Inception: Mercury 3
Mercury 3 is a reasoning model from Inception released on Oct 16, 2026. It reads text and writes text, with a 1M token context window and up to 131K tokens per reply.
Show moreShow less
It costs $0.10 per million input tokens and $0.35 per million output tokens. Cached input bills at $0.01, 90% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
5 providers serve it, including Vercel AI Gateway, NanoGPT and Venice AI.
- Modalities
- In / out price
- $0.10 / $0.35 per 1M
- Context
- 1M
- Max output
- 131K
- Released
- Oct 16, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Mercury 3 pricing
USD, as listed on Oct 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.10 / 1M tokens | |
|---|---|---|
| Output | $0.35 / 1M tokens | |
| Cached input (read) | $0.01 / 1M tokens | 90% off input |
Mercury 3 providers
5 providers serve it, including Vercel AI Gateway, NanoGPT and Venice AI. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Inception First party | $0.10 | $0.35 | $0.01 | 1M | 131K |
| Vercel AI Gateway | $0.10 | $0.35 | $0.01 | 1M | 131K |
| NanoGPT | $0.10 | $0.35 | $0.01 | 1M | 131K |
| Venice AI | $0.10 | $0.35 | $0.01 | 1M | 131K |
| Kilo Gateway | $0.20 | $0.70 | $0.02 | 1M | 131K |
What Mercury 3 costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Mercury 3 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Mercury 3
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 10
Reads text. Tool calling, structured output, reasoning. Served by 38 providers.
by openaiAug 5, 2025128K context$0.07/M input tokens$0.30/M output tokens38 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 6 providers.
by stepfunApr 2, 2026$0.1046/M input tokens$0.3138/M output tokens6 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 13 providers.
by stepfunJan 29, 2026$0.1046/M input tokens$0.3138/M output tokens13 providers
- 200K context
Reads text. Tool calling, structured output, reasoning. Served by 23 providers.
by z-aiJan 19, 2026$0.07/M input tokens$0.40/M output tokens23 providers
- 262K context
Reads text. Tool calling, structured output, reasoning.
by xiaomiDec 16, 2025$0.10/M input tokens$0.30/M output tokens
- 33K context
Reads text. Tool calling, reasoning.
by qwenMar 31, 2025$0.15/M input tokens$0.15/M output tokens
More from Inception
- 260K context
Reads text. Tool calling, structured output, reasoning. Served by 5 providers.
by inceptionSep 8, 2026$0.20/M input tokens$0.75/M output tokens5 providers
- 260K context
Reads text. Tool calling, structured output, reasoning.
by inceptionSep 1, 2026$0.04/M input tokens$0.15/M output tokens
- 32K context
Reads text.
by inceptionMar 30, 2026$0.25/M input tokens$0.75/M output tokens
- 128K context
Reads text. Tool calling, structured output, reasoning. Served by 6 providers.
by inceptionFeb 24, 2026$0.25/M input tokens$0.75/M output tokens6 providers
- 32K context
Reads text. Tool calling.
by inceptionFeb 26, 2025$0.25/M input tokens$1/M output tokens
Mercury 3 questions
How much does the Mercury 3 API cost?
$0.10 per million input tokens and $0.35 per million output tokens, with cached input at $0.01. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Mercury 3?
1,000,000 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Mercury 3?
5 providers serve it, including Vercel AI Gateway, NanoGPT and Venice AI. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Mercury 3 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Mercury 3 open source?
No. Inception serves it through an API only, so you cannot download the weights or host it yourself.
When was Mercury 3 released?
Oct 16, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 22, 2026. The summary is written from these facts.