Overview
Model specifications
- Context
- 200,000 tokens
- Maximum output
- 4,096 tokens
- Architecture
- text+image->text
- Tokenizer
- Claude
- Knowledge cutoff
- 2023-08-31
- Moderated
- Yes
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.25 /M tokens
- Output
- $1.25 /M tokens
- Cache read
- $0.03 /M tokens
- Cache write
- $0.3 /M tokens
- Cache Write (1h)
- $0.5 /M tokens
API
Quick start
Call this exact model ID through OpenRouter’s OpenAI-compatible API.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"anthropic/claude-3-haiku","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
textimage
Output
text
API
Supported API parameters
max_tokensstoptemperaturetool_choicetoolstop_ktop_pAvailable providers
1 Provider
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Amazon Bedrock
unknown- Context
- 200K
- Maximum output
- 4K
- Input
- $0.250
- Output
- $1.25
- Cache read
- $0.030
- Cache write
- $0.300