Claude 2.1: Intelligence, Performance & Price Analysis
Analysis of Anthropic's Claude 2.1 and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Anthropic has launched a newer model, Claude 3 Sonnet. We suggest considering this model instead of Claude 2.1. See the following pages for a comparison of Claude 3 Sonnet to other models and Claude 3 Sonnet API provider benchmarks.
Comparison Summary
Intelligence:
Claude 2.1 is of lower quality compared to average, with a MMLU score of 0.495 and a Intelligence Index across evaluations of 24.
Price:Claude 2.1 is more expensive compared to average with a price of $12.00 per 1M Tokens (blended 3:1).
Claude 2.1 Input token price: $8.00, Output token price: $24.00 per 1M Tokens.
Speed:Claude 2.1 Input token price: $8.00, Output token price: $24.00 per 1M Tokens.
Claude 2.1 is slower compared to average, with a output speed of 13.9 tokens per second.
Latency:Claude 2.1 has a lower latency compared to average, taking 1.20s to receive the first token (TTFT).
Context Window:Claude 2.1 has a smaller context windows than average, with a context window of 200k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Claude 2.1 Model Details
Comparisons to Claude 2.1
o4-mini (high)
o3
GPT-4.1
o3-pro
Llama 4 Maverick
Llama 4 Scout
Gemini 2.5 Flash (Reasoning)
Gemini 2.5 Pro
Claude 4 Sonnet
Claude 4 Sonnet (Extended Thinking)
Claude 4 Opus (Extended Thinking)
Mistral Medium 3
DeepSeek R1 0528 (May '25)
DeepSeek V3 0324 (Mar '25)
Grok 3 mini Reasoning (high)
Nova Premier
MiniMax M1 80k
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Qwen3 235B A22B (Reasoning)
GPT-4o (Nov '24)
Further details