| OpenRouter: meta-llama/llama-3.1-405b:free | S | — | — | — | — | — |
| OpenRouter: meta-llama/llama-3.1-405b-instruct:free | S | — | — | — | — | — |
| OpenRouter: meta-llama/llama-3.1-70b-instruct:free | S | — | — | — | — | — |
| OpenRouter: meta-llama/llama-3.1-8b-instruct:free | S | — | — | — | — | — |
| OpenRouter: nvidia/llama-3.1-nemotron-70b-instruct:free | S | — | — | — | — | — |
| OpenRouter: nvidia/llama-3.1-nemotron-nano-8b-v1:free | S | — | — | — | — | — |
| OpenRouter: nvidia/llama-3.1-nemotron-ultra-253b-v1:free | S | — | — | — | — | — |
| OpenRouter: meta-llama/llama-3.1-8b-instruct | S | — | — | — | — | $0.02$0.05 |
| Groq: llama-3.1-8b-instant | S | — | — | — | — | $0.05$0.08 |
| OpenRouter: neversleep/llama-3.1-lumimaid-8b | S | — | — | — | — | $0.09$0.6 |
| OpenRouter: tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.3 | S | — | — | — | — | $0.1$0.2 |
| OpenRouter: perplexity/llama-3.1-sonar-small-128k-chat | S | — | — | — | — | $0.2$0.2 |
| OpenRouter: perplexity/llama-3.1-sonar-small-128k-online | S | — | — | — | — | $0.2$0.2 |
| Perplexity: llama-3.1-sonar-small-128k-chat | S | — | — | — | — | $0.2$0.2 |
| Perplexity: llama-3.1-sonar-small-128k-online | S | — | — | — | — | $0.2$0.2 |
| Perplexity: llama-3.1-8b-instruct | S | — | — | — | — | $0.2$0.2 |
| Azure OpenAI: meta-llama-3.1-8b-instruct | S | — | — | — | — | $0.3$0.61 |
| OpenRouter: meta-llama/llama-3.1-70b-instruct | S | — | — | — | — | $0.4$0.4 |
| Groq: llama-3.1-70b | S | — | — | — | — | $0.59$0.79 |
| OpenRouter: nvidia/llama-3.1-nemotron-ultra-253b-v1 | S | — | — | — | — | $0.6$1.8 |
| OpenRouter: tokyotech-llm/llama-3.1-swallow-70b-instruct-v0.3 | S | — | — | — | — | $0.6$1.2 |
| OpenRouter: perplexity/llama-3.1-sonar-large-128k-chat | S | — | — | — | — | $1$1 |
| OpenRouter: perplexity/llama-3.1-sonar-large-128k-online | S | — | — | — | — | $1$1 |
| Perplexity: llama-3.1-70b-instruct | S | — | — | — | — | $1$1 |
| Perplexity: llama-3.1-sonar-large-128k-chat | S | — | — | — | — | $1$1 |
| Perplexity: llama-3.1-sonar-large-128k-online | S | — | — | — | — | $1$1 |
| OpenRouter: nvidia/llama-3.1-nemotron-70b-instruct | S | — | — | — | — | $1.2$1.2 |
| OpenRouter: neversleep/llama-3.1-lumimaid-70b | S | — | — | — | — | $2.5$3 |
| Azure OpenAI: meta-llama-3.1-70b-instruct | S | — | — | — | — | $2.68$3.54 |
| OpenRouter: meta-llama/llama-3.1-70b-instruct:nitro | S | — | — | — | — | $3.25$3.25 |
| OpenRouter: meta-llama/llama-3.1-405b-instruct | S | — | — | — | — | $4$4 |
| OpenRouter: meta-llama/llama-3.1-405b | S | — | — | — | — | $4$4 |
| OpenRouter: allenai/llama-3.1-tulu-3-405b | S | — | — | — | — | $5$10 |
| OpenRouter: perplexity/llama-3.1-sonar-huge-128k-online | S | — | — | — | — | $5$5 |
| Perplexity: llama-3.1-sonar-huge-128k-online | S | — | — | — | — | $5$5 |
| Azure OpenAI: meta-llama-3.1-405b-instruct | S | — | — | — | — | $5.33$16 |
| Replicate: meta/meta-llama-3.1-405b-instruct | S | — | — | — | — | $9.5$9.5 |
| OpenRouter: meta-llama/llama-3.1-405b-instruct:nitro | S | — | — | — | — | $14.62$14.62 |
| Workers AI: llama-3.1-8b-instruct-awq | S | — | — | — | — | $120000$270000 |
| Workers AI: llama-3.1-8b-instruct-fp8 | S | — | — | — | — | $150000$290000 |
| Workers AI: llama-3.1-8b-instruct | S | — | — | — | — | $280000$830000 |