openai
OpenAI: GPT-5
The OpenAI GPT-5 is an AI model that can handle multiple input modalities, including text, image, and file inputs. It has a high context length of 400,000 tokens and supports tools for additional functionality. Those with larger datasets or complex applications may want to consider the OpenAI GPT-5 due to its robust performance. The model's blended benchmark score of 72.8 across two independent benchmarks is competitive, although it comes at a cost: $1.25 per million input tokens and $10.00 per million output tokens. This price point may make it more suitable for organizations or individuals with significant resources.
Quality Score
100/100
price + capability + benchmarks
Input Price
$1.25
per 1M tokens · checked 2026-09-27
Output Price
$10.00
per 1M tokens · checked 2026-09-27
Context Window
400,000
tokens
Benchmark results
Independent, published benchmarks. Blended score 71.4 across 2 benchmarks, last refreshed 2026-09-27. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 88.0 |
| AI Index | broad capability composite | 37.9 |
- Model ID
- openai/gpt-5
- Vendor
- openai
- Released
- August 2025
- Tokenizer
- GPT
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $1.25/M input and $10.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.05 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.12 |
| A month of a busy support chatbot | 5M in / 2M out | $26.25 |
Strong choice for
Code
Unit Test Generation
Generating thorough test suites for existing functions.
Code
CI/CD Pipelines
Authoring GitHub Actions, GitLab CI, and CircleCI configs.
Data
CSV / Spreadsheet Cleanup
Normalizing messy tabular data with consistent fields.
Data
OCR / Document Parsing
Reading text out of images, PDFs, and scanned documents.
Data
Table Extraction from PDFs
Pulling structured tables out of complex documents.
Business
SOP / Process Docs
Standard operating procedure documentation.
Category rankings
Where OpenAI: GPT-5 places across the 59 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #1 | Function / Tool CallingAgents · of 25 ranked | 130 |
| #4 | OCR / Document ParsingData · of 25 ranked | 139 |
| #4 | Table Extraction from PDFsData · of 25 ranked | 139 |
| #4 | Diagram ExtractionVision · of 25 ranked | 138 |
| #5 | Unit Test GenerationCode · of 25 ranked | 141 |
| #5 | CI/CD PipelinesCode · of 25 ranked | 135 |
| #5 | CSV / Spreadsheet CleanupData · of 25 ranked | 144 |
| #5 | SOP / Process DocsBusiness · of 25 ranked | 127 |
| #5 | Agent WorkflowsAgents · of 25 ranked | 164 |
| #5 | Coding AgentsAgents · of 25 ranked | 164 |
| #6 | SQL GenerationCode · of 25 ranked | 152 |
| #6 | Code ReviewCode · of 25 ranked | 154 |
| #6 | Bug FixingCode · of 25 ranked | 159 |
| #6 | Essay GradingEducation · of 25 ranked | 154 |
| #6 | Browser AutomationAgents · of 25 ranked | 146 |
| #6 | Fitness CoachingPersonal · of 25 ranked | 125 |
| #6 | Scientific CodingResearch · of 25 ranked | 159 |
| #7 | Frontend Component DesignCode · of 25 ranked | 136 |
| #7 | Data AnalysisData · of 25 ranked | 146 |
| #7 | Financial AnalysisProfessional · of 25 ranked | 140 |
| #7 | Math TutoringEducation · of 25 ranked | 134 |
| #7 | Chart & Graph ReadingVision · of 25 ranked | 141 |
| #7 | Experiment DesignResearch · of 25 ranked | 141 |
| #8 | RFP ResponseBusiness · of 25 ranked | 161 |
| #9 | Regex WritingCode · of 25 ranked | 128 |
| #9 | ETL ScriptingData · of 25 ranked | 144 |
| #9 | Marketing CopyWriting · of 25 ranked | 123 |
| #9 | Language TranslationWriting · of 25 ranked | 128 |
| #9 | Medical Note SummarizationProfessional · of 25 ranked | 144 |
| #9 | Standardized Test PrepEducation · of 25 ranked | 123 |
| #9 | Resume WritingBusiness · of 25 ranked | 114 |
| #9 | Screenshot DebuggingVision · of 25 ranked | 135 |
| #9 | Tutoring for KidsPersonal · of 25 ranked | 128 |
| #10 | Contract ReviewProfessional · of 25 ranked | 163 |
| #11 | Creative WritingWriting · of 25 ranked | 147 |
| #11 | Screenwriting & DialogWriting · of 25 ranked | 147 |
| #11 | Academic WritingWriting · of 25 ranked | 147 |
| #11 | Legal DraftingProfessional · of 25 ranked | 147 |
| #11 | Physics TutoringEducation · of 25 ranked | 137 |
| #11 | OKRs & Strategic PlanningBusiness · of 25 ranked | 147 |
| #11 | Math ProofsResearch · of 25 ranked | 147 |
| #13 | Code RefactoringCode · of 25 ranked | 154 |
| #13 | Blog Post WritingWriting · of 25 ranked | 133 |
| #13 | RAG PipelinesAgents · of 25 ranked | 154 |
| #13 | Trip PlanningPersonal · of 25 ranked | 133 |
| #16 | History TutoringEducation · of 25 ranked | 138 |
| #16 | Sales / Cold EmailBusiness · of 25 ranked | 119 |
| #16 | Job Application DraftingBusiness · of 25 ranked | 119 |
| #16 | Character RoleplayPersonal · of 25 ranked | 143 |
| #16 | Journaling HelperPersonal · of 25 ranked | 119 |
| #16 | Recipe GenerationPersonal · of 25 ranked | 119 |
| #17 | Legal ResearchProfessional · of 25 ranked | 157 |
| #17 | Scientific ResearchProfessional · of 25 ranked | 157 |
| #17 | Fiction CollaboratorPersonal · of 25 ranked | 157 |
| #17 | Literature ReviewResearch · of 25 ranked | 157 |
| #20 | Long-Document SummarizationWriting · of 25 ranked | 152 |
| #20 | Long-Context Q&AAgents · of 25 ranked | 147 |
| #21 | Code DocumentationCode · of 25 ranked | 138 |
| #21 | Meeting NotesBusiness · of 25 ranked | 142 |
Similar models
openai
OpenAI: GPT-6 Luna Pro
$0.10 in / $0.50 out
1,050,000 ctx
100
openai
OpenAI: GPT-6 Luna Pro (batch)
$0.05 in / $0.25 out
1,050,000 ctx
100
openai
OpenAI: GPT-6 Luna
$0.10 in / $0.50 out
1,050,000 ctx
100
openai
OpenAI: GPT-6 Luna (batch)
$0.05 in / $0.25 out
1,050,000 ctx
100
openai
OpenAI: GPT-6 Sol Pro
$2.00 in / $10.00 out
1,050,000 ctx
100
openai
OpenAI: GPT-6 Sol Pro (batch)
$1.00 in / $5.00 out
1,050,000 ctx
100
Quick answers
- How much does OpenAI: GPT-5 cost?
- $1.25 per million input tokens and $10.00 per million output tokens.
- What is OpenAI: GPT-5's context window?
- 400,000 tokens, roughly 600 pages of text in a single request.
- Does OpenAI: GPT-5 support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5 process images?
- Yes, it accepts image input.