o3
Released
2025-04-16
Last refreshed
2026-05-29
Status
Researched 6d ago
ProprietaryMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use
o3 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 200k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
Specifications
- Family
- o3
- Released
- 2025-04-16
- Context
- 200k
- Max output
- 100,000
- Architecture
- Decoder Only
- Knowledge cutoff
- 2024-06
- Specialization
- general
- License
- Proprietary
- Training
- finetuned
Created by
Pricing
Output / 1M
$8.00
Input / 1M
$2.00
Cheapest of 3 routes · OpenAI API · cache read $0.500
About
OpenAI o3 reasoning model with advanced multi-step problem-solving capabilities.
o3 is a proprietary model. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenAI API, OpenRouter, and Vercel AI Gateway, with the cheapest tracked route listed at $2 input and $8 output per 1M tokens. Headline tracked benchmarks include HumanEval 96.7, SWE-bench Verified 71.7, and LiveCodeBench 79.1.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D4 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ C1 relevant benchmark in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| OpenAI API | $2.00 | $8.00 | $1.00 / $4.00 | read $0.500 | Serverless |
| OpenRouter | $2.00 | $8.00 | - | - | Serverless |
| Vercel AI Gateway | $2.00 | $8.00 | - | read $0.500 | Serverless |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch API
Benchmark peer barsfor Coding
Benchmark scores(10)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Source |
|---|---|---|---|
| HumanEval | 96.7 | 2025-04 | https://openai.com/index/introducing-o3-and-o4-mini/ |
| SWE-bench Verified | 71.7 | — | https://openai.com/index/openai-o3-system-card/ |
| LiveCodeBench | 79.1 | 2025-04 | https://openai.com/index/introducing-o3-and-o4-mini/ |
| Aider Polyglot | 81.3 | 2026-04 (high) | https://aider.chat/docs/leaderboards |
| Chatbot Arena | 1412.0 | — | https://lmarena.ai |
| Google-Proof Q&A | 87.7 | — | https://openai.com/index/openai-o3-system-card/ |
| Massive Multi-discipline Multimodal Understanding | 82.9 | — | https://mmmu-benchmark.github.io/ |
| MathVista | 86.8 | — | https://llm-stats.com/benchmarks/mathvista |
| MathVista | 86.8 | — | https://llm-stats.com/benchmarks/mathvista |
| AIME 2024 | 96.7 | — | https://openai.com/index/openai-o3-system-card/ |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(10)
Best LLMs for Code GenerationListedBest LLMs for RAGListedBest AI Agents & Agentic ModelsListedBest Multimodal / Vision LLMsListedBest LLMs for Reasoning & MathListedBest LLMs for Function Calling & Tool UseListedCheapest LLM APIs You Can Call Right NowListedBest Long Context LLMsListedBest Mainstream LLM APIs, RankedListedBest LLMs for WritingListed
Comparison and alternatives
Browse all comparisons →o3 vs Claude Opus 4.6o3 vs Claude Sonnet 4.6o3 vs Gemini 3.1 Pro Previewo3 vs Gemini 2.5 Proo3 vs DeepSeek R1o3 vs Grok 4o3 vs Grok 4 Fast Reasoningo3 vs GPT-4o (08-06)o3 vs o1 (12-17)o3 vs Composer 2.5o3 vs GPT-5.5o3 vs Tencent Hy3 Previewo3 vs Tencent Hunyuan Turbo So3 vs GPT-5.4o3 vs DeepSeek V4 Flasho3 vs Claude Opus 4.7
Show all 53 popular comparisonssorted by 7-day search impressions
o3 vs Kimi K2.6219o3 vs Claude Sonnet 4.5166o3 vs DeepSeek V4 Pro148o3 vs Ling-2.6-1T126o3 vs Llama 3 8B Instruct116o3 vs Xiaomi MiMo-V2.582o3 vs Grok-379o3 vs Claude 3.7 Sonnet79o3 vs Step 3.5 Flash67o3 vs Gemini 2.5 Pro Preview 05-0664o3 vs DeepSeek V3.161o3 vs Mistral Large 260o3 vs Kimi K2 Thinking58o3 vs DeepSeek V355o3 vs GLM-5.151o3 vs DeepSeek V3.251o3 vs GPT-5.242o3 vs Kimi K2.538o3 vs Phi-3 Mini 4k37o3 vs Claude Opus 4.533o3 vs GLM-532o3 vs DeepSeek R1 052830o3 vs Trinity-Large-Thinking27o3 vs Qwen3-Max26o3 vs o3 Mini21o3 vs Qwen3.6-27B20o3 vs Mistral Large 2 (2407)20o3 vs Qwen3.6-35B-A3B18o3 vs Llama 3.1 70B Instruct17o3 vs DeepSeek V3 Base14o3 vs Llama 3.2 1B Instruct14o3 vs Qwen3.5-397B-A17B13o3 vs Llama 3 70B Instruct13o3 vs GLM-5V-Turbo12o3 vs Gemini 2.5 Flash11o3 vs GLM-5 9B11o3 vs Qwen2.5-7B-Instruct10o3 vs GLM-5 Turbo10o3 vs Qwen2.5-72B-Instruct9o3 vs Mixtral 8x22B Instruct v0.39o3 vs Ling-2.6-Flash8o3 vs Gemma 7B Instruct7o3 vs Mixtral 8x7B5o3 vs Qwen3.5-27B4o3 vs DeepSeek R1 Distill Llama 70B4o3 vs Qwen2-7B-Instruct3o3 vs Qwen3.5-122B-A10B3o3 vs Phi-4 Mini Flash Reasoning2o3 vs Llama 2 13B Chat1o3 vs Mixtral 8x7B Instruct v0.11o3 vs Qwen3.5-35B-A3B1o3 vs Gemini 3.1 Pro Preview Custom Tools1o3 vs Qwen3-235B-A22B0