Transparent pricing for 15+ LLMs with zero markup
Model | Input ($/M tokens) | Output ($/M tokens) | Best For |
---|---|---|---|
openai/gpt-5 | $1.25 | $10.00 | Complex reasoning & analysis |
openai/gpt-5-mini | $0.25 | $2.00 | Cost-effective reasoning |
openai/gpt-5-nano | $0.05 | $0.40 | Balanced performance |
openai/o3 | $2.00 | $8.00 | Complex reasoning & analysis |
openai/o3-mini | $1.10 | $4.40 | Cost-effective reasoning |
openai/o4-mini | $1.10 | $4.40 | Balanced performance |
openai/gpt-4.1 | $2.00 | $8.00 | Advanced tasks |
openai/gpt-4.1-mini | $0.40 | $1.60 | Efficient advanced tasks |
openai/gpt-4o | $2.50 | $10.00 | Multimodal & complex queries |
openai/gpt-4o-mini | $0.15 | $0.60 | Fast, affordable searches |
Model | Input ($/M tokens) | Output ($/M tokens) | Best For |
---|---|---|---|
groq/openai-gpt-oss-120b | $0.15 | $0.75 | High-performance search |
groq/openai-gpt-oss-20b | $0.10 | $0.50 | Budget-friendly quality |
groq/kimi-k2 | $1.00 | $3.00 | High-performance search |
groq/qwen3-32b | $0.29 | $0.59 | Budget-friendly quality |
groq/llama-3.3-70b-versatile | $0.59 | $0.79 | Versatile applications |
groq/deepseek-r1-distill-llama-70b | $0.75 | $0.99 | Deep reasoning tasks |
groq/llama-4-maverick-17b-128e-instruct | $0.20 | $0.60 | Fast, efficient searches |
Model | Input ($/M tokens) | Output ($/M tokens) | Best For |
---|---|---|---|
anthropic/claude-sonnet-4 | $3.00 | $15.00 | highly creative writing and intelligent model |
Model | Input ($/M tokens) | Output ($/M tokens) | Best For |
---|---|---|---|
deepseek/deepseek-chat | $0.27 | $1.10 | General purpose chat |
deepseek/deepseek-reasoner | $0.55 | $2.19 | Complex reasoning |
How does pricing compare to using providers directly?
Can I bring my own API keys?
provider_key
parameter to be billed directly by the model provider. Youβll still pay $0.004 per search for our infrastructure.How often are prices updated?
Is there a free tier?