claude-3.5-haiku
vercel_ai_gateway · chat model
Input
$0.8000 / 1M tokens
Output
$4.0000 / 1M tokens
Cached input
$0.0800 / 1M tokens
Context
8.2K
Pricing
| Item | Raw value (per token) | Normalized |
|---|---|---|
| Input | 8e-7 | $0.8000 / 1M tokens |
| Output | 0.000004 | $4.0000 / 1M tokens |
| Cached input | 8e-8 | $0.0800 / 1M tokens |
| Cache write | N/A | $1.0000 / 1M tokens |
| Embedding | 8e-7 | $0.8000 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
200.0K
Max output tokens
8.2K
Max tokens
8.2K
Capabilities
| Capability | Supported |
|---|---|
| Vision | Yes |
| Function calling | Yes |
| Parallel function calling | No |
| Tool choice | Yes |
| Prompt caching | No |
| Reasoning | No |
| Response schema | Yes |
| System messages | No |
| Audio input | No |
| Audio output | No |
| Web search | No |
| PDF input | No |
| Video input | No |
Similar models
Models with comparable pricing in the same mode (chat).
| Model | Provider | Input | Output | Context | Coding | Features |
|---|---|---|---|---|---|---|
| anthropic.claude-3-5-haiku-20241022-v1:0 | Bedrock | $0.8000 / 1M tokens | $4.0000 / 1M tokens | 8.2K | N/A | Tools Cache |
| us.anthropic.claude-3-5-haiku-20241022-v1:0 | Bedrock | $0.8000 / 1M tokens | $4.0000 / 1M tokens | 8.2K | N/A | Tools Cache |
| anthropic-claude-3.5-haiku | gradient_ai | $0.8000 / 1M tokens | $4.0000 / 1M tokens | 1.0K | N/A | |
| us.anthropic.claude-3-5-haiku-20241022-v1:0 | Bedrock | $0.8000 / 1M tokens | $4.0000 / 1M tokens | 8.2K | N/A | Tools Cache |
| kimi-k2.6 | moonshot | $0.9500 / 1M tokens | $4.0000 / 1M tokens | 262.1K | N/A | Vision Tools Reasoning |
| qwen3-vl-235b-a22b-thinking | novita | $0.9800 / 1M tokens | $3.9500 / 1M tokens | 32.8K | N/A | Vision Reasoning |
Sources
| Pricing source | LiteLLM model cost map |
| Synced at | 2026-05-27 |
| Manual review | Not reviewed |
Raw LiteLLM fields
{
"cache_creation_input_token_cost": 0.000001,
"cache_read_input_token_cost": 8e-8,
"input_cost_per_token": 8e-7,
"litellm_provider": "vercel_ai_gateway",
"max_input_tokens": 200000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.000004,
"supports_vision": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_response_schema": true
}