Mercury 2

Name: Mercury 2
Brand: venice.ai
Price: 0.3125 USD
Availability: InStock

Mercury 2 is a diffusion-based reasoning LLM from Inception, delivering over 1,000 tokens per second — 5x faster than leading speed-optimized models — with strong reasoning, tool use, and structured output capabilities.

mercury-2 · venice.ai

Text · Venice catalog$0.31 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.31 per 1M tokensper 1M tokens

Context window128KMax tokens

Benchmarks6Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Chat1 result

Tau2 Airlinetau2-airline · chat

53.0%

ReportedOct 2026

Instruction Following1 result

IFBenchifbench · instruction_following

71.0%

ReportedOct 2026

Math1 result

AIME 2025aime-2025 · math

91.1%

ReportedOct 2026

Reasoning3 results

GPQAgpqa · reasoning

74.0%

ReportedOct 2026

LiveCodeBenchlivecodebench · reasoning

67.0%

ReportedOct 2026

SciCodescicode · reasoning

38.0%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.31
Output price per 1M tokens: $0.94
Cache read price per 1M tokens: $0.0313
Blended price per 1M tokens (50/50): $0.63

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingWeb search

Endpoint metadata

Privacy: anonymized
Quantization: not-available
Maximum completion tokens: 50K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Quantization: not-available
Supports E2 E E: No
Supports Vision: No
Supports X Search: No
Optimized For Code: No
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: high
Reasoning Effort Options: none, low, medium, high
Supports Multiple Images: No
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes