How do I get higher rate limits?
How do I get higher rate limits?
How do I handle rate limits?
How do I handle rate limits?
How are tokens counted?
How are tokens counted?
Does the API return token counts or dollar costs?
Does the API return token counts or dollar costs?
usage object with token counts, but not a dollar-cost field:prompt_tokens— all input tokens, including cached input.prompt_tokens_details.cached_tokens— the subset ofprompt_tokensserved from the prefix cache.completion_tokens— all generated tokens, including reasoning tokens.completion_tokens_details.reasoning_tokens— the subset ofcompletion_tokensused for reasoning.total_tokens—prompt_tokens + completion_tokens.
stream: true), set stream_options.include_usage: true to receive a final usage chunk before data: [DONE]. Use the rates on Models to calculate cost.Can I feed these docs to an LLM or coding agent?
Can I feed these docs to an LLM or coding agent?
Do Mercury models support image or vision input?
Do Mercury models support image or vision input?
How do the free tokens work?
How do the free tokens work?
Can I use Mercury with MCP clients or agent frameworks?
Can I use Mercury with MCP clients or agent frameworks?
https://api.inceptionlabs.ai/v1, provide your API key, and set the model to mercury-2.5. Tool definitions follow the OpenAI function schema shown in the Tool Use guide.Does the API support embeddings?
Does the API support embeddings?
/v1/chat/completions), fill-in-the-middle completions (/v1/fim/completions), and code edit completions (/v1/edit/completions). There is no /v1/embeddings endpoint or embedding model. Pair Mercury with a separate embeddings provider if your workflow needs vector representations.Can I fine-tune Mercury models?
Can I fine-tune Mercury models?
Are Mercury sampling results reproducible? Is there a seed parameter?
Are Mercury sampling results reproducible? Is there a seed parameter?
seed parameter, and temperature on mercury-2 and mercury-2.5 is restricted to the range 0.5–1.0. Values outside that range are silently reset to the model’s default (0.75 for mercury-2, 1 for mercury-2.5) and the response includes a warning field noting the reset. Bit-exact reproducibility across runs is not supported today. Aggregate over multiple samples if you need stable evaluation numbers, or contact support to discuss your use case.The code edit endpoint (/v1/edit/completions) uses a different temperature range of 0–2 with a default of 0.2 and no clamping.How long is a cached prompt prefix retained?
How long is a cached prompt prefix retained?
usage.prompt_tokens_details.cached_tokens field reports how many prompt tokens were served from cache on a given request, and cached tokens are billed at each model’s input_cache_reads rate (see Models). The API does not expose a documented TTL or a way to pin, invalidate, or inspect cache entries. If your workload depends on a specific retention guarantee, contact support.What is the data retention policy for API requests?
What is the data retention policy for API requests?