anthropic
anthropic/claude-3.5-haiku
Claude 3.5 Haiku
Fast and cost-effective.
- Base input
- $0.8800/1M tok
- Output
- $4.40/1M tok
- Cache read
- —/1M tok
- Context 200k
- Max out 8k
- ✓ tools
- ✓ streaming
Every model, one bill.
Real prices vs provider list. Cache-aware by default. Copy the model ID and ship.
8 / 8
anthropic
anthropic/claude-3.5-sonnet
Claude 3.5 Sonnet
Best-in-class reasoning and coding.
- Base input
- $3.30/1M tok
- Output
- $16.50/1M tok
- Cache read
- —/1M tok
- Context 200k
- Max out 8k
- ✓ tools
- ✓ vision
- ✓ streaming
deepseek
deepseek/deepseek-v3
DeepSeek V3
High quality at aggressive price.
- Base input
- $0.2970/1M tok
- Output
- $1.21/1M tok
- Cache read
- —/1M tok
- Context 128k
- Max out 8k
- ✓ tools
- ✓ streaming
google
google/gemini-2.0-flash
Gemini 2.0 Flash
Google fast multimodal with huge context.
- Base input
- $0.1100/1M tok
- Output
- $0.4400/1M tok
- Cache read
- —/1M tok
- Context 1000k
- Max out 8k
- ✓ tools
- ✓ vision
- ✓ streaming
meta
meta/llama-3.3-70b
Llama 3.3 70B
Open-weight high-performance model.
- Base input
- $0.2530/1M tok
- Output
- $0.4400/1M tok
- Cache read
- —/1M tok
- Context 128k
- Max out 8k
- ✓ tools
- ✓ streaming
mistral
mistral/mistral-large
Mistral Large
Mistral flagship.
- Base input
- $2.20/1M tok
- Output
- $6.60/1M tok
- Cache read
- —/1M tok
- Context 128k
- Max out 8k
- ✓ tools
- ✓ streaming
openai
openai/gpt-4o
GPT-4o
OpenAI flagship multimodal model.
- Base input
- $2.75/1M tok
- Output
- $11.00/1M tok
- Cache read
- —/1M tok
- Context 128k
- Max out 16k
- ✓ tools
- ✓ vision
- ✓ streaming
openai
openai/gpt-4o-mini
GPT-4o mini
Affordable OpenAI multimodal.
- Base input
- $0.1650/1M tok
- Output
- $0.6600/1M tok
- Cache read
- —/1M tok
- Context 128k
- Max out 16k
- ✓ tools
- ✓ vision
- ✓ streaming