Anthropic: Claude 3.5 Haiku
anthropic/claude-3.5-haiku
Claude 3.5 Haiku is Anthropic's budget option at $0.8/$4 per million input/output tokens, with a 200K-token context. It sits toward the back of the board on capability, at #192 of 235 on the TryAii Score, though its benchmark evidence has gone stale.
Prompt $/1M
$0.800
Completion $/1M
$4.000
Context
200,000 tok
Best provider
34 tok/s · Amazon Bedrock
Specs
- Model id
- anthropic/claude-3.5-haiku
- Display name
- Anthropic: Claude 3.5 Haiku
- Modality
- text+image->text
- Tokenizer
- Claude
- Instruct type
- —
- Context length
- 200,000
- Max completion
- 8,192
- Prompt $/1M
- $0.800
- Completion $/1M
- $4.000
- Free tier
- no
Capabilities
- Function callingyes
- JSON modeno
- System promptno
- Visionno
- Moderatedyes
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Amazon Bedrockfastest | 34 |
| anthropicfastest | — |
| Artificial Analysis | 0 |
Prompt caching by provider
| Provider | Min tokens to cache |
|---|---|
| Anthropic | 2,048 tokens |