GPT-5 Nano
openai/gpt-5-nano-2025-08-07
OpenAI: GPT-5 Nano is a model from OpenAI that accepts text, image, and file inputs and generates text outputs. It has a context length of 400,000 tokens, supports tool use and reasoning capabilities, and is not open weights. It was released on January 1, 2025.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 400K tokens
- Max output
- 128K tokens
- Input price
- $0.050 / 1M tokens
- Output price
- $0.40 / 1M tokens
- Cache read
- $0.005 / 1M tokens
- Modalities
- text, image, file → text
- Knowledge cutoff
- May 31, 2024
- Released
- Jan 1, 2025
Measured evidence
Public benchmark record
- BFCL
- 51.5%2026-07-28
- BFCL
- 51.5%2026-07-27
- BFCL
- 51.5%2026-07-29
- BFCL
- 51.5%2026-07-31
- BFCL
- 51.5%2026-07-30
- BFCL
- 51.5%2026-08-02
- BFCL
- 51.5%2026-08-01
- BFCL
- 51.5%2026-08-05
- BFCL
- 51.5%2026-08-03
- BFCL
- 51.5%2026-08-09
- BFCL
- 51.5%2026-08-04
- BFCL
- 51.5%2026-08-06
- BFCL
- 51.5%2026-08-07
- BFCL
- 51.5%2026-08-14
- BFCL
- 51.5%2026-08-10
- BFCL
- 51.5%2026-08-08
- BFCL
- 51.5%2026-08-11
- BFCL
- 51.5%2026-08-18
- BFCL
- 51.5%2026-08-15
- BFCL
- 51.5%2026-08-12
- BFCL
- 51.5%2026-08-13
- BFCL
- 51.5%2026-08-19
- BFCL
- 51.5%2026-08-16
- BFCL
- 51.5%2026-08-20
- BFCL
- 51.5%2026-08-27
- BFCL
- 51.5%2026-08-17
- BFCL
- 51.5%2026-08-21
- BFCL
- 51.5%2026-08-22
- BFCL
- 51.5%2026-08-23
- BFCL
- 51.5%2026-08-24
- BFCL
- 51.5%2026-09-05
- BFCL
- 51.5%2026-08-28
- BFCL
- 51.5%2026-08-25
- BFCL
- 51.5%2026-08-26
- BFCL
- 51.5%2026-09-06
- BFCL
- 51.5%2026-08-29
- BFCL
- 51.5%2026-08-30
- BFCL
- 51.5%2026-08-31
- BFCL
- 51.5%2026-09-01
- BFCL
- 51.5%2026-09-02
- BFCL
- 51.5%2026-09-03
- BFCL
- 51.5%2026-09-04
- Design Arena Coding
- 1115 Elo2026-07-28
- Design Arena Coding
- 1115 Elo2026-07-27
- Design Arena Coding
- 1115 Elo2026-07-30
- Design Arena Coding
- 1115 Elo2026-07-29
- Design Arena Coding
- 1115 Elo2026-07-31
- Design Arena Coding
- 1114 Elo2026-08-02
- Design Arena Coding
- 1113 Elo2026-08-05
- Design Arena Coding
- 1114 Elo2026-08-01
- Design Arena Coding
- 1112 Elo2026-08-09
- Design Arena Coding
- 1114 Elo2026-08-03
- Design Arena Coding
- 1114 Elo2026-08-04
- Design Arena Coding
- 1109 Elo2026-08-14
- Design Arena Coding
- 1113 Elo2026-08-06
- Design Arena Coding
- 1112 Elo2026-08-10
- Design Arena Coding
- 1113 Elo2026-08-07
- Design Arena Coding
- 1103 Elo2026-08-18
- Design Arena Coding
- 1112 Elo2026-08-08
- Design Arena Coding
- 1103 Elo2026-08-15
- Design Arena Coding
- 1112 Elo2026-08-11
- Design Arena Coding
- 1111 Elo2026-08-12
- Design Arena Coding
- 1109 Elo2026-08-13
- Design Arena Coding
- 1102 Elo2026-08-19
- Design Arena Coding
- 1109 Elo2026-08-27
- Design Arena Coding
- 1102 Elo2026-08-20
- Design Arena Coding
- 1103 Elo2026-08-16
- Design Arena Coding
- 1101 Elo2026-09-05
- Design Arena Coding
- 1103 Elo2026-08-17
- Design Arena Coding
- 1109 Elo2026-08-21
- Design Arena Coding
- 1109 Elo2026-08-22
- Design Arena Coding
- 1109 Elo2026-08-23
- Design Arena Coding
- 1108 Elo2026-08-28
- Design Arena Coding
- 1109 Elo2026-08-24
- Design Arena Coding
- 1109 Elo2026-08-25
- Design Arena Coding
- 1109 Elo2026-08-26
- Design Arena Coding
- 1100 Elo2026-09-06
- Design Arena Coding
- 1108 Elo2026-08-29
- Design Arena Coding
- 1108 Elo2026-08-30
- Design Arena Coding
- 1108 Elo2026-08-31
- Design Arena Coding
- 1108 Elo2026-09-01
- Design Arena Coding
- 1107 Elo2026-09-02
- Design Arena Coding
- 1105 Elo2026-09-03
- Design Arena Coding
- 1104 Elo2026-09-04
- Design Arena UI
- 1103 Elo2026-07-28
- Design Arena UI
- 1103 Elo2026-07-27
- Design Arena UI
- 1103 Elo2026-07-30
- Design Arena UI
- 1103 Elo2026-07-29
- Design Arena UI
- 1103 Elo2026-07-31
- Design Arena UI
- 1103 Elo2026-08-02
- Design Arena UI
- 1103 Elo2026-08-01
- Design Arena UI
- 1102 Elo2026-08-05
- Design Arena UI
- 1099 Elo2026-08-09
- Design Arena UI
- 1103 Elo2026-08-03
- Design Arena UI
- 1103 Elo2026-08-04
- Design Arena UI
- 1098 Elo2026-08-14
- Design Arena UI
- 1102 Elo2026-08-06
- Design Arena UI
- 1102 Elo2026-08-07
- Design Arena UI
- 1100 Elo2026-08-10
- Design Arena UI
- 1100 Elo2026-08-08
- Design Arena UI
- 1094 Elo2026-08-18
- Design Arena UI
- 1100 Elo2026-08-11
- Design Arena UI
- 1095 Elo2026-08-15
- Design Arena UI
- 1100 Elo2026-08-12
- Design Arena UI
- 1100 Elo2026-08-13
- Design Arena UI
- 1094 Elo2026-08-19
- Design Arena UI
- 1095 Elo2026-08-16
- Design Arena UI
- 1094 Elo2026-08-20
- Design Arena UI
- 1092 Elo2026-08-27
- Design Arena UI
- 1094 Elo2026-08-17
- Design Arena UI
- 1089 Elo2026-09-05
- Design Arena UI
- 1093 Elo2026-08-21
- Design Arena UI
- 1093 Elo2026-08-22
- Design Arena UI
- 1094 Elo2026-08-23
- Design Arena UI
- 1094 Elo2026-08-24
- Design Arena UI
- 1093 Elo2026-08-28
- Design Arena UI
- 1094 Elo2026-08-25
- Design Arena UI
- 1094 Elo2026-08-26
- Design Arena UI
- 1089 Elo2026-09-06
- Design Arena UI
- 1093 Elo2026-08-29
- Design Arena UI
- 1093 Elo2026-08-30
- Design Arena UI
- 1093 Elo2026-08-31
- Design Arena UI
- 1093 Elo2026-09-01
- Design Arena UI
- 1092 Elo2026-09-02
- Design Arena UI
- 1090 Elo2026-09-03
- Design Arena UI
- 1088 Elo2026-09-04
- Design Arena Website
- 1126 Elo2026-07-28
- Design Arena Website
- 1126 Elo2026-07-30
- Design Arena Website
- 1126 Elo2026-07-27
- Design Arena Website
- 1126 Elo2026-07-29
- Design Arena Website
- 1126 Elo2026-07-31
- Design Arena Website
- 1125 Elo2026-08-02
- Design Arena Website
- 1125 Elo2026-08-01
- Design Arena Website
- 1125 Elo2026-08-05
- Design Arena Website
- 1125 Elo2026-08-03
- Design Arena Website
- 1124 Elo2026-08-09
- Design Arena Website
- 1125 Elo2026-08-04
- Design Arena Website
- 1121 Elo2026-08-14
- Design Arena Website
- 1124 Elo2026-08-06
- Design Arena Website
- 1125 Elo2026-08-07
- Design Arena Website
- 1123 Elo2026-08-10
- Design Arena Website
- 1124 Elo2026-08-08
- Design Arena Website
- 1112 Elo2026-08-18
- Design Arena Website
- 1123 Elo2026-08-11
- Design Arena Website
- 1112 Elo2026-08-15
- Design Arena Website
- 1123 Elo2026-08-12
- Design Arena Website
- 1121 Elo2026-08-13
- Design Arena Website
- 1112 Elo2026-08-19
- Design Arena Website
- 1112 Elo2026-08-16
- Design Arena Website
- 1112 Elo2026-08-20
- Design Arena Website
- 1121 Elo2026-08-27
- Design Arena Website
- 1112 Elo2026-08-17
- Design Arena Website
- 1117 Elo2026-09-05
- Design Arena Website
- 1121 Elo2026-08-21
- Design Arena Website
- 1121 Elo2026-08-22
- Design Arena Website
- 1121 Elo2026-08-23
- Design Arena Website
- 1121 Elo2026-08-24
- Design Arena Website
- 1121 Elo2026-08-28
- Design Arena Website
- 1121 Elo2026-08-25
- Design Arena Website
- 1122 Elo2026-08-26
- Design Arena Website
- 1114 Elo2026-09-06
- Design Arena Website
- 1121 Elo2026-08-29
- Design Arena Website
- 1120 Elo2026-08-30
- Design Arena Website
- 1120 Elo2026-08-31
- Design Arena Website
- 1121 Elo2026-09-01
- Design Arena Website
- 1119 Elo2026-09-02
- Design Arena Website
- 1118 Elo2026-09-03
- Design Arena Website
- 1117 Elo2026-09-04
- LMArena Creative Writing
- 1251 Elo2026-07-21
- LMArena Creative Writing
- 1251 Elo2026-07-27
- LMArena Creative Writing
- 1251 Elo2026-07-30
- LMArena Creative Writing
- 1251 Elo2026-08-02
- LMArena Creative Writing
- 1251 Elo2026-08-03
- LMArena Creative Writing
- 1250 Elo2026-08-06
- LMArena Creative Writing
- 1249 Elo2026-08-12
- LMArena Creative Writing
- 1249 Elo2026-08-21
- LMArena Creative Writing
- 1250 Elo2026-09-02
- LMArena Creative Writing
- 1250 Elo2026-08-27
- LMArena Creative Writing
- 1250 Elo2026-09-01
- LMArena Instruction Following
- 1305 Elo2026-07-21
- LMArena Instruction Following
- 1306 Elo2026-07-27
- LMArena Instruction Following
- 1306 Elo2026-07-30
- LMArena Instruction Following
- 1306 Elo2026-08-02
- LMArena Instruction Following
- 1306 Elo2026-08-03
- LMArena Instruction Following
- 1306 Elo2026-08-06
- LMArena Instruction Following
- 1306 Elo2026-08-12
- LMArena Instruction Following
- 1306 Elo2026-08-21
- LMArena Instruction Following
- 1306 Elo2026-09-02
- LMArena Instruction Following
- 1306 Elo2026-08-27
- LMArena Instruction Following
- 1306 Elo2026-09-01
- LMArena Long Query
- 1311 Elo2026-07-21
- LMArena Long Query
- 1311 Elo2026-07-27
- LMArena Long Query
- 1311 Elo2026-07-30
- LMArena Long Query
- 1312 Elo2026-08-02
- LMArena Long Query
- 1312 Elo2026-08-03
- LMArena Long Query
- 1312 Elo2026-08-06
- LMArena Long Query
- 1312 Elo2026-08-12
- LMArena Long Query
- 1312 Elo2026-08-21
- LMArena Long Query
- 1312 Elo2026-09-02
- LMArena Long Query
- 1312 Elo2026-08-27
- LMArena Long Query
- 1312 Elo2026-09-01
- LMArena Math
- 1316 Elo2026-07-21
- LMArena Math
- 1316 Elo2026-07-27
- LMArena Math
- 1316 Elo2026-07-30
- LMArena Math
- 1316 Elo2026-08-02
- LMArena Math
- 1316 Elo2026-08-03
- LMArena Math
- 1316 Elo2026-08-06
- LMArena Math
- 1317 Elo2026-08-12
- LMArena Math
- 1317 Elo2026-08-21
- LMArena Math
- 1317 Elo2026-09-01
- LMArena Math
- 1317 Elo2026-08-27
- LMArena Text
- 1337 Elo2026-07-21
- LMArena Text
- 1337 Elo2026-07-27
- LMArena Text
- 1337 Elo2026-07-30
- LMArena Text
- 1337 Elo2026-08-02
- LMArena Text
- 1338 Elo2026-08-10
- LMArena Text
- 1337 Elo2026-08-06
- LMArena Text
- 1337 Elo2026-08-03
- LMArena Text
- 1337 Elo2026-08-21
- LMArena Text
- 1337 Elo2026-08-12
- LMArena Text
- 1337 Elo2026-09-01
- LMArena Text
- 1337 Elo2026-09-02
- LMArena Text
- 1337 Elo2026-08-27
- LMArena Vision
- 1162 Elo2026-07-12
- LMArena Vision
- 1147 Elo2026-07-21
- LMArena Vision
- 1147 Elo2026-07-26
- LMArena Vision
- 1147 Elo2026-07-30
- LMArena Vision
- 1148 Elo2026-08-02
- LMArena Vision
- 1148 Elo2026-08-06
- LMArena Vision
- 1148 Elo2026-08-21
- LMArena Vision
- 1145 Elo2026-08-27
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 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 Tool & Function CallingProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 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 Frontend & UIProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 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 Logic & Problem SolvingProvisional evidence
50% 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 Hermes AgentProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Competition MathProvisional evidence
40% 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
40% 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 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 AI AgentsProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 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 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 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 OCR & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for CodingProvisional evidence
24% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 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 Computer & Browser UseProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 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 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 Code CompletionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Debugging & Code ReviewProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 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 Local LLM for CodingProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 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.
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.