cd /news/large-language-models/mercury-2-5-llm-hits-770-tokens-per-… · home topics large-language-models article
[ARTICLE · art-138605] src=artificialanalysis.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Mercury 2.5 LLM hits 770 tokens per second

Inception's Mercury 2.5 reasoning model scores 12 on the Artificial Analysis Intelligence Index and runs at 770 output tokens per second, according to Artificial Analysis. The model, released September 8, 2026, supports text input and output with a 260k-token context window and is priced at $0.25 per 1M input tokens and $0.75 per 1M output tokens, averaging $0.06 per task on the Intelligence Index. Mercury 2.5 generated 35M tokens during the Intelligence Index evaluation, below the 84M median.

read4 min views1 publishedSep 23, 2026
Mercury 2.5 LLM hits 770 tokens per second
Image: source

Model summary

Mercury 2.5 is above average in intelligence and well priced when comparing to other models of similar price. It's also notably fast and fairly concise. The model supports text input, outputs text, and has a 260k tokens context window.

Mercury 2.5 scores 12 on the Artificial Analysis Intelligence Index, placing it above average among comparable models (median: 12). When evaluating the Intelligence Index, it generated 35M tokens, which is fairly concise in comparison to the median of 84M.

Pricing for Mercury 2.5 is $0.25 per 1M input tokens (moderately priced, median: $0.25) and $0.75 per 1M output tokens (moderately priced, median: $0.90). On average, it costs $0.06 per task to evaluate Mercury 2.5 on the Intelligence Index.

At 770 tokens per second, Mercury 2.5 is notably fast (110).

Reasoning Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist.
Input modality Supports: text
Output modality Supports: text
Context window 260k ~390 A4 pages of size 12 Arial font

Metrics are compared against models of the same class:

  • Non-reasoning models → compared only with other non-reasoning models
  • Reasoning models → compared across both reasoning and non-reasoning
  • Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
  • Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:

  • <$0.15 per 1M tokens

  • $0.15–$1 per 1M tokens

  • $1 per 1M tokens Highlights

IntelligenceUpdated #

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Measures the performance of models on specific capabilities and industries

Artificial Analysis Finance & Accounting Index

Intelligence Evaluations

[AA-Briefcase v1.1](https://artificialanalysis.ai/evaluations/aa-briefcase)Updated

Agentic knowledge work, (Elo-500)/2000

[GDPval-AA v2.1](https://artificialanalysis.ai/evaluations/gdpval-aa)Updated

Agentic real-world work tasks, (Elo-500)/2000

[AutomationBench-AA](https://artificialanalysis.ai/evaluations/automationbench-aa)Updated

Agentic SaaS workflows

Agentic coding & terminal use

Coding

Reasoning & knowledge

GDP.pdfNew Professional document reasoning, All-pass

CritPtUnder review Physics reasoning

Knowledge

1 - hallucination rate

Long context reasoning

Legal agentic work, criterion pass rate

Agentic business operations

Quantitative analysis on spreadsheets & documents

Agentic tool use

Kubernetes incident root-cause analysis

Visual reasoning

MLCR-AANew Medical long context reasoning

AA-Briefcase v1.1Updated

AA-Briefcase Elo

AA-Omniscience

AA-Omniscience Index

Intelligence Index Comparisons #

Intelligence Index vs. Cost per Intelligence Index Task

Token Use #

Output Tokens per Intelligence Index Task

Cost #

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Context Window #

Context Window

Speed #

Measured by Output Speed (tokens per second)

Output Speed

Time per Intelligence Index Task

Latency #

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

End-to-End Response Time #

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Frequently Asked Questions #

Common questions about Mercury 2.5

Mercury 2.5 was released on September 8, 2026.

Mercury 2.5 was created by Inception.

Mercury 2.5 scores 12 on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 12).

Mercury 2.5 generates output at 770.4 tokens per second (based on Inception's API), which is well above average compared to other reasoning models in a similar price tier (median: 110.3 t/s).

Mercury 2.5 has a time to first token (TTFT) of 2.91s (based on Inception's API), which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 2.22s).

Mercury 2.5 costs $0.25 per 1M input tokens (better than average, median: $0.25) and $0.75 per 1M output tokens (better than average, median: $0.90), based on Inception's API.

Mercury 2.5 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens (based on Inception's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.14 per 1M tokens. Pricing may vary by provider. Compare provider pricing

When evaluated on the Intelligence Index, Mercury 2.5 generated 35M output tokens, which is better than average compared to other reasoning models in a similar price tier (median: 84M).

Yes, Mercury 2.5 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Mercury 2.5 supports text input.

Mercury 2.5 supports text output.

No, Mercury 2.5 does not support image input. It can only process text.

No, Mercury 2.5 is not multimodal. It only supports text input.

Mercury 2.5 has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

No, Mercury 2.5 is proprietary. The model weights are not publicly available.

Mercury 2.5 is a proprietary model and Inception has not disclosed the model size or parameter count.

Mercury 2.5 achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Mercury 2.5 is available via API through 1 provider. Compare API providers

Mercury 2.5 is available through 1 API provider. Compare providers

── more in #large-language-models 4 stories · sorted by recency
── more on @mercury 2.5 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mercury-2-5-llm-hits…] indexed:0 read:4min 2026-09-23 ·