Compact Claude 3 model with vision for fast, affordable inference.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Compact Claude 3 model with vision for fast, affordable inference. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Claude 3 Haiku (2024-03-07) on OffRail starts at $0.25 per million input tokens and $1.25 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Claude 3 Haiku (2024-03-07) supports a context window of up to 200,000 tokens on its largest provider deployment.
Claude 3 Haiku (2024-03-07) is served by Anthropic through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Claude 3 Haiku (2024-03-07) supports tool (function) calling, but not JSON output modes.
Claude 3 Haiku (2024-03-07) was released on March 4, 2024.
Claude Opus 5
1,000,000 context$5.00 in / $25.00 out per 1M
Claude Sonnet 5
1,000,000 context$2.00 in / $10.00 out per 1M
Claude Fable 5
1,000,000 context$10.00 in / $50.00 out per 1M
Claude Opus 4.8
1,000,000 context$5.00 in / $25.00 out per 1M
Claude Opus 4.7
1,000,000 context$5.00 in / $25.00 out per 1M
Claude Sonnet 4.6
1,000,000 context$3.00 in / $15.00 out per 1M