Prices refreshed 2026-08-28 · 281 models · 42 GPUs · 5 live sources
Models · Hugging Face 2026-08-28
Conversation · X today
Rising tools · GitHub 2026-08-28
What it costs to run AI, today
Two markets decide your inference bill: the token market (per-million-token API prices) and the GPU-hour market (renting the hardware yourself). We pull both from provider APIs every day and show you where the floor is.
Token market: $ / 1M tokens
all 281 →| Model | In | Out | Floor at |
|---|---|---|---|
| DeepSeek V4 Flash Vision Exp3 providers · listed 2026-08-21 | $0.220 | $0.660 | OpenRouter |
| GLM 5.33 providers · listed 2026-08-18 | $1.40 | $4.40 | Z.ai+2 same price |
| Qwen3.8 27B3 providers · listed 2026-08-14 | $0.400 | $2.55 | W&B Inference+1 same price |
| Gemini 3.7 Flash4 providers · listed 2026-08-13 | $0.750 | $3.75 | Google Vertex AI+3 same price |
| Qwen3.8 2.4T A95B3 providers · listed 2026-08-12 | $2.00 | $6.00 | DeepInfra+1 same price |
| Grok 4.63 providers · listed 2026-08-12 | $2.00 | $6.00 | xAI+1 same price |
| Muse Glimmer 30B4 providers · listed 2026-08-09 | $0.300 | $1.20 | DeepInfra+1 same price |
| Qwen3.8 Max6 providers · listed 2026-08-03 | $1.65 | $4.95 | Scx AI+1 same price |
GPU-hour market
all 42 →| GPU | VRAM | From | Floor at |
|---|---|---|---|
| B200 | 180 GB | $3.06spot | Verda |
| H200 | 141 GB | $2.00spot | Verda |
| H100 SXM | 80 GB | $1.34marketplace | Vast.ai |
| A100 SXM 80GB | 80 GB | $0.667marketplace | Vast.ai |
| MI300X | 192 GB | $0.500community | RunPod |
| L40S | 48 GB | $0.401marketplace | Vast.ai |
| RTX 5090 | 32 GB | $0.321marketplace | Vast.ai |
| RTX 4090 | 24 GB | $0.120marketplace | Vast.ai |
New this week
all new models →- Hy4 preview listed 2026-08-28 · in $0.834
- GLM 5.3 Flash listed 2026-08-26 · in $0.075
- Qwen3.8 Flash listed 2026-08-26 · in $0.150
- GLM 5.3 Flash (batch) listed 2026-08-26 · in $0.150
- Muse Spark 1.2 Contributor listed 2026-08-21 · in $0.100
Pay per token, rent the card, or own the box
01 / APILowest ops burdenCompare the workload mix →
02 / RENTFlexible raw computeShop live GPU-hours →
03 / OWNPrivate, sustained usePrice local hardware →
Undecided? The self-hosting cost table prices every notable open model against today's cheapest fitting GPU, or work your own numbers in the calculator. Or describe your workload and get a ranked plan across all three, free while in beta.
What's moving in open models & tooling
- 1 no API yet
- 2 price it →
- 3 price it →
- 4 price it →
- 5 no API yet
- 6 no API yet
- 7 no API yet
- 8 no API yet
- 9 price it →
- 10 no API yet
- 11 no API yet
- 12 no API yet
Every model, newest listings first
| Model | Cheapest in $/1M | Cheapest out $/1M | Context | Providers | Cheapest input at |
|---|---|---|---|---|---|
| Hy4 previewlisted 2026-08-28 | $0.834 | $2.50 | 1049K | 1 | OpenRouter |
| GLM 5.3 Flashlisted 2026-08-26 | $0.075 | $0.250 | 1311K | 2 | OpenRouter |
| Qwen3.8 Flashlisted 2026-08-26 | $0.150 | $0.470 | 1000K | 1 | OpenRouter |
| GLM 5.3 Flash (batch)listed 2026-08-26 | $0.150 | $0.500 | 1049K | 1 | OpenRouter |
| DeepSeek V4 Flash Vision Explisted 2026-08-21 | $0.220 | $0.660 | 1049K | 3 | OpenRouter |
| Muse Spark 1.2 Contributorlisted 2026-08-21 | $0.100 | $0.200 | 1049K | 2 | Meta |
| Hy-MT2-1.8Blisted 2026-08-20 | $0.044 | $0.177 | 8K | 1 | OpenRouter |
| Hy-MT2-30B-A3Blisted 2026-08-20 | $0.074 | $0.295 | 8K | 1 | OpenRouter |
| GLM Latestlisted 2026-08-19 | $1.25 | $4.40 | 1311K | 1 | OpenRouter |
| Hy-MT2-7Blisted 2026-08-19 | $0.074 | $0.295 | 8K | 1 | OpenRouter |
| GLM 5.3listed 2026-08-18 | $1.40 | $4.40 | 1000K | 3 | Z.ai |
| Qwen3.8 27Blisted 2026-08-14 | $0.400 | $2.55 | 262K | 3 | W&B Inference |
| Gemini 3.7 Flashlisted 2026-08-13 | $0.750 | $3.75 | 1049K | 4 | Google Vertex AI |
| Gemini 3.7 Flash (batch)listed 2026-08-13 | $0.188 | $0.938 | 1049K | 1 | OpenRouter |
| Qwen3.8 2.4T A95Blisted 2026-08-12 | $2.00 | $6.00 | 262K | 3 | DeepInfra |
| Grok 4.6listed 2026-08-12 | $2.00 | $6.00 | 500K | 3 | xAI |
| Seed-2.0-Codelisted 2026-08-12 | $0.500 | $3.00 | 256K | 2 | DeepInfra |
| Seed 2.1 Turbolisted 2026-08-12 | $0.500 | $2.50 | 262K | 1 | OpenRouter |
| Qwen3.8 2.4T A95B (batch)listed 2026-08-12 | $2.50 | $6.25 | 1010K | 1 | OpenRouter |
| DeepSeek V4 Pro 0813 (batch)listed 2026-08-12 | $1.32 | $3.96 | 1049K | 1 | OpenRouter |
| Sakana Namazulisted 2026-08-11 | $0.950 | $4.00 | 262K | 1 | OpenRouter |
| Solar Pro 4listed 2026-08-10 | $0.030 | $0.120 | 524K | 1 | OpenRouter |
| Muse Glimmer 30Blisted 2026-08-09 | $0.300 | $1.20 | 131K | 4 | DeepInfra |
| Muse Glimmer 30B (batch)listed 2026-08-09 | $0.350 | $1.50 | 131K | 1 | OpenRouter |
| Muse Spark 1.2listed 2026-08-05 | $1.25 | $4.25 | 1049K | 2 | Meta |
| Qwen3.8 Maxlisted 2026-08-03 | $1.65 | $4.95 | 1000K | 6 | Scx AI |
| DeepSeek V4 Flashlisted 2026-07-31 | $0.050 | $0.100 | 1311K | 13 | OpenRouter |
| DeepSeek V4 Flash 0731 (batch)listed 2026-07-31 | $0.140 | $0.280 | 1049K | 1 | OpenRouter |
| Inkling Smalllisted 2026-07-30 | $0.450 | $1.20 | 524K | 3 | DeepInfra |
| Inkling Small (batch)listed 2026-07-30 | $0.500 | $1.20 | 524K | 1 | OpenRouter |
| Qwen3.7 Flashlisted 2026-07-27 | $0.030 | $0.130 | 1000K | 1 | OpenRouter |
| Claude Opus 5 (Fast)listed 2026-07-24 | $10.00 | $50.00 | 1000K | 1 | OpenRouter |
| Claude Opus 5 (batch)listed 2026-07-24 | $2.50 | $12.50 | 1000K | 1 | OpenRouter |
| Ling-3.0-Flashlisted 2026-07-23 | $0.021 | $0.063 | 262K | 3 | OpenRouter |
| Gemini 3.5 Flash Litelisted 2026-07-21 | $0.300 | $2.50 | 1049K | 3 | Google Vertex AI |
| Gemini 3.6 Flashlisted 2026-07-21 | $0.750 | $3.75 | 1049K | 3 | Google Vertex AI |
| Laguna S 2.1listed 2026-07-21 | $0.090 | $0.180 | 1049K | 1 | OpenRouter |
| Gemini 3.6 Flash (batch)listed 2026-07-21 | $0.375 | $1.88 | 1049K | 1 | OpenRouter |
| Gemini 3.5 Flash Lite (batch)listed 2026-07-21 | $0.150 | $1.25 | 1049K | 1 | OpenRouter |
| LongCat 2.0listed 2026-07-20 | $0.300 | $1.20 | 1049K | 1 | OpenRouter |
| Inklinglisted 2026-07-17 | $0.950 | $4.05 | 524K | 3 | DeepInfra |
| Inkling (batch)listed 2026-07-17 | $1.00 | $4.05 | 524K | 1 | OpenRouter |
| Kimi K3listed 2026-07-16 | $2.85 | $14.25 | 1049K | 7 | DeepInfra |
| Muse Spark 1.1listed 2026-07-16 | $1.25 | $4.25 | 1049K | 2 | Meta |
| Kimi K3 (batch)listed 2026-07-16 | $3.00 | $15.00 | 1049K | 1 | OpenRouter |
| KAT-Coder-Air V2.5listed 2026-07-10 | $0.150 | $0.600 | 256K | 1 | OpenRouter |
| KAT-Coder-Pro V2.5listed 2026-07-10 | $0.740 | $2.96 | 262K | 1 | OpenRouter |
| GPT-5.6 Sollisted 2026-07-09 | $2.00 | $10.00 | 1050K | 4 | OpenRouter |
| GPT-5.6 Terralisted 2026-07-09 | $2.00 | $12.00 | 922K | 4 | Azure AI Foundry |
| GPT-5.6 Lunalisted 2026-07-09 | $0.200 | $1.20 | 922K | 4 | Azure AI Foundry |
| GPT-5.6 Luna Prolisted 2026-07-09 | $0.200 | $1.20 | 1050K | 1 | OpenRouter |
| GPT-5.6 Terra Prolisted 2026-07-09 | $2.00 | $12.00 | 1050K | 1 | OpenRouter |
| GPT-5.6 Sol Prolisted 2026-07-09 | $2.00 | $10.00 | 1050K | 1 | OpenRouter |
| Grok 4.5listed 2026-07-08 | $2.00 | $6.00 | 500K | 2 | xAI |
| Grok Latestlisted 2026-07-08 | $2.00 | $6.00 | 500K | 1 | OpenRouter |
| Aion-3.0-Minilisted 2026-07-07 | $0.700 | $1.40 | 131K | 1 | OpenRouter |
| Aion-3.0listed 2026-07-07 | $3.00 | $6.00 | 131K | 1 | OpenRouter |
| Hy3listed 2026-07-06 | $0.083 | $0.330 | 262K | 3 | OpenRouter |
| Laguna XS 2.1listed 2026-07-02 | $0.060 | $0.120 | 262K | 1 | OpenRouter |
| Claude Sonnet 5listed 2026-06-30 | $2.00 | $10.00 | 1000K | 7 | AWS Bedrock |
| Claude Sonnet 5 (batch)listed 2026-06-30 | $1.00 | $5.00 | 1000K | 1 | OpenRouter |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)listed 2026-06-30 | $0.250 | $1.50 | 66K | 1 | OpenRouter |
| Nex-N2-Minilisted 2026-06-24 | $0.025 | $0.100 | 262K | 1 | OpenRouter |
| Fugu Ultralisted 2026-06-24 | $5.00 | $30.00 | 1000K | 1 | OpenRouter |
| GLM-5.2listed 2026-06-16 | $0.610 | $1.98 | 1049K | 11 | Scx AI |
| Kimi K2.7 Codelisted 2026-06-12 | $0.660 | $3.40 | 262K | 8 | OpenRouter |
| Claude Fable 5listed 2026-06-09 | $10.00 | $50.00 | 1000K | 7 | AWS Bedrock |
| Claude Fable Latestlisted 2026-06-09 | $10.00 | $50.00 | 1000K | 1 | OpenRouter |
| Claude Fable 5 (batch)listed 2026-06-09 | $5.00 | $25.00 | 1000K | 1 | OpenRouter |
| Nex-N2-Prolisted 2026-06-08 | $0.250 | $1.00 | 262K | 1 | OpenRouter |
| Nemotron 3 Ultralisted 2026-06-04 | $0.500 | $2.20 | 262K | 4 | DeepInfra |
| Nemotron 3 Ultra (batch)listed 2026-06-04 | $0.600 | $3.60 | 512K | 1 | OpenRouter |
| Qwen3.7 Pluslisted 2026-06-03 | $0.320 | $1.28 | 1000K | 3 | Together AI |
| MiniMax M3listed 2026-05-31 | $0.230 | $0.960 | 262K | 8 | W&B Inference |
| MiniMax M3 (batch)listed 2026-05-31 | $0.300 | $1.20 | 524K | 1 | OpenRouter |
| Step 3.7 Flashlisted 2026-05-28 | $0.200 | $1.15 | 262K | 3 | Novita AI |
| Claude Opus 4.8listed 2026-05-27 | $5.00 | $25.00 | 1000K | 7 | AWS Bedrock |
| Claude Opus 4.8 (Fast)listed 2026-05-27 | $10.00 | $50.00 | 1000K | 1 | OpenRouter |
| Claude Opus 4.8 (batch)listed 2026-05-27 | $2.50 | $12.50 | 1000K | 1 | OpenRouter |
| Qwen3.7 Maxlisted 2026-05-21 | $1.25 | $3.75 | 1000K | 5 | Novita AI |
| Grok Build 0.1listed 2026-05-20 | $1.00 | $2.00 | 256K | 2 | xAI |
| Gemini 3.5 Flashlisted 2026-05-19 | $1.50 | $9.00 | 1049K | 4 | Google Vertex AI |
| Gemini 3.5 Flash (batch)listed 2026-05-19 | $0.750 | $4.50 | 1049K | 1 | OpenRouter |
| Claude Opus 4.7 (Fast)listed 2026-05-12 | $30.00 | $150 | 1000K | 1 | OpenRouter |
| Perceptron Mk1listed 2026-05-12 | $0.150 | $1.50 | 33K | 1 | OpenRouter |
| Gemini 3.1 Flash Lite (batch)listed 2026-05-07 | $0.125 | $0.750 | 1049K | 1 | OpenRouter |
| GPT Chat Latestlisted 2026-05-05 | $5.00 | $30.00 | 400K | 1 | OpenRouter |
| Grok 4.3listed 2026-04-30 | $1.25 | $2.50 | 200K | 4 | Azure AI Foundry |
| Mistral Medium 3.5listed 2026-04-30 | $1.50 | $7.50 | 262K | 2 | Mistral AI |
| IBM Granite 4.1 8Blisted 2026-04-30 | $0.050 | $0.100 | 131K | 2 | W&B Inference |
| Mistral Medium 3.5 (batch)listed 2026-04-30 | $0.750 | $3.75 | 262K | 1 | OpenRouter |
| Qwen3.6 27Blisted 2026-04-27 | $0.150 | $0.500 | 262K | 7 | Libertai |
| Qwen3.6 35B A3Blisted 2026-04-27 | $0.100 | $0.450 | 262K | 7 | DeepInfra |
| Google Gemini Flash Latestlisted 2026-04-27 | $0.300 | $2.50 | 1049K | 2 | Google Gemini API |
| MoonshotAI Kimi Latestlisted 2026-04-27 | $2.00 | $5.00 | 131K | 2 | Moonshot |
| Google Gemini Pro Latestlisted 2026-04-27 | $1.25 | $10.00 | 1049K | 2 | Google Gemini API |
| Anthropic Claude Haiku Latestlisted 2026-04-27 | $1.00 | $5.00 | 200K | 1 | OpenRouter |
| OpenAI GPT Mini Latestlisted 2026-04-27 | $0.750 | $4.50 | 400K | 1 | OpenRouter |
| Anthropic Claude Sonnet Latestlisted 2026-04-27 | $2.00 | $10.00 | 1000K | 1 | OpenRouter |
| OpenAI GPT Latestlisted 2026-04-27 | $2.00 | $10.00 | 1050K | 1 | OpenRouter |
| Qwen3.5 Plus 2026-04-20listed 2026-04-27 | $0.300 | $1.80 | 1000K | 1 | OpenRouter |
| Qwen3.6 Flashlisted 2026-04-27 | $0.188 | $1.13 | 1000K | 1 | OpenRouter |
| Qwen3.6 Max Previewlisted 2026-04-27 | $1.03 | $6.16 | 262K | 1 | OpenRouter |
| GPT-5.5listed 2026-04-24 | $5.00 | $30.00 | 1050K | 3 | Azure AI Foundry |
| GPT-5.5 Prolisted 2026-04-24 | $30.00 | $180 | 1050K | 1 | OpenRouter |
| GPT-5.4 Image 2listed 2026-04-21 | $8.00 | $15.00 | 272K | 1 | OpenRouter |
| Claude Opus Latestlisted 2026-04-21 | $5.00 | $25.00 | 1000K | 1 | OpenRouter |
| Kimi K2.6listed 2026-04-20 | $0.650 | $3.40 | 262K | 9 | W&B Inference |
| Claude Opus 4.7 (batch)listed 2026-04-16 | $2.50 | $12.50 | 1000K | 1 | OpenRouter |
| Gemma 4 26B A4B listed 2026-04-03 | $0.070 | $0.300 | 262K | 6 | DeepInfra |
| Gemma 4 31Blisted 2026-04-02 | $0.090 | $0.340 | 262K | 8 | OpenRouter |
| Gemma 4 31B (batch)listed 2026-04-02 | $0.390 | $0.970 | 262K | 1 | OpenRouter |
| GLM 5V Turbolisted 2026-04-01 | $1.20 | $4.00 | 205K | 2 | Novita AI |
| Trinity Large Thinkinglisted 2026-04-01 | $0.220 | $0.850 | 262K | 1 | OpenRouter |
| Grok 4.20listed 2026-03-31 | $1.25 | $2.50 | 2000K | 2 | OpenRouter |
| Grok 4.20 Multi-Agentlisted 2026-03-31 | $1.25 | $2.50 | 2000K | 2 | OpenRouter |
| Lyria 3 Pro Previewlisted 2026-03-30 | free | free | 1049K | 1 | OpenRouter |
| Lyria 3 Clip Previewlisted 2026-03-30 | free | free | 1049K | 1 | OpenRouter |
| KAT-Coder-Pro V2listed 2026-03-27 | $0.300 | $1.20 | 262K | 1 | OpenRouter |
| Reka Edgelisted 2026-03-20 | $0.100 | $0.100 | 16K | 1 | OpenRouter |
| MiniMax M2.7listed 2026-03-18 | $0.250 | $0.550 | 197K | 6 | DeepInfra |
| GPT-5.4 Minilisted 2026-03-17 | $0.750 | $4.50 | 272K | 4 | Azure AI Foundry |
| GPT-5.4 Nanolisted 2026-03-17 | $0.200 | $1.25 | 272K | 4 | Azure AI Foundry |
| Mistral Small 4listed 2026-03-16 | $0.100 | $0.300 | 32K | 7 | Mistral AI |
| Mistral Small 4 (batch)listed 2026-03-16 | $0.150 | $0.600 | 262K | 1 | OpenRouter |
| GLM 5 Turbolisted 2026-03-15 | $1.20 | $4.00 | 203K | 2 | Novita AI |
| Nemotron 3 Superlisted 2026-03-11 | $0.085 | $0.400 | 262K | 2 | DeepInfra |
| Qwen3.5-9Blisted 2026-03-10 | $0.100 | $0.150 | 262K | 3 | DeepInfra |
| Seed-2.0-Litelisted 2026-03-10 | $0.250 | $2.00 | 262K | 1 | OpenRouter |
| Qwen3.5-9B (batch)listed 2026-03-10 | $0.170 | $0.250 | 262K | 1 | OpenRouter |
| GPT-5.4listed 2026-03-05 | $2.50 | $15.00 | 1050K | 4 | Azure AI Foundry |
| GPT-5.4 Prolisted 2026-03-05 | $30.00 | $180 | 1050K | 1 | OpenRouter |
| Mercury 2listed 2026-03-04 | $0.250 | $0.750 | 128K | 2 | Inception |
| GPT Audiolisted 2026-01-19 | $2.50 | $10.00 | 128K | 3 | Azure AI Foundry |
| GPT Audio Minilisted 2026-01-19 | $0.600 | $2.40 | 128K | 3 | Azure AI Foundry |
| Nemotron 3 Nanolisted 2025-12-14 | $0.050 | $0.200 | 262K | 3 | Novita AI |
| GPT-5.1listed 2025-11-13 | $1.25 | $10.00 | 272K | 5 | Azure AI Foundry |
| Kimi K2 Thinkinglisted 2025-11-06 | $0.600 | $1.20 | 128K | 9 | AWS Bedrock |
| GPT-OSS-Safeguard-20blisted 2025-10-29 | $0.070 | $0.200 | 128K | 4 | AWS Bedrock |
| Qwen3 VL 32B Instructlisted 2025-10-23 | $0.104 | $0.416 | 131K | 3 | OpenRouter |
| Qwen3 VL 8B Instructlisted 2025-10-14 | $0.080 | $0.200 | 131K | 4 | Novita AI |
| Qwen3 VL 30B A3B Instructlisted 2025-10-06 | $0.150 | $0.600 | 262K | 4 | Fireworks AI |
| Qwen3 VL 235B A22B Instructlisted 2025-09-23 | $0.200 | $0.880 | 262K | 6 | DeepInfra |
| Qwen3 VL 235B A22B Thinkinglisted 2025-09-23 | $0.220 | $0.880 | 262K | 4 | Fireworks AI |
| DeepSeek V3.1 Terminuslisted 2025-09-22 | $0.270 | $1.00 | 164K | 4 | DeepInfra |
| Qwen3 Next 80B A3B Instructlisted 2025-09-11 | $0.090 | $0.900 | 262K | 7 | DeepInfra |
| Qwen3 Next 80B A3B Thinkinglisted 2025-09-11 | $0.140 | $0.900 | 262K | 7 | DeepInfra |
| GLM 4.5Vlisted 2025-08-11 | $0.600 | $1.20 | 128K | 4 | Z.ai |
| Codestral 2508listed 2025-08-01 | $0.200 | $0.600 | 128K | 4 | Google Vertex AI |
| Qwen3 Coder 30B A3B Instructlisted 2025-07-31 | $0.070 | $0.270 | 160K | 5 | Novita AI |
| GLM-4.5 Airlisted 2025-07-25 | $0.125 | $0.450 | 128K | 7 | Pinstripes |
| GLM-4.5listed 2025-07-25 | $0.400 | $1.60 | 131K | 6 | DeepInfra |
| Gemini 2.5 Flash Litelisted 2025-07-22 | $0.075 | $0.300 | 1049K | 4 | Oracle OCI |
| Kimi K2listed 2025-07-11 | $0.500 | $2.00 | 131K | 11 | DeepInfra |
| Llama Guard 4 12Blisted 2025-04-30 | $0.180 | $0.180 | 164K | 4 | DeepInfra |
| Qwen3 32Blisted 2025-04-28 | $0.050 | $0.100 | 131K | 9 | Lambda |
| Qwen3 30B A3Blisted 2025-04-28 | $0.051 | $0.200 | 33K | 8 | Cloudflare |
| Qwen3 14Blisted 2025-04-28 | $0.050 | $0.200 | 33K | 5 | W&B Inference |
| Qwen3 8Blisted 2025-04-28 | $0.035 | $0.138 | 128K | 4 | Novita AI |
| O3listed 2025-04-16 | $2.00 | $8.00 | 200K | 5 | Azure AI Foundry |
| o4 Minilisted 2025-04-16 | $1.00 | $4.00 | - | 5 | Replicate |
| Llama 4 Mavericklisted 2025-04-05 | $0.200 | $0.600 | 131K | 3 | Vercel AI Gateway |
| Gemma 3 12Blisted 2025-03-13 | $0.050 | $0.100 | 131K | 5 | DeepInfra |
| Gemma 3 27Blisted 2025-03-12 | $0.060 | $0.160 | 128K | 7 | Nebius |
| Qwen2.5 VL 72B Instructlisted 2025-02-01 | $0.130 | $0.400 | 131K | 5 | Nebius |
| DeepSeek R1 Distill Llama 70Blisted 2025-01-23 | $0.200 | $0.375 | 131K | 10 | DeepInfra |
| Phi-4listed 2025-01-10 | $0.070 | $0.140 | 16K | 3 | DeepInfra |
| Llama 3.3 70Blisted 2024-12-06 | $0.120 | $0.200 | 131K | 16 | Hyperbolic |
| Llama 3.2 3Blisted 2024-09-25 | $0.020 | $0.020 | 131K | 9 | DeepInfra |
| Llama 3.2 1B Instructlisted 2024-09-25 | $0.020 | $0.020 | 131K | 6 | Novita AI |
| Command R (08-2024)listed 2024-08-30 | $0.150 | $0.150 | 128K | 3 | Cohere |
| Command R+ (08-2024)listed 2024-08-30 | $1.56 | $1.56 | 128K | 3 | Oracle OCI |
| Hermes 3 405B Instructlisted 2024-08-16 | $1.00 | $1.00 | 131K | 3 | DeepInfra |
| Llama 3.1 8Blisted 2024-07-23 | $0.020 | $0.030 | 128K | 16 | Nebius |
| Llama 3.1 70B Instructlisted 2024-07-23 | $0.120 | $0.300 | 33K | 11 | Hyperbolic |
| Mistral Nemolisted 2024-07-19 | $0.019 | $0.030 | 131K | 9 | DeepInfra |
| GPT-4o-Minilisted 2024-07-18 | $0.150 | $0.600 | 128K | 6 | Azure AI Foundry |
| GPT-4 Turbolisted 2024-04-09 | $10.00 | $30.00 | 128K | 4 | Azure AI Foundry |
| GPT-OSS 120B | $0.030 | $0.170 | 131K | 21 | W&B Inference |
| DeepSeek R1 | $0.200 | $0.400 | 131K | 17 | Lambda |
| DeepSeek V3 | $0.200 | $0.200 | 33K | 16 | Hyperbolic |
| GPT-OSS 20B | $0.015 | $0.070 | 131K | 15 | Darkbloom |
| Llama 4 Scout | $0.050 | $0.100 | 16K | 11 | Lambda |
| GLM-4.7 | $0.400 | $1.50 | 203K | 11 | GMI Cloud |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | 10 | AWS Bedrock |
| Claude-3.7-Sonnet | $3.00 | $15.00 | 200K | 10 | AWS Bedrock |
| Claude Sonnet 4 | $3.00 | $15.00 | 1000K | 10 | AWS Bedrock |
| Claude Sonnet 4.5 | $3.00 | $15.00 | 200K | 10 | AWS Bedrock |
| DeepSeek V3.2 | $0.260 | $0.380 | 164K | 10 | DeepInfra |
| DeepSeek-V3.1 | $0.250 | $0.950 | 164K | 10 | DeepInfra |
| DeepSeek V4 Pro | $0.435 | $0.870 | 1000K | 10 | Tencent |
| Kimi K2.5 | $0.450 | $2.25 | 262K | 10 | DeepInfra |
| Qwen3 235B A22B | $0.071 | $0.100 | 262K | 10 | OpenRouter |
| Claude Opus 4 | $5.00 | $25.00 | 200K | 9 | Snowflake |
| Llama 4 Maverick | $0.050 | $0.100 | 131K | 9 | Lambda |
| GLM-4.6 | $0.400 | $1.75 | 203K | 9 | OpenRouter |
| Claude Opus 4.5 | $5.00 | $25.00 | 200K | 8 | AWS Bedrock |
| Claude Sonnet 4.6 | $3.00 | $15.00 | 1000K | 8 | AWS Bedrock |
| GPT-5 | $1.25 | $10.00 | 272K | 8 | Azure AI Foundry |
| Gemini 2.5 Flash | $0.150 | $0.600 | 1049K | 8 | Oracle OCI |
| Claude-3.5-Sonnet | $3.00 | $15.00 | 1000K | 7 | AWS Bedrock |
| Claude Opus 4.1 | $15.00 | $75.00 | 200K | 7 | AWS Bedrock |
| Claude Opus 4.6 | $5.00 | $25.00 | 1000K | 7 | AWS Bedrock |
| Claude Opus 4.7 | $5.00 | $25.00 | 1000K | 7 | AWS Bedrock |
| Claude Opus 5 | $5.00 | $25.00 | 1000K | 7 | AWS Bedrock |
| Llama-3-70b | $0.120 | $0.300 | 131K | 7 | Hyperbolic |
| GPT-5 Mini | $0.250 | $1.20 | 272K | 7 | Azure AI Foundry |
| GPT-5 Nano | $0.050 | $0.400 | 272K | 7 | Azure AI Foundry |
| Mistral Large | $0.500 | $1.50 | 262K | 7 | Mistral AI |
| MiniMax M2.5 | $0.300 | $1.10 | 1000K | 7 | AWS Bedrock |
| QwQ-32B | $0.150 | $0.200 | 131K | 7 | DeepInfra |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1049K | 7 | Databricks |
| Qwen3-Coder-480b-A35b-Instruct | $0.220 | $1.50 | 262K | 7 | Google Vertex AI |
| GLM-5 | $0.600 | $2.08 | 203K | 7 | DeepInfra |
| GPT-4o | $2.50 | $10.00 | 128K | 6 | Azure AI Foundry |
| GPT-4.1 | $2.00 | $8.00 | 1048K | 6 | Azure AI Foundry |
| Llama 3.1 405B | $0.120 | $0.300 | 33K | 6 | Hyperbolic |
| Grok-4 | $3.00 | $15.00 | 131K | 6 | Azure AI Foundry |
| MiniMax M2.1 | $0.270 | $1.20 | 204K | 6 | OpenRouter |
| GLM-5.1 | $1.05 | $3.50 | 203K | 6 | OpenRouter |
| Gemini-3-Pro | $2.00 | $12.00 | 1049K | 6 | Google Vertex AI |
| MiniMax M2 | $0.255 | $1.02 | 205K | 6 | OpenRouter |
| Qwen3.5 397B A17B | $0.450 | $3.00 | 262K | 6 | DeepInfra |
| Claude-3.5-Haiku | $0.800 | $4.00 | 200K | 5 | AWS Bedrock |
| Claude 3 Haiku | $0.250 | $1.25 | 200K | 5 | AWS Bedrock |
| Claude-3-Opus | $15.00 | $75.00 | 200K | 5 | AWS Bedrock |
| Llama-3-8b | $0.030 | $0.040 | 8K | 5 | DeepInfra |
| Mixtral-8x7B-Instruct-V0.1 | $0.150 | $0.150 | 16K | 5 | Anyscale |
| O1 | $15.00 | $60.00 | 200K | 5 | Azure AI Foundry |
| o3 Mini | $1.10 | $4.40 | 200K | 5 | Azure AI Foundry |
| GPT-4.1 Mini | $0.400 | $1.60 | 1048K | 5 | Azure AI Foundry |
| GPT-4.1 Nano | $0.100 | $0.400 | 1048K | 5 | Azure AI Foundry |
| GPT-5.2 | $1.75 | $14.00 | 272K | 5 | Azure AI Foundry |
| Llama-3.2-11b-Vision-Instruct | $0.049 | $0.049 | 128K | 5 | Cloudflare |
| Llama-Guard-3-8B | $0.020 | $0.030 | 128K | 5 | Nebius |
| DeepSeek R1 Distill Qwen 32B | $0.150 | $0.150 | - | 5 | Nscale |
| GLM-4.7 Flash | $0.060 | $0.400 | 203K | 5 | DeepInfra |
| Qwen2p5-Coder-32b | $0.060 | $0.200 | - | 5 | Nscale |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1049K | 5 | Google Vertex AI |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1049K | 5 | Google Vertex AI |
| Gemini 3 Flash Preview | $0.500 | $3.00 | 1049K | 5 | Google Vertex AI |
| Qwen3 235B A22B Thinking 2507 | $0.110 | $0.600 | 262K | 5 | OpenRouter |
| Command-R-Plus | $2.50 | $10.00 | 128K | 4 | Cohere |
| GPT-3.5 Turbo | $0.500 | $1.50 | 16K | 4 | Vercel AI Gateway |
| Grok-3 | $3.00 | $15.00 | 131K | 4 | Azure AI Foundry |
| Grok-3-Mini | $0.250 | $0.500 | 131K | 4 | Azure AI Foundry |
| Ministral 3 3B 2512 | $0.040 | $0.040 | 128K | 4 | Azure AI Foundry |
| Mistral-7b | $0.070 | $0.130 | 4K | 4 | Perplexity |
| Mixtral 8x7B | $0.070 | $0.280 | 4K | 4 | Perplexity |
| Llama3.1-70b | $0.120 | $0.300 | 131K | 4 | Lambda |
| Llama3.1-8b | $0.025 | $0.040 | 131K | 4 | Lambda |
| MythoMax 13B | $0.090 | $0.090 | 4K | 4 | Novita AI |
| Qwen2p5-72b | $0.120 | $0.300 | 131K | 4 | Hyperbolic |
| Gemini-2.0-Flash-001 | $0.100 | $0.400 | 1000K | 4 | DeepInfra |
| Mistral Small 3.2 24B | $0.075 | $0.200 | 128K | 4 | DeepInfra |
| Llama3.3-70b | $0.120 | $0.300 | 131K | 4 | Lambda |
| Pixtral-12b | $0.150 | $0.150 | 128K | 4 | Mistral AI |
| Qwen2.5-Coder-7B | $0.010 | $0.030 | - | 4 | Nscale |
| Qwen3.5 35B A3B | $0.140 | $1.00 | 262K | 4 | DeepInfra |
| Qwen3.5-122B-A10B | $0.250 | $1.75 | 262K | 4 | Libertai |
| Jamba-1.5-Large | $2.00 | $8.00 | 256K | 3 | AWS Bedrock |
| Jamba-1.5-Mini | $0.200 | $0.400 | 256K | 3 | AWS Bedrock |
| Gemma-7b-It | $0.050 | $0.080 | 8K | 3 | Groq |
| GPT-4 | $30.00 | $60.00 | 8K | 3 | Azure AI Foundry |
| GPT-5-Chat | $1.25 | $10.00 | 128K | 3 | Azure AI Foundry |
| GPT-5.2 Chat | $1.75 | $14.00 | 128K | 3 | Azure AI Foundry |
| Llama-3-2-90b-Vision-Instruct | $2.00 | $2.00 | 128K | 3 | Oracle OCI |
| Grok-4-1-Fast-Non-Reasoning | $0.200 | $0.500 | 131K | 3 | Azure AI Foundry |
| Grok-4-1-Fast-Reasoning | $0.200 | $0.500 | 131K | 3 | Azure AI Foundry |
| Grok-Code-Fast-1 | $0.200 | $1.50 | 131K | 3 | Azure AI Foundry |
| Mistral-Large-3 | $0.500 | $1.20 | 256K | 3 | Azure AI Foundry |
| Mistral-Medium | $0.400 | $2.00 | 131K | 3 | Azure AI Foundry |
| Mistral Small 3.1 24B | $0.100 | $0.300 | 131K | 3 | OpenRouter |
| Command-R | $0.150 | $0.600 | 128K | 3 | Cohere |
| Llama-2-70b-Chat | $0.500 | $1.50 | 4K | 3 | Databricks |
| MiMo-V2.5-Pro | $0.522 | $1.04 | 1049K | 3 | Novita AI |
| MiMo-V2.5 | $0.168 | $0.336 | 1049K | 3 | Novita AI |
| Qwen3.5 27B | $0.260 | $2.40 | 262K | 3 | DeepInfra |
| Nemotron 3.5 Lightning | $0.050 | $0.200 | 262K | 2 | OpenRouter |
| Qwen3.6 Plus | $0.325 | $1.95 | 1000K | 2 | OpenRouter |
| Qwen3 Coder | $0.220 | $0.950 | 262K | 2 | OpenRouter |
Sources: LiteLLM + OpenRouter + Helicone cross-check · refreshed 2026-08-28 · GPU quotes 2026-08-28