| Model | Provider | |||||||
|---|---|---|---|---|---|---|---|---|
Llama 3.2 1B Instruct meta-llama | Lepton | #147 | $0.01 | 0.33s | 323.6T/s | 100.00% | ||
Gemini Flash 1.5 8B google | Google AI Studio | #65 | $0.04 | 0.52s | 182.0T/s | 98.30% | ||
MythoMax 13B gryphe | Fireworks | - | $0.07 | 0.23s | 110.6T/s | 100.00% | ||
Gemini Flash 1.5 google | Google AI Studio | #26 | $0.08 | 3.92s | 174.4T/s | 100.00% | ||
DeepSeek V3 deepseek | DeepSeek | #8 | $0.14 | 1.49s | 54.0T/s | 99.72% | ||
GPT-4o-mini openai | OpenAI | #23 | $0.15 | 0.56s | 69.1T/s | 99.33% | ||
Mistral Nemo mistralai | Mistral | - | $0.04 | 0.28s | 106.3T/s | 100.00% | ||
Llama 3.1 70B Instruct meta-llama | Fireworks | #38 | $0.12 | 0.43s | 100.2T/s | 100.00% | ||
Mistral Tiny mistralai | Mistral | #136 | $0.25 | 0.21s | 89.9T/s | 100.00% | ||
Llama 3.3 70B Instruct meta-llama | Together | #22 | $0.12 | 0.85s | 157.3T/s | 99.98% | ||
Qwen2.5 72B Instruct qwen | Fireworks | #37 | $0.23 | 0.35s | 85.0T/s | 100.00% | ||
Ministral 3B mistralai | Mistral | - | $0.04 | 0.18s | 119.4T/s | 100.00% | ||
Ministral 8B mistralai | Mistral | #81 | $0.10 | 0.22s | 97.0T/s | 100.00% | ||
Claude 3.5 Sonnet anthropic | Anthropic | #8 | $3.12 | 2.70s | 62.0T/s | 99.55% | ||
Claude 3.5 Sonnet (self-moderated) anthropic | Anthropic | - | $3.12 | 2.70s | 62.0T/s | 99.96% | ||
Qwen2.5 Coder 32B Instruct qwen | Fireworks | #56 | $0.07 | 0.77s | 93.1T/s | 100.00% | ||
Command R (08-2024) cohere | Cohere | #68 | $0.15 | 0.28s | 90.2T/s | 100.00% | ||
Gemma 2 27B google | Together | #43 | $0.27 | 0.49s | 54.9T/s | 100.00% | ||
GPT-4o-mini (2024-07-18) openai | OpenAI | #23 | $0.15 | 0.47s | 87.3T/s | 100.00% | ||
Llama 3.1 8B Instruct meta-llama | Together | #101 | $0.02 | 0.35s | 302.6T/s | 100.00% | ||
Hermes 3 405B Instruct nousresearch | DeepInfra | #15 | $0.81 | 0.53s | 19.1T/s | 99.90% | ||
OpenChat 3.5 7B openchat | Lepton | #118 | $0.06 | 0.44s | 90.6T/s | 100.00% | ||
WizardLM-2 8x22B microsoft | Together | - | $0.50 | 0.80s | 61.1T/s | 100.00% | ||
Llama 3 70B Instruct meta-llama | Fireworks | #54 | $0.23 | 0.44s | 141.5T/s | 100.00% | ||
Llama 3 8B Instruct meta-llama | Fireworks | #91 | $0.03 | 0.30s | 216.9T/s | 100.00% | ||
Gemini Flash 2.0 Experimental (free) google | Google AI Studio | #4 | $0.00 | 2.06s | 138.6T/s | 60.43% | ||
Grok 2 1212 x-ai | xAI | - | $2.08 | 0.52s | 68.0T/s | 99.93% | ||
Qwen2-VL 72B Instruct qwen | Hyperbolic | - | $0.40 | 4.66s | 7.8T/s | 95.89% | ||
Llama 3.2 1B Instruct (free) meta-llama | SambaNova | #147 | $0.00 | 0.41s | 2137.9T/s | 98.58% | ||
Llama 3.2 3B Instruct meta-llama | Fireworks | #119 | $0.02 | 0.33s | 217.9T/s | 100.00% | ||
Rocinante 12B thedrummer | Infermatic | - | $0.25 | 0.76s | 22.1T/s | 100.00% | ||
Magnum v4 72B anthracite-org | Infermatic | - | $1.89 | 1.24s | 31.6T/s | 99.99% | ||
Claude 3.5 Haiku anthropic | Google Vertex | #24 | $0.83 | 2.29s | 62.1T/s | 99.99% | ||
Claude 3.5 Haiku (self-moderated) anthropic | Anthropic | - | $0.83 | 2.58s | 53.2T/s | 95.94% | ||
Unslopnemo 12b thedrummer | Infermatic | - | $0.50 | 0.63s | 68.4T/s | 100.00% | ||
Mistral Large 2411 mistralai | Mistral | #38 | $2.05 | 0.59s | 41.6T/s | 99.99% | ||
GPT-4o (2024-11-20) openai | OpenAI | #1 | $2.58 | 0.55s | 87.5T/s | 99.97% | ||
Llama 3.1 405B Instruct meta-llama | Fireworks | - | $0.81 | 0.77s | 58.9T/s | 99.99% | ||
Hermes 3 70B Instruct nousresearch | Hyperbolic | #43 | $0.12 | 0.73s | 31.7T/s | 99.97% | ||
Llama 3.1 Euryale 70B v2.2 sao10k | DeepInfra | - | $0.35 | 0.63s | 35.1T/s | 100.00% | ||
GPT-4 openai | Azure | - | $30.48 | 1.23s | 37.6T/s | 96.00% | ||
GPT-3.5 Turbo 16k openai | OpenAI | #98 | $0.51 | 0.28s | 113.1T/s | 95.99% | ||
GPT-3.5 Turbo openai | OpenAI | #96 | $0.51 | 0.42s | 115.0T/s | 99.95% | ||
MythoMax 13B (nitro) gryphe | Fireworks | - | $0.20 | 0.23s | 110.6T/s | 100.00% | ||
Hermes 13B nousresearch | NovitaAI | - | $0.17 | 0.59s | 81.9T/s | 100.00% | ||
OpenHermes 2.5 Mistral 7B teknium | NovitaAI | #120 | $0.17 | 0.81s | 65.6T/s | 100.00% | ||
Mixtral 8x7B Instruct mistralai | Fireworks | #111 | $0.24 | 0.39s | 139.0T/s | 100.00% | ||
Mistral Small mistralai | Mistral | - | $0.20 | 0.65s | 60.2T/s | 100.00% | ||
Claude 3 Haiku anthropic | Google Vertex | - | $0.26 | 1.11s | 134.0T/s | 100.00% | ||
Claude 3 Haiku (self-moderated) anthropic | Anthropic | - | $0.26 | 1.09s | 129.7T/s | 99.83% | ||
Gemini Pro 1.5 google | Google AI Studio | #9 | $1.29 | 1.88s | 49.2T/s | 99.56% | ||
WizardLM-2 7B microsoft | Lepton | - | $0.06 | 0.29s | 76.4T/s | 100.00% | ||
Mixtral 8x22B Instruct mistralai | Mistral | #86 | $0.91 | 0.33s | 79.9T/s | 100.00% | ||
GPT-4o (extended) openai | OpenAI | - | $6.14 | 0.82s | 93.6T/s | 76.00% | ||
GPT-4o openai | OpenAI | - | $2.58 | 1.02s | 140.9T/s | 100.00% | ||
Hermes 2 Pro - Llama-3 8B nousresearch | Lambda | - | $0.03 | 0.52s | 101.3T/s | 99.88% | ||
Mistral 7B Instruct (nitro) mistralai | Lepton | - | $0.07 | 0.42s | 87.9T/s | 52.00% | ||
Mistral 7B Instruct mistralai | Together | #136 | $0.03 | 0.30s | 139.9T/s | 100.00% | ||
Mistral 7B Instruct (free) mistralai | Lepton | - | $0.00 | 0.42s | 87.9T/s | 95.99% | ||
Dolphin 2.9.2 Mixtral 8x22B 🐬 cognitivecomputations | NovitaAI | - | $0.91 | 1.82s | 24.0T/s | 99.11% | ||
Claude 3.5 Sonnet (2024-06-20) anthropic | Anthropic | - | $3.12 | 1.42s | 60.1T/s | 99.99% | ||
Claude 3.5 Sonnet (2024-06-20) (self-moderated) anthropic | Anthropic | - | $3.12 | 1.42s | 60.1T/s | 99.98% | ||
Gemma 2 9B google | DeepInfra | #65 | $0.03 | 0.47s | 49.0T/s | 100.00% | ||
Nova Lite 1.0 amazon | Amazon BedRock | #63 | $0.06 | 0.53s | 73.6T/s | 96.00% | ||
Llama 3.2 11B Vision Instruct meta-llama | Together | - | $0.06 | 0.82s | 122.1T/s | 100.00% | ||
Llama 3.1 Nemotron 70B Instruct nvidia | Infermatic | #38 | $0.12 | 1.43s | 30.1T/s | 95.95% | ||
Qwen2.5 7B Instruct qwen | Together | - | $0.27 | 0.75s | 130.9T/s | 96.00% | ||
Nova Pro 1.0 amazon | Amazon BedRock | - | $0.83 | 0.56s | 75.9T/s | 95.99% | ||
Command R+ (08-2024) cohere | Cohere | #48 | $2.45 | 0.62s | 57.5T/s | 99.96% | ||
Codestral Mamba mistralai | Mistral | - | $0.25 | 0.43s | 91.3T/s | 96.00% | ||
Llama 3.1 70B Instruct (free) meta-llama | SambaNova | - | $0.00 | 1.68s | 391.9T/s | 88.29% | ||
Llama 3.1 Sonar 70B Online perplexity | Perplexity | #130 | $1.01 | 1.43s | 55.7T/s | 99.99% | ||
GPT-4o (2024-08-06) openai | Azure | #15 | $2.58 | 10.44s | 97.4T/s | 99.98% | ||
ChatGPT-4o openai | OpenAI | - | $5.12 | 0.69s | 94.3T/s | 99.88% | ||
Llama 3.1 Sonar 405B Online perplexity | Perplexity | - | $5.04 | 2.25s | 19.8T/s | 97.33% | ||
GPT-4 Turbo (older v1106) openai | OpenAI | #24 | $10.24 | 1.18s | 31.9T/s | 95.99% | ||
OpenChat 3.5 7B (free) openchat | Lepton | - | $0.00 | 0.51s | 83.8T/s | 96.00% | ||
Mistral Large mistralai | Mistral | #26 | $2.05 | 0.72s | 31.2T/s | 99.95% | ||
Claude 3 Sonnet anthropic | Anthropic | - | $3.12 | 1.49s | 64.1T/s | 99.95% | ||
Claude 3 Sonnet (self-moderated) anthropic | Anthropic | - | $3.12 | 1.49s | 64.1T/s | 100.00% | ||
Claude 3 Opus anthropic | Anthropic | - | $15.60 | 2.92s | 26.6T/s | 99.98% | ||
Llama 3 70B Instruct (nitro) meta-llama | Fireworks | - | $0.80 | 0.44s | 141.5T/s | 100.00% | ||
Llama 3 8B Instruct (free) meta-llama | Together (lite) | - | $0.00 | 0.58s | 181.0T/s | 100.00% | ||
LlamaGuard 2 8B meta-llama | Together | - | $0.18 | 0.41s | 45.1T/s | 100.00% | ||
Llama 3 Euryale 70B v2.1 sao10k | DeepInfra | - | $0.35 | 0.17s | 40.1T/s | 100.00% | ||
Gemma 2 9B (free) google | DeepInfra | - | $0.00 | 0.53s | 48.8T/s | 100.00% |
Created by JC, data from OpenRouter and Chatbot Arena