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? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| tev1-4b-experimental 2 sources | Together AI | – | – | 0.0420 | free | 0.0315 | – | – | – | – | 32,768 | – | 2026-11-11 ↑ | official |
| gpt-image-1.5 | Together AI | – | – | – | 0.0340 | 0.0340 | – | – | – | – | – | – | – | official |
| meta-llama/Meta-Llama-3.1-8B-Instruct | DeepInfra | – | – | 0.0300 | 0.0500 | 0.0350 | – | – | – | – | 131,072 | – | – | aggregator |
| Llama 3.2 3B Instruct 2 sources | Novita AI | – | – | 0.0300 | 0.0500 | 0.0350 | – | – | – | – | 131,072 | llama3 | 2026-01-13 ↓ | aggregator |
| qwen-image-20 | Together AI | – | – | – | 0.0350 | 0.0350 | – | – | – | – | – | – | 2026-11-11 ↓ | official |
| seedream-50-lite | Together AI | – | – | – | 0.0350 | 0.0350 | – | – | – | – | – | – | – | official |
| gpt-oss-20b | Darkbloom | fp8 | – | 0.0180 | 0.0900 | 0.0360 | 0.009000 | – | – | – | 131,072 | o200k | – | api |
| gpt-oss-20b | AkashML | fp4 | – | 0.0180 | 0.0900 | 0.0360 | 0.009000 | – | – | – | 131,072 | o200k | 2026-11-16 ↓ | api |
| meta-llama/Meta-Llama-3-8B-Instruct | DeepInfra | – | – | 0.0300 | 0.0600 | 0.0375 | – | – | – | – | 8,192 | – | 2025-08-22 ↓ | aggregator |
| Qwen3 Reranker 8B | Novita AI | – | – | 0.0500 | free | 0.0375 | – | – | – | – | 32,768 | – | – | aggregator |
| Extract | scaledown promo −20% | – | – | 0.0500 | free | 0.0375 | – | – | – | – | 1,000,000 | – | – | api |
| Summarize | scaledown promo −20% | – | – | 0.0500 | free | 0.0375 | – | – | – | – | 1,000,000 | – | – | api |
| gemini-flash-image-2-5 | Together AI | – | – | – | 0.0390 | 0.0390 | – | – | – | – | – | – | – | official |
| Ministral 3B 2 sources | Azure AI Foundry | – | – | 0.0400 | 0.0400 | 0.0400 | – | – | – | – | 128,000 | – | – | aggregator |
| Prompt Guard 2 86M 2 sources | Groq | – | – | 0.0400 | 0.0400 | 0.0400 | – | – | – | – | 512 | – | – | aggregator |
| Voxtral Mini 3B 2507 2 sources | AWS Bedrock | – | – | 0.0400 | 0.0400 | 0.0400 | – | – | 0.0200 | 0.0200 | 32,768 | – | – | aggregator |
| Llama 3 8B Instruct 2 sources | Novita AI | – | – | 0.0400 | 0.0400 | 0.0400 | – | – | – | – | 8,192 | – | 2026-01-13 ↓ | aggregator |
| Gemma 4 E4B IT 2 sources | DeepInfra | – | – | 0.0200 | 0.100 | 0.0400 | – | – | – | – | 131,072 | – | – | aggregator |
| flux-1-kontext-pro | Together AI | – | – | 0.0400 | – | 0.0400 | – | – | – | – | – | – | – | official |
| flux1-1-pro | Together AI | – | – | 0.0400 | – | 0.0400 | – | – | – | – | – | – | – | official |
| Granite 4.0 Micro | Cloudflare Workers AI | – | – | 0.0170 | 0.112 | 0.0408 | – | – | – | – | 131,000 | – | – | api |
| Llama 3 8B Lunaris | OpenRouter | – | – | 0.0400 | 0.0500 | 0.0425 | – | – | – | – | 8,192 | llama3 | – | api |
| Llama 3 8B Lunaris | Parasail | – | – | 0.0400 | 0.0500 | 0.0425 | – | – | – | – | 8,192 | llama3 | – | api |
| Llama 3 8B Lunaris | DeepInfra | fp8+turbo | – | 0.0400 | 0.0500 | 0.0425 | – | – | – | – | 8,192 | llama3 | – | api |
| Sao10K/L3-8B-Lunaris-v1-Turbo | DeepInfra | – | – | 0.0400 | 0.0500 | 0.0425 | – | – | – | – | 8,192 | – | 2025-10-04 ↑ | aggregator |
| Gemma 3 4B | Parasail | – | – | 0.0400 | 0.0500 | 0.0425 | 0.0200 | – | – | – | 131,072 | gemini | – | api |
| Nex-N2.5-Mini | OpenRouter | – | – | 0.0250 | 0.100 | 0.0438 | 0.002500 | – | – | – | 262,144 | qwen2 | – | api |
| Nex-N2.5-Mini | Nex AGI | – | – | 0.0250 | 0.100 | 0.0438 | 0.002500 | – | – | – | 262,144 | qwen2 | – | api |
| gpt-oss-120b | Prime Intellect | fp4 | – | 0.0350 | 0.0750 | 0.0450 | 0.0310 | – | – | – | 131,072 | o200k | 2026-11-09 ↕ | api |
| gpt-oss-20b | DeepInfra | flex | – | 0.0240 | 0.112 | 0.0460 | 0.0120 | – | – | – | 131,072 | o200k | – | api |
| gemini-31-flash-image | Together AI | – | – | – | 0.0466 | 0.0466 | – | – | – | – | – | – | 2026-11-11 ↓ | official |
| Llama 3.2 11b Vision Instruct | DeepInfra | – | – | 0.0490 | 0.0490 | 0.0490 | – | – | – | – | 131,072 | – | – | aggregator |
| Gemma 3 4B 2 sources | AWS Bedrock | – | – | 0.0400 | 0.0800 | 0.0500 | – | – | 0.0200 | 0.0400 | 131,072 | gemini | – | aggregator |
| Sao10k L3 8B Lunaris 2 sources | Novita AI | – | – | 0.0500 | 0.0500 | 0.0500 | – | – | – | – | 8,192 | – | 2026-01-13 ↓ | aggregator |
| L3 8B Stheno V3.2 2 sources | Novita AI | – | – | 0.0500 | 0.0500 | 0.0500 | – | – | – | – | 8,192 | – | 2026-01-13 ↓ | aggregator |
| Gemma 4 E2B IT 2 sources | AWS Bedrock | – | – | 0.0400 | 0.0800 | 0.0500 | – | – | 0.0200 | 0.0400 | 128,000 | – | – | aggregator |
| Rerank 5 Pro | Cohere | – | – | 0.0500 | – | 0.0500 | – | – | – | – | – | – | – | official |
| Gemma 3 4B | DeepInfra | flex | – | 0.0400 | 0.0800 | 0.0500 | – | – | – | – | 131,072 | gemini | – | api |
| Gemma 4 26B A4B | Prime Intellect | – | – | 0.0340 | 0.101 | 0.0508 | 0.0170 | – | – | – | 262,144 | gemma | 2026-11-14 ↑ | api |
| Nemotron 3.5 Lightning 30B A3B | Perplexity | – | – | 0.0115 | 0.170 | 0.0511 | 0.001150 | – | – | – | 262,144 | – | – | aggregator |
| Gemma 3 4B | AWS Bedrock | – | ap-southeast-2 | 0.0412 | 0.0824 | 0.0515 | – | – | – | – | 131,072 | gemini | – | aggregator |
| LFM2-24B-A2B | Together AI | – | – | 0.0300 | 0.120 | 0.0525 | – | – | – | – | 32,768 | – | – | aggregator |
| Qwen3-Embedding-8B | Novita AI | – | – | 0.0700 | free | 0.0525 | – | – | – | – | 40,960 | – | – | aggregator |
| gpt-image-2 | Together AI | – | – | – | 0.0530 | 0.0530 | – | – | – | – | – | – | – | official |
| Qwen3.7 Flash | OpenRouter | – | – | 0.0300 | 0.130 | 0.0550 | 0.006000 | 0.0380 | – | – | 1,000,000 | qwen2 | – | api |
| Qwen3.7 Flash 2 sources | Alibaba Cloud | – | – | 0.0300 | 0.130 | 0.0550 | 0.006000 | 0.0380 | – | – | 1,000,000 | qwen2 | – | api |
| gpt-oss-20b | CoreWeave | fp4 | – | 0.0300 | 0.130 | 0.0550 | 0.0300 | – | – | – | 131,072 | o200k | – | api |
| Qwen2.5 7B Instruct | DeepInfra | – | – | 0.0400 | 0.100 | 0.0550 | – | – | – | – | 32,768 | – | – | aggregator |
| llama-guard-3-8b | DeepInfra | – | – | 0.0550 | 0.0550 | 0.0550 | – | – | – | – | 131,072 | – | – | aggregator |
| gpt-oss-20b | DekaLLM | – | – | 0.0290 | 0.140 | 0.0568 | 0.0290 | – | – | – | 131,072 | o200k | – | 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