Compare

Side by side model comparisons for high intent pricing and context questions.

102 featured pairs. Each page shows input and output rates, context windows, and tokenizer accuracy.

All comparisons

GPT-5 vs Claude Opus 4.8: $1.25 vs $5.00 input per 1M
GPT-5 vs Gemini 3.1 Pro: $1.25 vs $2.00 input per 1M
Claude Opus 4.8 vs Gemini 3.1 Pro: $5.00 vs $2.00 input per 1M
GPT-4.1 vs Claude Sonnet 5: $2.00 vs $2.00 input per 1M
GPT-4.1 vs Gemini 2.5 Pro: $2.00 vs $1.25 input per 1M
Claude Sonnet 5 vs Gemini 2.5 Pro: $2.00 vs $1.25 input per 1M
GPT-5 Mini vs Claude Sonnet 4.6: $0.250 vs $3.00 input per 1M
GPT-4.1 Mini vs Claude Haiku 4.5: $0.400 vs $1.00 input per 1M
GPT-4o mini vs Gemini 2.5 Flash: $0.150 vs $0.300 input per 1M
Gemini 2.5 Flash vs Claude Haiku 4.5: $0.300 vs $1.00 input per 1M
Gemini 3 Flash vs GPT-5 Mini: $0.500 vs $0.250 input per 1M
GPT-4.1 Nano vs Gemini 2.5 Flash-Lite: $0.100 vs $0.100 input per 1M
Claude Haiku 4.5 vs Gemini 2.5 Flash-Lite: $1.00 vs $0.100 input per 1M
DeepSeek V4 Flash vs GPT-4.1 Nano: $0.140 vs $0.100 input per 1M
DeepSeek V4 Flash vs Gemini 3.1 Flash-Lite: $0.140 vs $0.250 input per 1M
DeepSeek V4 Pro vs GPT-4o mini: $0.435 vs $0.150 input per 1M
o3 vs Claude Opus 4.6: $2.00 vs $5.00 input per 1M
o4-mini vs GPT-5 Mini: $1.10 vs $0.250 input per 1M
Grok 4 vs GPT-5: $3.00 vs $1.25 input per 1M
Mistral Large 3 vs GPT-4.1 Mini: $0.500 vs $0.400 input per 1M
GPT-5 Nano vs Gemini 2.0 Flash-Lite: $0.050 vs $0.075 input per 1M
Command R vs GPT-4o mini: $0.150 vs $0.150 input per 1M
Command R+ vs Claude Sonnet 4.6: $2.50 vs $3.00 input per 1M
Llama 3.3 70B (Groq) vs Llama 3.3 70B (Together): $0.590 vs $0.880 input per 1M
Grok 4 Fast vs GPT-5 Mini: $0.200 vs $0.250 input per 1M
DeepSeek V3 vs DeepSeek V3 (Together): $0.270 vs $1.25 input per 1M
DeepSeek V3 vs DeepSeek V3 (Fireworks): $0.270 vs $0.900 input per 1M
Mixtral 8x7B (Groq) vs Llama 3.3 70B (Groq): $0.240 vs $0.590 input per 1M
Mixtral 8x22B (Together) vs Mixtral 8x22B (Fireworks): $1.20 vs $0.900 input per 1M
Llama 3.1 8B Instant (Groq) vs Llama 3.1 8B (Together): $0.050 vs $0.180 input per 1M
Command R7B vs GPT-5 Nano: $0.037 vs $0.050 input per 1M
Claude 3.5 Haiku vs Claude Haiku 4.5: $0.800 vs $1.00 input per 1M
Gemini 1.5 Flash vs Gemini 2.5 Flash: $0.075 vs $0.300 input per 1M
o1 vs o3: $15.00 vs $2.00 input per 1M
Mistral Nemo vs Mistral Small: $0.150 vs $0.060 input per 1M
Llama 3.1 70B (Together) vs Llama 3.3 70B (Groq): $0.880 vs $0.590 input per 1M
Llama 3.1 70B (Fireworks) vs Llama 3.1 70B (Together): $0.900 vs $0.880 input per 1M
Claude 3 Opus vs Claude Opus 4.8: $15.00 vs $5.00 input per 1M
Claude 3 Sonnet vs Claude Sonnet 5: $3.00 vs $2.00 input per 1M
GPT-3.5 Turbo vs GPT-4o mini: $0.500 vs $0.150 input per 1M
DeepSeek Coder vs Codestral: $0.140 vs $1.00 input per 1M
Qwen2.5 Coder 32B (Together) vs Codestral: $0.800 vs $1.00 input per 1M
Llama 3.2 1B (Groq) vs Llama 3.2 3B (Groq): $0.040 vs $0.060 input per 1M
Command Light vs Command R7B: $0.300 vs $0.037 input per 1M
GPT-4 vs GPT-4.1: $30.00 vs $2.00 input per 1M
Claude 3 Haiku vs Claude 3.5 Haiku: $0.250 vs $0.800 input per 1M
Gemini 1.5 Flash-8B vs Gemini 2.5 Flash-Lite: $0.037 vs $0.100 input per 1M
Open Mixtral 8x7B vs Mixtral 8x7B (Groq): $0.700 vs $0.240 input per 1M
Llama 3.2 3B (Groq) vs Llama 3.2 3B (Together): $0.060 vs $0.060 input per 1M
Llama 3.2 3B (Together) vs Llama 3.2 3B (Fireworks): $0.060 vs $0.100 input per 1M
Gemma 7B (Groq) vs Gemma 2 9B (Groq): $0.070 vs $0.200 input per 1M
Command R+ (08-2024) vs Command R+: $2.50 vs $2.50 input per 1M
DeepSeek VL vs Pixtral 12B: $0.140 vs $0.150 input per 1M
o1-mini vs o4-mini: $1.10 vs $1.10 input per 1M
Claude 3.5 Sonnet vs Claude Sonnet 5: $3.00 vs $2.00 input per 1M
DeepSeek R1 vs DeepSeek R1 (Together): $0.550 vs $3.00 input per 1M
DeepSeek R1 vs DeepSeek R1 (Fireworks): $0.550 vs $0.900 input per 1M
Llama 4 Maverick (Together) vs Llama 4 Maverick (Fireworks): $0.270 vs $0.220 input per 1M
Llama 4 Scout (Groq) vs Llama 4 Maverick (Together): $0.110 vs $0.270 input per 1M
Open Mixtral 8x22B vs Mixtral 8x22B (Together): $2.00 vs $1.20 input per 1M
QwQ 32B (Groq) vs Qwen3 32B (Groq): $0.290 vs $0.290 input per 1M
GPT-4.1 (2025-04-14) vs GPT-4.1: $2.00 vs $2.00 input per 1M
GPT-5 vs Claude Sonnet 5: $1.25 vs $2.00 input per 1M
GPT-4o vs Claude Sonnet 5: $2.50 vs $2.00 input per 1M
GPT-4o vs Gemini 2.5 Pro: $2.50 vs $1.25 input per 1M
GPT-5 Mini vs Gemini 2.5 Flash: $0.250 vs $0.300 input per 1M
GPT-4.1 Mini vs Gemini 2.5 Flash: $0.400 vs $0.300 input per 1M
Claude Sonnet 4.6 vs Gemini 2.5 Flash: $3.00 vs $0.300 input per 1M
Claude Opus 4.6 vs GPT-5: $5.00 vs $1.25 input per 1M
Gemini 3.1 Pro vs Claude Sonnet 5: $2.00 vs $2.00 input per 1M
GPT-4o mini vs Claude Haiku 4.5: $0.150 vs $1.00 input per 1M
GPT-5 Nano vs Claude Haiku 4.5: $0.050 vs $1.00 input per 1M
GPT-4.1 Nano vs DeepSeek V4 Flash: $0.100 vs $0.140 input per 1M
Ministral 8B vs GPT-5 Nano: $0.150 vs $0.050 input per 1M
Mistral Small vs GPT-4o mini: $0.060 vs $0.150 input per 1M
Command R7B vs Gemini 2.5 Flash-Lite: $0.037 vs $0.100 input per 1M
DeepSeek Chat vs GPT-4o mini: $0.280 vs $0.150 input per 1M
Grok 3 Mini vs GPT-5 Mini: $0.300 vs $0.250 input per 1M
o3 vs DeepSeek R1: $2.00 vs $0.550 input per 1M
o3-mini vs o4-mini: $1.10 vs $1.10 input per 1M
DeepSeek Reasoner vs o4-mini: $0.550 vs $1.10 input per 1M
DeepSeek R1 Distill Qwen 32B vs DeepSeek R1 Distill Llama 70B (Groq): $0.300 vs $0.750 input per 1M
o1-preview vs o1: $15.00 vs $15.00 input per 1M
Llama 3.3 70B (Groq) vs Llama 3.3 70B (Fireworks): $0.590 vs $0.900 input per 1M
Llama 3.3 70B (Together) vs Llama 3.3 70B (Fireworks): $0.880 vs $0.900 input per 1M
DeepSeek V3 (Together) vs DeepSeek V3 (Fireworks): $1.25 vs $0.900 input per 1M
Qwen2.5 72B (Together) vs Qwen2.5 72B (Fireworks): $1.20 vs $0.900 input per 1M
Llama 3.1 8B Instant (Groq) vs Llama 3.1 8B (Fireworks): $0.050 vs $0.200 input per 1M
Open Mixtral 8x22B vs Mixtral 8x22B (Fireworks): $2.00 vs $0.900 input per 1M
DeepSeek R1 (Together) vs DeepSeek R1 (Fireworks): $3.00 vs $0.900 input per 1M
Codestral vs GPT-4.1 Mini: $1.00 vs $0.400 input per 1M
DeepSeek Coder vs Qwen2.5 Coder 32B (Together): $0.140 vs $0.800 input per 1M
Pixtral 12B vs Llama 3.2 11B Vision (Groq): $0.150 vs $0.180 input per 1M
Grok 2 Vision vs Pixtral 12B: $2.00 vs $0.150 input per 1M
GPT-4 Turbo vs GPT-4o: $10.00 vs $2.50 input per 1M
GPT-4o vs GPT-4.1: $2.50 vs $2.00 input per 1M
Gemini 1.5 Pro vs Gemini 2.5 Pro: $1.25 vs $1.25 input per 1M
Gemini 2.0 Flash vs Gemini 2.5 Flash: $0.100 vs $0.300 input per 1M
Grok 3 vs Grok 4: $3.00 vs $3.00 input per 1M
Mistral Large (2407) vs Mistral Large 3: $2.00 vs $0.500 input per 1M
Command A vs Command R+: $2.50 vs $2.50 input per 1M
Claude 2.1 vs Claude Opus 4.8: $8.00 vs $5.00 input per 1M

Open calculator

Browse models