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 |
|---|---|---|---|---|---|---|---|---|
| 1 | Mistral NemoMistral AI | 118.6 | 29.9 | — | 131K | $0.022 | Open | 18 Jul 2024 |
| 2 | Ling 3.0 Flash VLNEWinclusionAI (Ant Group) | — | — | — | 262K | $0.031 | Open | 10 Sep 2026 |
| 3 | Ling 3.0 FlashinclusionAI (Ant Group) | — | — | — | 262K | $0.032 | Open | 23 Jul 2026 |
| 4 | gpt-oss-20bOpenAI · +1 variant | 137.8 | 60.8 | — | 131K | $0.036 | Open | 5 Aug 2025 |
| 5 | Granite 4.0 MicroIBM | — | 28.3 | — | 131K | $0.041 | Open | 20 Oct 2025 |
| 6 | Llama 3 8B LunarisSao10K | — | — | — | 8K | $0.043 | Open | 13 Aug 2024 |
| 7 | Nex-N2.5-MiniNEWNex AGI | — | — | — | 262K | $0.044 | Open | 8 Sep 2026 |
| 8 | Qwen3.7 FlashAlibaba (Qwen) | 144.6 | 82.3 | — | 1M | $0.055 | Closed | 27 Jul 2026 |
| 9 | gpt-oss-120bbatchOpenAI · +1 variant | — | — | — | 131K | $0.056 | Open | 5 Aug 2025 |
| 10 | Mistral Small 3Mistral AI | 127.1 | 47.3 | — | 33K | $0.058 | Open | 30 Jan 2025 |
| 11 | Llama 3.1 8B InstructMeta | — | — | — | 131K | $0.058 | Open | 23 Jul 2024 |
| 12 | Schematron V2 TurboNEWInference.net | — | — | — | 128K | $0.060 | Open | 12 Sep 2026 |
| 13 | Nova Micro 1.0Amazon | — | — | — | 128K | $0.061 | — | 5 Dec 2024 |
| 14 | Gemma 3 4BGoogle | 116.0 | 23.2 | — | 131K | $0.063 | Open | 12 Mar 2025 |
| 15 | Command R7B (12-2024)Cohere | — | — | — | 128K | $0.066 | — | 14 Dec 2024 |
| 16 | Mercury 2.5NEWInception Labs | — | — | — | 260K | $0.068 | — | 8 Sep 2026 |
| 17 | GPT-5 NanobatchOpenAI · +1 variant | — | — | — | 400K | $0.069 | — | 7 Aug 2025 |
| 18 | Llama 3.2 1B InstructMeta | — | — | — | 60K | $0.070 | Open | 25 Sep 2024 |
| 19 | Gemma 3 12BGoogle | 123.5 | 39.5 | — | 131K | $0.075 | Open | 12 Mar 2025 |
| 20 | Laguna XS 2.1Poolside | — | — | — | 262K | $0.075 | Open | 2 Jul 2026 |
| 21 | Ministral 3 8B 2512batchMistral AI · +1 variant | — | — | — | 262K | $0.075 | Open | 2 Dec 2025 |
| 22 | Hy-MT2-1.8BTencent | — | — | — | 8K | $0.077 | Open | 20 Aug 2026 |
| 23 | Qwen3 30B A3B Instruct 2507Alibaba (Qwen) | — | — | — | 262K | $0.084 | Open | 29 Jul 2025 |
| 24 | Nemotron 3.5 LightningNVIDIA | — | — | — | 1M | $0.085 | Open | 11 Aug 2026 |
| 25 | Phi 4Microsoft | 130.4 | 56.1 | — | 16K | $0.087 | Open | 12 Dec 2024 |
| 26 | Gemini 2.5 Flash LitebatchGoogle · +1 variant | — | — | — | 1.05M | $0.087 | — | 22 Jul 2025 |
| 27 | GPT-4.1 NanobatchOpenAI · +1 variant | — | — | — | 1.05M | $0.087 | — | 14 Apr 2025 |
| 28 | MythoMax 13Bgryphe | — | — | — | 8K | $0.087 | Open | 2 Jul 2023 |
| 29 | Nemotron 3 Nano 30B A3BNVIDIA | — | — | — | 262K | $0.087 | Open | 14 Dec 2025 |
| 30 | Solar Mini 4NEWUpstage | — | — | — | 524K | $0.087 | — | 23 Sep 2026 |
| 31 | Ling 3.0 Flash FininclusionAI (Ant Group) | — | — | — | 262K | $0.090 | — | 27 Aug 2026 |
| 32 | DeepSeek V4 Flash 0731DeepSeek | 154.5 | 91.0 | — | 1.31M | $0.093 | Open | 31 Jul 2026 |
| 33 | GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant | — | — | — | 1.05M | $0.095 | Open | 26 Aug 2026 |
| 34 | Schematron V2 SmallNEWInference.net | — | — | — | 128K | $0.095 | Open | 12 Sep 2026 |
| 35 | GPT-6 LunaNEWbatchOpenAI · +1 variant | — | — | — | 1.05M | $0.10 | — | 22 Sep 2026 |
| 36 | GPT-6 Luna ProNEWbatchOpenAI · +1 variant | — | — | — | 1.05M | $0.10 | — | 22 Sep 2026 |
| 37 | Ministral 3 3B 2512Mistral AI | — | — | — | 131K | $0.10 | Open | 2 Dec 2025 |
| 38 | Reka EdgeReka AI | — | — | — | 16K | $0.10 | Open | 20 Mar 2026 |
| 39 | Nova Lite 1.0Amazon | — | — | — | 300K | $0.10 | — | 5 Dec 2024 |
| 40 | Granite 4.2 8BNEWIBM | — | — | — | 131K | $0.11 | Open | 31 Aug 2026 |
| 41 | Qwen3.5-9BAlibaba (Qwen) | 139.4 | 79.0 | — | 262K | $0.11 | Open | 24 Feb 2026 |
| 42 | Laguna S 2.1Poolside | — | — | — | 1.05M | $0.11 | Open | 21 Jul 2026 |
| 43 | Qwen3.5-FlashAlibaba (Qwen) | — | 82.3 | — | 1M | $0.11 | — | 25 Feb 2026 |
| 44 | Nex-N2.5-ProNEWNex AGI | — | — | — | 262K | $0.12 | Open | 8 Sep 2026 |
| 45 | Llama 3.2 3B InstructMeta | — | — | — | 131K | $0.12 | Open | 25 Sep 2024 |
| 46 | Qwen3 Coder 30B A3B InstructAlibaba (Qwen) | — | — | — | 262K | $0.12 | Open | 31 Jul 2025 |
| 47 | Muse Spark 1.2 ContributorMeta | — | — | — | 1.05M | $0.13 | — | 21 Aug 2026 |
| 48 | Muse Spark 1.3 ContributorNEWMeta | — | — | — | 1.05M | $0.13 | — | 2 Sep 2026 |
| 49 | Qwen2.5 7B InstructAlibaba (Qwen) | — | — | — | 33K | $0.13 | Open | 16 Oct 2024 |
| 50 | Reka Flash 3Reka AI | — | — | — | 66K | $0.13 | Open | 12 Mar 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