Offerings
Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).
Showing every active offering, including the long tail. Show curated models only
More columns: + Vendor + Region - Cache - Batch - Tokenizer - Last change + Source All columns Default columns
| Model | Host | Variant | Region | Input | Output | Blended ↑? | Cache read | Cache write | Batch in | Batch out | Context | Tokenizer | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Nemotron 3.5 Lightning | ModelRun | fp4 | – | 0.0700 | 0.200 | 0.103 | 0.0400 | – | – | – | 1,048,576 | – | – | api |
| gpt-oss-120b | Mancer | fp8 | – | 0.0550 | 0.250 | 0.104 | 0.0550 | – | – | – | 131,072 | o200k | 2026-11-02 ↑ | api |
| Nemotron 3 Nano 30B A3B | OpenRouter | – | – | 0.0600 | 0.240 | 0.105 | 0.0120 | – | – | – | 262,144 | – | – | api |
| Nova Lite 1.0 | OpenRouter | – | – | 0.0600 | 0.240 | 0.105 | – | – | – | – | 300,000 | – | – | api |
| Nemotron 3 Nano 30B A3B | Nebius AI Studio | fp8 | – | 0.0600 | 0.240 | 0.105 | 0.0120 | – | – | – | 262,144 | – | – | api |
| Nova Lite 1.0 | AWS Bedrock | – | eu-west-1 | 0.0600 | 0.240 | 0.105 | – | – | – | – | 300,000 | – | – | api |
| Nova Lite 1.0 | AWS Bedrock | – | – | 0.0600 | 0.240 | 0.105 | – | – | – | – | 300,000 | – | – | api |
| Amazon Nova Lite 2 sources | AWS Bedrock | – | – | 0.0600 | 0.240 | 0.105 | 0.0150 | 0.0600 | 0.0300 | 0.120 | 300,000 | – | – | aggregator |
| Model Router 2 sources | Azure AI Foundry | – | – | 0.140 | free | 0.105 | – | – | – | – | 200,000 | – | – | aggregator |
| Amazon Nova Lite | Amazon | – | – | 0.0600 | 0.240 | 0.105 | – | – | – | – | 300,000 | – | – | aggregator |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | Nebius AI Studio | – | – | 0.0600 | 0.240 | 0.105 | 0.0120 | – | – | – | 262,144 | – | – | aggregator |
| nvidia/Nemotron-3-Nano-Omni | Nebius AI Studio | – | – | 0.0600 | 0.240 | 0.105 | – | – | – | – | 262,144 | – | – | aggregator |
| Nemotron 3.5 Lightning 2 sources | Nebius AI Studio | – | – | 0.0600 | 0.240 | 0.105 | 0.0300 | – | – | – | 1,048,576 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | – | 0.0600 | 0.240 | 0.105 | – | – | 0.0300 | 0.120 | 256,000 | – | – | aggregator |
| DeepSeek V4 Flash 0731 | DeepInfra | – | – | 0.0800 | 0.180 | 0.105 | 0.0160 | – | – | – | 1,048,576 | deepseek | – | aggregator |
| Nemotron 3 Nano 30B A3B | AWS Bedrock | – | – | 0.0600 | 0.240 | 0.105 | – | – | – | – | 262,144 | – | – | aggregator |
| Amazon Nova Lite | AWS Bedrock | – | us | 0.0600 | 0.240 | 0.105 | 0.0150 | – | 0.0300 | 0.120 | 300,000 | – | – | aggregator |
| NVIDIA Nemotron Nano 9B v2 | AWS Bedrock | – | ap-southeast-2 | 0.0618 | 0.237 | 0.106 | – | – | – | – | 128,000 | – | – | aggregator |
| gpt-oss-safeguard-20b | AWS Bedrock | – | ap-southeast-2 | 0.0721 | 0.206 | 0.106 | – | – | – | – | 131,072 | o200k | – | aggregator |
| Mistral Small 3.2 24B | OpenRouter | – | – | 0.0750 | 0.200 | 0.106 | – | – | – | – | 256,000 | mistral | – | api |
| Mistral Small 3.2 24B | DeepInfra | fp8 | – | 0.0750 | 0.200 | 0.106 | – | – | – | – | 256,000 | mistral | – | api |
| Mistral-Small-3.2-24B-Instruct-2506 2 sources | DeepInfra | – | – | 0.0750 | 0.200 | 0.106 | – | – | – | – | 128,000 | – | 2025-10-04 ↑ | official |
| Granite 4.2 8B | DeepInfra | – | – | 0.0600 | 0.250 | 0.108 | 0.0150 | – | – | – | 131,072 | – | – | api |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | Together AI | – | – | 0.0600 | 0.250 | 0.108 | – | – | – | – | 131,072 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | ap-southeast-2 | 0.0618 | 0.247 | 0.108 | – | – | – | – | 256,000 | – | – | aggregator |
| GLM 5.3 Flash | Wafer | nvfp4 | – | 0.0650 | 0.240 | 0.109 | 0.0640 | – | – | – | 1,048,576 | – | 2026-11-11 ↑ | api |
| Ministral 3 3B 2512 | Mistral AI | – | eu | 0.110 | 0.110 | 0.110 | 0.0110 | – | – | – | 131,072 | mistral | – | api |
| LFM3-1.7B | Liquid AI | fp8 | – | 0.0800 | 0.200 | 0.110 | 0.0200 | – | – | – | 262,144 | – | – | api |
| LFM3-1.7B | OpenRouter | – | – | 0.0800 | 0.200 | 0.110 | 0.0200 | – | – | – | 262,144 | – | – | api |
| eu.meta.llama3-2-1b-instruct-v1:0 | AWS Bedrock | – | eu-west-1 | 0.110 | 0.110 | 0.110 | – | – | – | – | 128,000 | – | – | aggregator |
| Amazon Nova Lite | AWS Bedrock | – | apac | 0.0630 | 0.252 | 0.110 | 0.0158 | – | – | – | 300,000 | – | – | aggregator |
| Ling 3.0 Flash VL 2 sources | Novita AI promo −72% | – | – | 0.0750 | 0.220 | 0.111 | 0.0150 | – | – | – | 131,072 | – | – | api |
| Ling 3.0 Flash Fin 2 sources | Novita AI promo −44% | – | – | 0.0750 | 0.220 | 0.111 | 0.0150 | – | – | – | 262,144 | – | – | api |
| Ling 3.0 Flash Sante 2 sources | Novita AI promo −44% | – | – | 0.0750 | 0.220 | 0.111 | 0.0150 | – | – | – | 262,144 | – | – | api |
| GLM 5.3 Flash | particle-ai | flex+nvfp4 | – | 0.0650 | 0.250 | 0.111 | 0.0200 | – | – | – | 1,048,576 | – | – | api |
| DeepSeek V4 Flash | OpenRouter | – | – | 0.0900 | 0.180 | 0.113 | 0.0180 | – | – | – | 1,048,576 | deepseek | – | api |
| DeepSeek V4 Flash | DeepInfra | fp8 | – | 0.0900 | 0.180 | 0.113 | 0.0180 | – | – | – | 1,048,576 | deepseek | – | api |
| Qwen3.5-9B | SiliconFlow | fp8 | – | 0.100 | 0.150 | 0.113 | – | – | – | – | 262,144 | qwen2 | – | api |
| Qwen3.5-9B 4 sources | DeepInfra | – | – | 0.100 | 0.150 | 0.113 | – | – | – | – | 262,144 | qwen2 | – | official |
| DeepSeek V4 Flash 2 sources | DeepInfra | – | – | 0.0900 | 0.180 | 0.113 | 0.0180 | 0.113 | – | – | 1,048,576 | deepseek | – | aggregator |
| Gemini Embedding 001 | – | – | 0.150 | free | 0.113 | – | – | – | – | 2,048 | – | – | aggregator | |
| Gemini Embedding 001 | Google Vertex AI | – | – | 0.150 | free | 0.113 | – | – | – | – | 2,048 | – | – | aggregator |
| DeepSeek-V4-Flash | DeepInfra | – | – | 0.0900 | 0.180 | 0.113 | 0.0180 | – | – | – | 1,000,000 | – | – | official |
| Gemma 3 12B | DeepInfra | priority | – | 0.0750 | 0.225 | 0.113 | – | – | – | – | 131,072 | gemini | – | api |
| Gemma 4 26B A4B | AkashML | fp4 | – | 0.0700 | 0.240 | 0.113 | 0.0460 | – | – | – | 262,144 | gemma | – | api |
| DeepSeek V4 Flash 0731 | Wafer | nvfp4 | us | 0.0500 | 0.300 | 0.113 | 0.0350 | – | – | – | 1,048,576 | deepseek | 2026-11-19 ↑ | api |
| Qwen3.5-Flash | OpenRouter | – | – | 0.0650 | 0.260 | 0.114 | – | – | – | – | 1,000,000 | qwen2 | – | api |
| Qwen3.5-Flash | Alibaba Cloud | – | – | 0.0650 | 0.260 | 0.114 | – | – | – | – | 1,000,000 | qwen2 | – | api |
| GPT OSS 20B 2 sources | Google Vertex AI | – | – | 0.0700 | 0.250 | 0.115 | 0.007000 | – | 0.0350 | 0.125 | 131,072 | – | 2026-09-11 ↓ | aggregator |
| DeepSeek V4.1 Flash 1017 | IonStream | flex | – | 0.0775 | 0.233 | 0.116 | 0.002325 | – | – | – | 1,048,576 | deepseek | 2026-11-12 ↓ | api |
Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence