Mercury 2
Last verified September 7, 2026 · Inception Labs pricing ↗$0.250/1M input · $0.750/1M output · 128K context · Inception Labs
Mercury 2 costs $0.250 per 1M input tokens and $0.750 per 1M output tokens from Inception Labs, with a 128K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0007, or $6.75 per 10,000 requests. On that workload it is cheaper than 134 of the 171 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Mercury 2 Costs Per Request
At $0.250 per 1M input and $0.750 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0007 | $6.75 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0024 | $24.50 |
| Coding-agent step | 30,000 / 2,000 | $0.0090 | $90.00 |
Mercury 2 vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Mercury 2 Inception Labs | $0.250 | $0.750 | 128K | $0.0024 |
| Qwen3 Coder Next Alibaba | $0.120 | $0.800 | 262K | $0.0014 |
| Nemotron 3 Super 120B NVIDIA | $0.300 | $0.800 | 1.0M | $0.0029 |
| Llama 4 Maverick Meta | $0.270 | $0.850 | 1.0M | $0.0027 |
Alternatives to Mercury 2
Cheaper Alternative
Qwen3 Coder Next
$0.120 in · $0.800 out · Alibaba
8% cheaper with same or larger context
Premium UpgradeNemotron 3 Super 120B
$0.300 in · $0.800 out · NVIDIA
Upgrade with 1000K context
Same ProviderMercury 2.5 (Preview)
$0.040 in · $0.150 out · Inception Labs
81% cheaper in Inception Labs ecosystem
Pricing Details
Inception LabsFirst diffusion-based reasoning LLM. $0.25/$0.75 confirmed on three Inception surfaces that agree: the models page, the docs pricing table and its own /v1/models endpoint. Cached input $0.025/1M; cache writes are free ($0). Still sold, and as of September 7, 2026 it is the only model Inception's own API serves. Speed has three live figures and they are not interchangeable: 1,009 tok/s on NVIDIA Blackwell per Inception's launch post (vendor lab claim), 709.9 output tok/s measured by Artificial Analysis (2nd of 177), and 233 tok/s P50 across providers on OpenRouter's live traffic. We previously carried 788 tok/s attributed to Artificial Analysis; that page now reads 709.9 and we could not reconstruct the earlier capture, so this row is corrected to the current figure and dated. AA Intelligence Index 15. AIME 2025 91.1, GPQA Diamond 73.6, HumanEval 89.4 circulate widely but we could not find them on any Inception first-party page, so treat them as unverified. Verbosity caveat: produces ~2.6x output tokens of median model on AA suite. Sibling Mercury Edit 2 (FIM/NextEdit, 32K, 8,192 max output) shares the same rate card. Mercury Coder is absent from Inception's site, docs and API and from OpenRouter's catalogue. Estimated tokens (different tokenizer).
Input / 1M tokens
$0.25
Output / 1M tokens
$0.75
Context Window
128K
Max Output
50K
Price History
No price change recorded since 2026-08-11, when this site started tracking this model; it launched on 2026-05-12.
Frequently Asked Questions
Common questions about Mercury 2 pricing and usage
How much does Mercury 2 cost?
Mercury 2 costs $0.25 per 1 million input tokens and $0.75 per 1 million output tokens. This pricing is set by Inception Labs.
What tokenizer does Mercury 2 use?
Mercury 2 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Mercury 2's context window?
Mercury 2 supports a context window of 128K tokens (128,000 tokens). The maximum output length is 50K tokens.
How does Mercury 2 compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Mercury 2 costs $0.0024 per request. The nearest-priced alternatives cost: Qwen3 Coder Next (Alibaba) $0.0014, Nemotron 3 Super 120B (NVIDIA) $0.0029, Llama 4 Maverick (Meta) $0.0027. The table above lists their full rates and context windows.
How do I count tokens for Mercury 2?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Mercury 2 using the cl100k_base tokenizer.
Read More About Mercury 2
Mercury 2.5's 80% discount was due to end at 07:00 UTC on September 8 and make the cheapest model we price 5.00x dearer. It did not end. Seven weeks later OpenRouter still bills $0.04 and $0.15.
September 7, 2026 · 12 min read
Xiaomi MiMo UltraSpeed charges 3x for 10x the speed. The catch is you can only rent it for two weeks.
June 9, 2026 · 8 min read
Mercury 2 outputs at 788 tokens per second for $0.75 per million. The diffusion math turns frontier reasoning pricing into a rounding error.
May 13, 2026 · 11 min read