Verified 2026-11-18 · rates follow the live catalog
Claude Haiku 4.5. 200k context.
| Provider | Anthropic |
|---|---|
| Context window | 195K |
| Input / 1M tokens | $1 |
| Output / 1M tokens | $5 |
| Cached input / 1M tokens | $0.10 |
A call with 50,000 input tokens and 10,000 output tokens bills at $0.100: 50,000 ÷ 1,000,000 × $1 for input, plus 10,000 ÷ 1,000,000 × $5 for output. A prompt prefix that hits the cache bills at $0.10 per million instead of the full input rate, so a long reused system prompt is far cheaper on the second call than the first.
Both API formats are served from one host and one key, so a tool that speaks either works without a translation layer:
https://api.openference.com/v1/chat/completionshttps://api.openference.com/v1/messagesSet OPENAI_BASE_URL or ANTHROPIC_BASE_URL to that host and keep the client library you already use.
Send Claude Haiku 4.5 in the model field.
Capabilities: image input, tool and function calling.
The rest of the catalog, with rates side by side, is on all models.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API