |
| 16 | Poolside: Laguna XS 2.1poolside/laguna-xs-2.1 | — | $0.060 | $0.120 | 262,144 | Details → |
| 17 | Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbo | — | $0.030 | $0.150 | 128,000 | Details → |
| 18 | Z.ai: GLM Flash Latest~z-ai/glm-flash-latest | — | $0.045 | $0.140 | 1,310,720 | Details → |
| 19 | Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash | 71 1/5 | $0.045 | $0.140 | 1,310,720 | Details → |
| 20 | Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024 | — | $0.037 | $0.150 | 128,000 | Details → |
| 21 | Inception: Mercury 2.5inception/mercury-2.5 | 16 1/5 | $0.040 | $0.150 | 260,000 | Details → |
| 22 | MythoMax 13Bgryphe/mythomax-l2-13b | — | $0.080 | $0.110 | 8,192 | Details → |
| 23 | Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | — | $0.100 | $0.100 | 131,072 | Details → |
| 24 | Google: Gemma 3 12Bgoogle/gemma-3-12b-it | 0 1/5 | $0.050 | $0.150 | 131,072 | Details → |
| 25 | Reka Edgerekaai/reka-edge | — | $0.100 | $0.100 | 16,384 | Details → |
| 26 | Microsoft: Phi 4microsoft/phi-4 | 4 1/5 | $0.070 | $0.140 | 16,384 | Details → |
| 27 | Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b | — | $0.044 | $0.177 | 8,192 | Details → |
| 28 | OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batch | 17 1/5 | $0.025 | $0.200 | 400,000 | Details → |
| 29 | Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct | 1 2/5 | $0.027 | $0.201 | 60,000 | Details → |
| 30 | inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin | 35 1/5 | $0.060 | $0.180 | 262,144 | Details → |
| 31 | Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | 18 1/5 | $0.100 | $0.150 | 262,144 | Details → |
| 32 | Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batch | 5 1/5 | $0.050 | $0.200 | 1,048,576 | Details → |
| 33 | OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | 17 3/5 | $0.050 | $0.200 | 1,047,576 | Details → |
| 34 | Upstage: Solar Mini 4 NEWupstage/solar-mini4 | — | $0.050 | $0.200 | 524,288 | Details → |
| 35 | NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | 6 1/5 | $0.050 | $0.200 | 262,144 | Details → |
| 36 | Z.ai: GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batch | 71 1/5 | $0.060 | $0.200 | 1,048,576 | Details → |
| 37 | Poolside: Laguna S 2.1poolside/laguna-s-2.1 | — | $0.090 | $0.180 | 1,048,576 | Details → |
| 38 | NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | 17 1/5 | $0.080 | $0.200 | 1,000,000 | Details → |
| 39 | Inference.net: Schematron V2 Smallinference-net/schematron-v2-small | — | $0.050 | $0.230 | 128,000 | Details → |
| 40 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 51 2/5 | $0.068 | $0.225 | 262,144 | Details → |
| 41 | OpenAI: GPT-6 Luna Pro (batch) NEWopenai/gpt-6-luna-pro:batch | — | $0.050 | $0.250 | 1,050,000 | Details → |
| 42 | OpenAI: GPT-6 Luna (batch) NEWopenai/gpt-6-luna:batch | 62 1/5 | $0.050 | $0.250 | 1,050,000 | Details → |
| 43 | Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | — | $0.150 | $0.150 | 262,144 | Details → |
| 44 | Amazon: Nova Lite 1.0amazon/nova-lite-v1 | — | $0.060 | $0.240 | 300,000 | Details → |
| 45 | Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor | — | $0.100 | $0.200 | 1,048,576 | Details → |
| 46 | Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor | — | $0.100 | $0.200 | 1,048,576 | Details → |
| 47 | ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b | — | $0.100 | $0.200 | 128,000 | Details → |
| 48 | Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | — | $0.100 | $0.200 | 32,768 | Details → |
| 49 | Reka Flash 3rekaai/reka-flash-3 | 4 1/5 | $0.100 | $0.200 | 65,536 | Details → |
| 50 | IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b | 14 1/5 | $0.060 | $0.250 | 131,072 | Details → |