← Model list
Mercury 2
inception·inception/mercury-2·GA·Closed·mercury series·NEW
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
At a glance
Official price$0.25 / $0.75 per 1M
Cache read $0.025 · Inception
Lowest paid$0.25 / $0.75
NanoGPT Gateway · 1.3× spread
Context128,000
Output limit50,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff2025-01-01
Released / updated2026-02-24 / 2026-06-11
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence21.9
Value58
Coding31.1
Agentic9.5
Output speed835 tok/s
TTFT3.93 s
Cost per task$0.0798
Value formulaIQ 21.9 ÷ min blended $0.375 = 58
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 5 providers5 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT | Gateway | $0.25 | $0.75 | $0.025 | — | 128,000 | 50,000 | |
| InceptionOfficial | Gateway | $0.25 | $0.75 | $0.025 | — | 128,000 | 50,000 | |
| OpenRouter | Gateway | $0.25 | $0.75 | $0.025 | — | 128,000 | 50,000 | |
| Vercel AI Gateway | Cloud | $0.25 | $0.75 | $0.025 | — | 128,000 | 128,000 | |
| Venice AI | Gateway | $0.313 | $0.938 | $0.031 | — | 128,000 | 50,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NanoGPT$60.50
2Inception · Official$60.50
3OpenRouter$60.50
4Vercel AI Gateway$60.50
5Venice AI$75.63
Switch to NanoGPT to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = loweffort = mediumeffort = higheffort = none
1 / 5 providers expose no reasoning control (reasoning_options: []).
Related models
Inception: Mercury 2same series$0.25 / $0.75Mercury Coder Small Betasame series$0.25 / $1.00Mercury Coder Smallsame series$0.25 / $1.00DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0MiMo-V2.5cheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended