Mercury 2
inception/mercury-2-20260304
Inception: Mercury 2 is a text‑only model from Inception released on 2026‑02‑24. It supports up to 128 000 tokens of context, includes tool integration and reasoning capabilities, and is priced at $0.25 per M input tokens and $0.75 per M output tokens. The model’s weights are not publicly available.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 128K tokens
- Max output
- 50K tokens
- Input price
- $0.25 / 1M tokens
- Output price
- $0.75 / 1M tokens
- Cache read
- $0.025 / 1M tokens
- Modalities
- text → text
- Knowledge cutoff
- —
- Released
- Jan 1, 2024
Measured evidence
Public benchmark record
- Design Arena Coding
- 1020 Elo2026-07-28
- Design Arena Coding
- 1020 Elo2026-07-27
- Design Arena Coding
- 1020 Elo2026-07-30
- Design Arena Coding
- 1020 Elo2026-07-29
- Design Arena Coding
- 1021 Elo2026-07-31
- Design Arena Coding
- 1022 Elo2026-08-02
- Design Arena Coding
- 1021 Elo2026-08-05
- Design Arena Coding
- 1022 Elo2026-08-01
- Design Arena Coding
- 1023 Elo2026-08-09
- Design Arena Coding
- 1022 Elo2026-08-03
- Design Arena Coding
- 1022 Elo2026-08-04
- Design Arena Coding
- 1022 Elo2026-08-14
- Design Arena Coding
- 1022 Elo2026-08-06
- Design Arena Coding
- 1022 Elo2026-08-10
- Design Arena Coding
- 1022 Elo2026-08-07
- Design Arena Coding
- 1019 Elo2026-08-18
- Design Arena Coding
- 1023 Elo2026-08-08
- Design Arena Coding
- 1017 Elo2026-08-15
- Design Arena Coding
- 1023 Elo2026-08-11
- Design Arena Coding
- 1023 Elo2026-08-12
- Design Arena Coding
- 1023 Elo2026-08-13
- Design Arena Coding
- 1019 Elo2026-08-19
- Design Arena Coding
- 1030 Elo2026-08-27
- Design Arena Coding
- 1019 Elo2026-08-20
- Design Arena Coding
- 1018 Elo2026-08-16
- Design Arena Coding
- 1018 Elo2026-08-17
- Design Arena Coding
- 1027 Elo2026-08-21
- Design Arena Coding
- 1028 Elo2026-08-22
- Design Arena Coding
- 1028 Elo2026-08-23
- Design Arena Coding
- 1030 Elo2026-08-28
- Design Arena Coding
- 1029 Elo2026-08-24
- Design Arena Coding
- 1029 Elo2026-08-25
- Design Arena Coding
- 1029 Elo2026-08-26
- Design Arena Coding
- 1030 Elo2026-08-29
- Design Arena Coding
- 1030 Elo2026-08-30
- Design Arena Coding
- 1030 Elo2026-08-31
- Design Arena Coding
- 1030 Elo2026-09-01
- Design Arena Coding
- 1029 Elo2026-09-02
- Design Arena Coding
- 1027 Elo2026-09-03
- Design Arena Coding
- 1025 Elo2026-09-04
- Design Arena UI
- 994 Elo2026-07-28
- Design Arena UI
- 995 Elo2026-07-27
- Design Arena UI
- 990 Elo2026-07-30
- Design Arena UI
- 990 Elo2026-07-29
- Design Arena UI
- 989 Elo2026-07-31
- Design Arena UI
- 987 Elo2026-08-02
- Design Arena UI
- 988 Elo2026-08-01
- Design Arena UI
- 988 Elo2026-08-05
- Design Arena UI
- 988 Elo2026-08-03
- Design Arena UI
- 994 Elo2026-08-09
- Design Arena UI
- 986 Elo2026-08-04
- Design Arena UI
- 993 Elo2026-08-14
- Design Arena UI
- 988 Elo2026-08-06
- Design Arena UI
- 993 Elo2026-08-07
- Design Arena UI
- 992 Elo2026-08-10
- Design Arena UI
- 993 Elo2026-08-08
- Design Arena UI
- 995 Elo2026-08-18
- Design Arena UI
- 997 Elo2026-08-11
- Design Arena UI
- 993 Elo2026-08-15
- Design Arena UI
- 998 Elo2026-08-12
- Design Arena UI
- 998 Elo2026-08-13
- Design Arena UI
- 995 Elo2026-08-19
- Design Arena UI
- 994 Elo2026-08-16
- Design Arena UI
- 995 Elo2026-08-20
- Design Arena UI
- 1004 Elo2026-08-27
- Design Arena UI
- 994 Elo2026-08-17
- Design Arena UI
- 994 Elo2026-08-21
- Design Arena UI
- 998 Elo2026-08-22
- Design Arena UI
- 1000 Elo2026-08-23
- Design Arena UI
- 1001 Elo2026-08-24
- Design Arena UI
- 1003 Elo2026-08-28
- Design Arena UI
- 1000 Elo2026-08-25
- Design Arena UI
- 1000 Elo2026-08-26
- Design Arena UI
- 1001 Elo2026-08-29
- Design Arena UI
- 1001 Elo2026-08-30
- Design Arena UI
- 1001 Elo2026-08-31
- Design Arena UI
- 1001 Elo2026-09-01
- Design Arena UI
- 999 Elo2026-09-02
- Design Arena UI
- 998 Elo2026-09-03
- Design Arena UI
- 996 Elo2026-09-04
- Design Arena Website
- 1010 Elo2026-07-28
- Design Arena Website
- 1010 Elo2026-07-30
- Design Arena Website
- 1010 Elo2026-07-27
- Design Arena Website
- 1010 Elo2026-07-29
- Design Arena Website
- 1012 Elo2026-07-31
- Design Arena Website
- 1016 Elo2026-08-02
- Design Arena Website
- 1015 Elo2026-08-01
- Design Arena Website
- 1016 Elo2026-08-05
- Design Arena Website
- 1016 Elo2026-08-03
- Design Arena Website
- 1017 Elo2026-08-09
- Design Arena Website
- 1016 Elo2026-08-04
- Design Arena Website
- 1022 Elo2026-08-14
- Design Arena Website
- 1017 Elo2026-08-06
- Design Arena Website
- 1017 Elo2026-08-07
- Design Arena Website
- 1016 Elo2026-08-10
- Design Arena Website
- 1016 Elo2026-08-08
- Design Arena Website
- 1016 Elo2026-08-18
- Design Arena Website
- 1019 Elo2026-08-11
- Design Arena Website
- 1013 Elo2026-08-15
- Design Arena Website
- 1021 Elo2026-08-12
- Design Arena Website
- 1022 Elo2026-08-13
- Design Arena Website
- 1016 Elo2026-08-19
- Design Arena Website
- 1014 Elo2026-08-16
- Design Arena Website
- 1016 Elo2026-08-20
- Design Arena Website
- 1034 Elo2026-08-27
- Design Arena Website
- 1016 Elo2026-08-17
- Design Arena Website
- 1031 Elo2026-08-21
- Design Arena Website
- 1032 Elo2026-08-22
- Design Arena Website
- 1033 Elo2026-08-23
- Design Arena Website
- 1035 Elo2026-08-24
- Design Arena Website
- 1036 Elo2026-08-28
- Design Arena Website
- 1035 Elo2026-08-25
- Design Arena Website
- 1034 Elo2026-08-26
- Design Arena Website
- 1036 Elo2026-08-29
- Design Arena Website
- 1036 Elo2026-08-30
- Design Arena Website
- 1036 Elo2026-08-31
- Design Arena Website
- 1036 Elo2026-09-01
- Design Arena Website
- 1036 Elo2026-09-02
- Design Arena Website
- 1034 Elo2026-09-03
- Design Arena Website
- 1033 Elo2026-09-04
- LMArena Creative Writing
- 1295 Elo2026-07-21
- LMArena Creative Writing
- 1295 Elo2026-07-27
- LMArena Creative Writing
- 1295 Elo2026-07-30
- LMArena Creative Writing
- 1295 Elo2026-08-02
- LMArena Creative Writing
- 1295 Elo2026-08-03
- LMArena Creative Writing
- 1295 Elo2026-08-06
- LMArena Creative Writing
- 1296 Elo2026-08-12
- LMArena Creative Writing
- 1296 Elo2026-08-21
- LMArena Creative Writing
- 1296 Elo2026-08-27
- LMArena Creative Writing
- 1296 Elo2026-09-01
- LMArena Instruction Following
- 1323 Elo2026-07-21
- LMArena Instruction Following
- 1323 Elo2026-07-27
- LMArena Instruction Following
- 1323 Elo2026-07-30
- LMArena Instruction Following
- 1323 Elo2026-08-02
- LMArena Instruction Following
- 1323 Elo2026-08-03
- LMArena Instruction Following
- 1323 Elo2026-08-06
- LMArena Instruction Following
- 1324 Elo2026-08-12
- LMArena Instruction Following
- 1323 Elo2026-08-21
- LMArena Instruction Following
- 1324 Elo2026-08-27
- LMArena Instruction Following
- 1324 Elo2026-09-01
- LMArena Long Query
- 1328 Elo2026-07-21
- LMArena Long Query
- 1328 Elo2026-07-27
- LMArena Long Query
- 1328 Elo2026-07-30
- LMArena Long Query
- 1328 Elo2026-08-02
- LMArena Long Query
- 1328 Elo2026-08-03
- LMArena Long Query
- 1328 Elo2026-08-06
- LMArena Long Query
- 1328 Elo2026-08-12
- LMArena Long Query
- 1329 Elo2026-08-21
- LMArena Long Query
- 1331 Elo2026-08-27
- LMArena Long Query
- 1331 Elo2026-09-01
- LMArena Text
- 1347 Elo2026-08-02
- LMArena Text
- 1347 Elo2026-07-21
- LMArena Text
- 1346 Elo2026-08-27
- LMArena Text
- 1347 Elo2026-07-27
- LMArena Text
- 1347 Elo2026-07-30
- LMArena Text
- 1346 Elo2026-08-10
- LMArena Text
- 1347 Elo2026-08-06
- LMArena Text
- 1347 Elo2026-08-03
- LMArena Text
- 1347 Elo2026-08-21
- LMArena Text
- 1346 Elo2026-08-12
- LMArena Text
- 1346 Elo2026-09-01
- LMArena WebDev
- 1164 Elo2026-07-16
- LMArena WebDev
- 1164 Elo2026-07-20
- LMArena WebDev
- 1164 Elo2026-07-21
- LMArena WebDev
- 1166 Elo2026-07-27
- LMArena WebDev
- 1166 Elo2026-07-24
- LMArena WebDev
- 1166 Elo2026-07-28
- LMArena WebDev
- 1166 Elo2026-07-30
- LMArena WebDev
- 1166 Elo2026-08-01
- LMArena WebDev
- 1166 Elo2026-07-31
- LMArena WebDev
- 1166 Elo2026-08-06
- LMArena WebDev
- 1166 Elo2026-08-02
- LMArena WebDev
- 1166 Elo2026-08-12
- LMArena WebDev
- 1166 Elo2026-08-10
- LMArena WebDev
- 1166 Elo2026-08-14
- LMArena WebDev
- 1166 Elo2026-08-21
- LMArena WebDev
- 1166 Elo2026-08-30
- LMArena WebDev
- 1166 Elo2026-09-01
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Frontend & UIEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Business WritingProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Marketing CopyProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Creative WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for a General AssistantProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Code CompletionProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for CodingProvisional evidence
42% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.
- Best Value LLMProvisional evidence
36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingProvisional evidence
33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
26% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Cheapest Capable LLMProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for SummarizationProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Competition MathProvisional evidence
15% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningProvisional evidence
15% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
- Best LLM for Tool & Function CallingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Computer & Browser UseProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for OCR & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Autonomous AgentsProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.