Cost & Efficiency
AI Pricing Comparison
Compare input/output token pricing, context windows, cached pricing signals, and source links across public model catalogs.
How to use this dashboard
Compare input/output token pricing, context windows, cached pricing signals, and source links across public model catalogs.
Use the search box to filter records, then sort the table columns to compare providers, models, dates, prices, and capability signals.
AI Pricing Comparison
120 records| Openrouter | Pareto Code Router | -1,000,000 | -1,000,000 | 200000 | — | Other · text |
| Openrouter | Body Builder (beta) | -1,000,000 | -1,000,000 | 128000 | — | Other · text |
| Nvidia | NVIDIA: Nemotron 3 Nano Omni (free) | 0 | 0 | 256000 | — | Other · text, audio, image, video |
| Poolside | Poolside: Laguna XS.2 (free) | 0 | 0 | 131072 | — | Other · text |
| Poolside | Poolside: Laguna M.1 (free) | 0 | 0 | 131072 | — | Other · text |
| Inclusionai | inclusionAI: Ling-2.6-1T (free) | 0 | 0 | 262144 | — | Other · text |
| Tencent | Tencent: Hy3 preview (free) | 0 | 0 | 262144 | — | Other · text |
| Baidu | Baidu: Qianfan-OCR-Fast (free) | 0 | 0 | 65536 | — | Other · image, text |
| Google: Gemma 4 26B A4B (free) | 0 | 0 | 262144 | — | Other · image, text, video | |
| Google: Gemma 4 31B (free) | 0 | 0 | 262144 | — | Other · image, text, video | |
| Google: Lyria 3 Pro Preview | 0 | 0 | 1048576 | — | Other · text, image, audio | |
| Google: Lyria 3 Clip Preview | 0 | 0 | 1048576 | — | Other · text, image, audio | |
| Nvidia | NVIDIA: Nemotron 3 Super (free) | 0 | 0 | 262144 | — | Other · text |
| Minimax | MiniMax: MiniMax M2.5 (free) | 0 | 0 | 196608 | — | Other · text |
| Openrouter | Free Models Router | 0 | 0 | 200000 | — | Other · text, image |
| Liquid | LiquidAI: LFM2.5-1.2B-Thinking (free) | 0 | 0 | 32768 | — | Other · text |
| Liquid | LiquidAI: LFM2.5-1.2B-Instruct (free) | 0 | 0 | 32768 | — | Other · text |
| Nvidia | NVIDIA: Nemotron 3 Nano 30B A3B (free) | 0 | 0 | 256000 | — | Other · text |
| Nvidia | NVIDIA: Nemotron Nano 12B 2 VL (free) | 0 | 0 | 128000 | — | Other · image, text, video |
| Qwen | Qwen: Qwen3 Next 80B A3B Instruct (free) | 0 | 0 | 262144 | — | Qwen · text |
| Nvidia | NVIDIA: Nemotron Nano 9B V2 (free) | 0 | 0 | 128000 | — | Other · text |
| Openai | OpenAI: gpt-oss-120b (free) | 0 | 0 | 131072 | — | GPT · text |
| Openai | OpenAI: gpt-oss-20b (free) | 0 | 0 | 131072 | — | GPT · text |
| Z Ai | Z.ai: GLM 4.5 Air (free) | 0 | 0 | 131072 | — | GLM · text |
| Qwen | Qwen: Qwen3 Coder 480B A35B (free) | 0 | 0 | 262000 | — | Qwen · text |
| Cognitivecomputations | Venice: Uncensored (free) | 0 | 0 | 32768 | — | Mistral · text |
| Google: Gemma 3n 2B (free) | 0 | 0 | 8192 | — | Other · text | |
| Google: Gemma 3n 4B (free) | 0 | 0 | 8192 | — | Other · text | |
| Google: Gemma 3 4B (free) | 0 | 0 | 32768 | — | Other · text, image | |
| Google: Gemma 3 12B (free) | 0 | 0 | 32768 | — | Other · text, image | |
| Google: Gemma 3 27B (free) | 0 | 0 | 131072 | — | Other · text, image | |
| Ibm Granite | IBM: Granite 4.0 Micro | 0.017 | 0.11 | 131000 | — | Other · text |
| Liquid | LiquidAI: LFM2-24B-A2B | 0.03 | 0.12 | 32768 | — | Other · text |
| Openai | OpenAI: gpt-oss-20b | 0.03 | 0.14 | 131072 | — | GPT · text |
| Qwen | Qwen: Qwen-Turbo | 0.0325 | 0.13 | 131072 | 0.0000000065 | Qwen · text |
| Openai | OpenAI: gpt-oss-120b | 0.039 | 0.19 | 131072 | — | GPT · text |
| Nvidia | NVIDIA: Nemotron Nano 9B V2 | 0.04 | 0.16 | 131072 | — | Other · text |
| Google: Gemma 3 4B | 0.04 | 0.08 | 131072 | — | Other · text, image | |
| Google: Gemma 3 12B | 0.04 | 0.13 | 131072 | — | Other · text, image | |
| Arcee Ai | Arcee AI: Trinity Mini | 0.045 | 0.15 | 131072 | — | Other · text |
| Nvidia | NVIDIA: Nemotron 3 Nano 30B A3B | 0.05 | 0.2 | 262144 | — | Other · text |
| Openai | OpenAI: GPT-5 Nano | 0.05 | 0.4 | 400000 | 0.00000001 | GPT · text, image, file |
| Qwen | Qwen: Qwen3 8B | 0.05 | 0.4 | 40960 | 0.00000005 | Qwen · text |
| Mistralai | Mistral: Mistral Small 3 | 0.05 | 0.08 | 32768 | — | Mistral · text |
| Google: Gemma 4 26B A4B | 0.06 | 0.33 | 262144 | — | Other · image, text, video | |
| Z Ai | Z.ai: GLM 4.7 Flash | 0.06 | 0.4 | 202752 | 0.00000001 | GLM · text |
| Google: Gemma 3n 4B | 0.06 | 0.12 | 32768 | — | Other · text | |
| Qwen | Qwen: Qwen3 14B | 0.06 | 0.24 | 40960 | — | Qwen · text |
| Qwen | Qwen: Qwen3.5-Flash | 0.065 | 0.26 | 1000000 | — | Qwen · text, image, video |
| Baidu | Baidu: ERNIE 4.5 21B A3B Thinking | 0.07 | 0.28 | 131072 | — | Other · text |
| Baidu | Baidu: ERNIE 4.5 21B A3B | 0.07 | 0.28 | 120000 | — | Other · text |
| Qwen | Qwen: Qwen3 Coder 30B A3B Instruct | 0.07 | 0.27 | 160000 | — | Qwen · text |
| Qwen | Qwen: Qwen3 235B A22B Instruct 2507 | 0.071 | 0.1 | 262144 | — | Qwen · text |
| Bytedance Seed | ByteDance Seed: Seed 1.6 Flash | 0.075 | 0.3 | 262144 | — | Other · image, text, video |
| Openai | OpenAI: gpt-oss-safeguard-20b | 0.075 | 0.3 | 131072 | 0.000000037 | GPT · text |
| Mistralai | Mistral: Mistral Small 3.2 24B | 0.075 | 0.2 | 128000 | — | Mistral · image, text |
| Google: Gemini 2.0 Flash Lite | 0.075 | 0.3 | 1048576 | 1.875e-8 | Gemini · text, image, file, audio, video | |
| Inclusionai | inclusionAI: Ling-2.6-flash | 0.08 | 0.24 | 262144 | 0.000000016 | Other · text |
| Qwen | Qwen: Qwen3 VL 8B Instruct | 0.08 | 0.5 | 131072 | — | Qwen · image, text |
| Qwen | Qwen: Qwen3 30B A3B Thinking 2507 | 0.08 | 0.4 | 131072 | 0.00000008 | Qwen · text |
| Qwen | Qwen: Qwen3 30B A3B | 0.08 | 0.28 | 40960 | — | Qwen · text |
| Qwen | Qwen: Qwen3 32B | 0.08 | 0.24 | 40960 | 0.00000004 | Qwen · text |
| Meta Llama | Meta: Llama 4 Scout | 0.08 | 0.3 | 327680 | — | Llama · text, image |
| Google: Gemma 3 27B | 0.08 | 0.16 | 131072 | — | Other · text, image | |
| Nvidia | NVIDIA: Nemotron 3 Super | 0.09 | 0.45 | 262144 | — | Other · text |
| Xiaomi | Xiaomi: MiMo-V2-Flash | 0.09 | 0.29 | 262144 | 0.000000045 | Other · text |
| Alibaba | Tongyi DeepResearch 30B A3B | 0.09 | 0.45 | 131072 | 0.00000009 | Other · text |
| Qwen | Qwen: Qwen3 Next 80B A3B Instruct | 0.09 | 1.1 | 262144 | — | Qwen · text |
| Qwen | Qwen: Qwen3 30B A3B Instruct 2507 | 0.09 | 0.3 | 262144 | — | Qwen · text |
| Qwen | Qwen: Qwen3 Next 80B A3B Thinking | 0.0975 | 0.78 | 131072 | — | Qwen · text |
| Rekaai | Reka Edge | 0.1 | 0.1 | 16384 | — | Other · image, text, video |
| Qwen | Qwen: Qwen3.5-9B | 0.1 | 0.15 | 262144 | — | Qwen · text, image, video |
| Bytedance Seed | ByteDance Seed: Seed-2.0-Mini | 0.1 | 0.4 | 262144 | — | Other · text, image, video |
| Stepfun | StepFun: Step 3.5 Flash | 0.1 | 0.3 | 262144 | — | Other · text |
| Mistralai | Mistral: Mistral Small Creative | 0.1 | 0.3 | 32768 | 0.00000001 | Mistral · text |
| Mistralai | Mistral: Ministral 3 3B 2512 | 0.1 | 0.1 | 131072 | 0.00000001 | Mistral · text, image |
| Mistralai | Mistral: Voxtral Small 24B 2507 | 0.1 | 0.3 | 32000 | 0.00000001 | Mistral · text, audio |
| Nvidia | NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 | 0.1 | 0.4 | 131072 | — | Llama · text |
| Google: Gemini 2.5 Flash Lite Preview 09-2025 | 0.1 | 0.4 | 1048576 | 0.00000001 | Gemini · text, image, file, audio, video | |
| Z Ai | Z.ai: GLM 4 32B | 0.1 | 0.1 | 128000 | — | GLM · text |
| Bytedance | ByteDance: UI-TARS 7B | 0.1 | 0.2 | 128000 | 0.0000001 | Other · image, text |
| Google: Gemini 2.5 Flash Lite | 0.1 | 0.4 | 1048576 | 0.00000001 | Gemini · text, image, file, audio, video | |
| Mistralai | Mistral: Devstral Small 1.1 | 0.1 | 0.3 | 131072 | 0.00000001 | Mistral · text |
| Openai | OpenAI: GPT-4.1 Nano | 0.1 | 0.4 | 1047576 | 0.000000025 | GPT · image, text, file |
| Rekaai | Reka Flash 3 | 0.1 | 0.2 | 65536 | — | Other · text |
| Google: Gemini 2.0 Flash | 0.1 | 0.4 | 1000000 | 0.000000025 | Gemini · text, image, file, audio, video | |
| Qwen | Qwen: Qwen3 VL 32B Instruct | 0.104 | 0.416 | 131072 | — | Qwen · text, image |
| Qwen | Qwen: Qwen3 VL 8B Thinking | 0.117 | 1.365 | 131072 | — | Qwen · image, text |
| Google: Gemma 4 31B | 0.13 | 0.38 | 262144 | — | Other · image, text, video | |
| Qwen | Qwen: Qwen3 VL 30B A3B Thinking | 0.13 | 1.56 | 131072 | — | Qwen · text, image |
| Qwen | Qwen: Qwen3 VL 30B A3B Instruct | 0.13 | 0.52 | 131072 | — | Qwen · text, image |
| Nousresearch | Nous: Hermes 4 70B | 0.13 | 0.4 | 131072 | — | Other · text |
| Z Ai | Z.ai: GLM 4.5 Air | 0.13 | 0.85 | 131072 | 0.000000025 | GLM · text |
| Nex Agi | Nex AGI: DeepSeek V3.1 Nex N1 | 0.135 | 0.5 | 131072 | — | DeepSeek · text |
| Qwen | Qwen: Qwen VL Plus | 0.1365 | 0.4095 | 131072 | 0.0000000273 | Qwen · text, image |
| Deepseek | DeepSeek: DeepSeek V4 Flash | 0.14 | 0.28 | 1048576 | 0.0000000028 | DeepSeek · text |
| Qwen | Qwen: Qwen3 Coder Next | 0.14 | 0.8 | 262144 | 0.00000009 | Qwen · text |
| Baidu | Baidu: ERNIE 4.5 VL 28B A3B | 0.14 | 0.56 | 30000 | — | Other · text, image |
| Tencent | Tencent: Hunyuan A13B Instruct | 0.14 | 0.57 | 131072 | — | Other · text |
| Qwen | Qwen: Qwen3 235B A22B Thinking 2507 | 0.1495 | 1.495 | 131072 | — | Qwen · text |
| Mistralai | Mistral: Mistral Small 4 | 0.15 | 0.6 | 262144 | 0.000000015 | Mistral · text, image |
| Minimax | MiniMax: MiniMax M2.5 | 0.15 | 1.15 | 196608 | 0.00000003 | Other · text |
| Arcee Ai | Arcee AI: Trinity Large Preview | 0.15 | 0.45 | 131000 | — | Other · text |
| Upstage | Upstage: Solar Pro 3 | 0.15 | 0.6 | 128000 | 0.000000015 | Other · text |
| Essentialai | EssentialAI: Rnj 1 Instruct | 0.15 | 0.15 | 32768 | — | Other · text |
| Mistralai | Mistral: Ministral 3 8B 2512 | 0.15 | 0.15 | 262144 | 0.000000015 | Mistral · text, image |
| Allenai | AllenAI: Olmo 3 32B Think | 0.15 | 0.5 | 65536 | — | Other · text |
| Deepseek | DeepSeek: DeepSeek V3.1 | 0.15 | 0.75 | 32768 | — | DeepSeek · text |
| Meta Llama | Meta: Llama 4 Maverick | 0.15 | 0.6 | 1048576 | — | Llama · text, image |
| Openai | OpenAI: GPT-4o-mini Search Preview | 0.15 | 0.6 | 128000 | 7.5e-8 | GPT · text |
| Qwen | Qwen: Qwen3.6 35B A3B | 0.1612 | 0.96525 | 262144 | 0.0000001612 | Qwen · text, image, video |
| Qwen | Qwen: Qwen3.5-35B-A3B | 0.1625 | 1.3 | 262144 | — | Qwen · text, image, video |
| Arcee Ai | Arcee AI: Spotlight | 0.18 | 0.18 | 131072 | — | Other · image, text |
| Meta Llama | Meta: Llama Guard 4 12B | 0.18 | 0.18 | 163840 | — | Llama · image, text |
| Qwen | Qwen: Qwen3.5-27B | 0.195 | 1.56 | 262144 | — | Qwen · text, image, video |
| Qwen | Qwen: Qwen3 Coder Flash | 0.195 | 0.975 | 1000000 | 0.000000039 | Qwen · text |
| Openai | OpenAI: GPT-5.4 Nano | 0.2 | 1.25 | 400000 | 0.00000002 | GPT · file, image, text |
| Allenai | AllenAI: Olmo 3.1 32B Instruct | 0.2 | 0.6 | 65536 | — | Other · text |
| Mistralai | Mistral: Ministral 3 14B 2512 | 0.2 | 0.2 | 262144 | 0.00000002 | Mistral · text, image |
| Prime Intellect | Prime Intellect: INTELLECT-3 | 0.2 | 1.1 | 131072 | — | Other · text |