OpenAI: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by OpenAI for your use-case.
Most Intelligent
Intelligence Index
Total 88 models
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 88 models
Lowest Price
Blended price (per 1M tokens)
Total 88 models
OpenAI offers 88 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on OpenAI are GPT-6 Astra (max) (57), GPT-6 Astra (max) (Flex) (57), and GPT-6 Astra (xhigh) (55).
- For time per task, GPT-6 Luna (low) (0.6 min), GPT-6.1 Terra (low) (1.2 min), and GPT-6 Luna (non-reasoning) (1.9 min) finish an Intelligence Index task fastest on OpenAI. Time per task varies significantly across models, with the slowest taking 4.0x longer than the quickest.
- For latency, GPT-5.4 nano (non-reasoning) (1.25s), GPT-5.4 mini (non-reasoning) (1.35s), and GPT-5.6 Luna (non-reasoning) (1.47s) offer the lowest time to first answer token.
- For pricing, GPT-6 Luna (max) (Flex) ($0.04), GPT-5 nano (minimal) ($0.05), and GPT-5 nano (medium) ($0.05) offer the lowest blended prices per 1M tokens.
- For context window size, GPT-6 Sol (max) (1M), GPT-6 Sol (low) (1M), and GPT-5.5 (xhigh) (1M) support the largest context windows on OpenAI.
Intelligence
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
Intelligence Index vs. Price
Pricing
Cost per Intelligence Index Task
Intelligence Index vs. Price
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task
Quality
Context Window
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate
Caching
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
Further Analysis | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
GPT-6 Astra (max) | 57 | $6.24 | 22.8 | 245.96 | 6.5% | 1M | Proprietary | |||
GPT-6 Astra (max) (Fast) | 57 | $12.49 | -- | -- | -- | 1M | Proprietary | |||
GPT-6 Astra (max) (Ultrafast) | 57 | $37.47 | -- | -- | -- | 1M | Proprietary | |||
GPT-6 Astra (max) (Flex) | 57 | $3.12 | 16.9 | 148.58 | 12.8% | 1M | Proprietary | |||
GPT-6 Astra (xhigh) | 55 | $3.66 | 11.6 | 111.97 | 3.4% | 1M | Proprietary | |||
GPT-6 Astra (high) | 55 | $3.24 | 9.4 | 63.44 | 1.6% | 1M | Proprietary | |||
GPT-6.1 Sol (max) | 55 | $1.27 | 23.3 | 197.65 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Sol (max) (Fast) | 55 | $2.54 | 15.2 | 128.56 | 0.8% | 1M | Proprietary | |||
GPT-6.1 Sol (max) (Flex) | 55 | $0.64 | 26.6 | 197.80 | 13.3% | 1M | Proprietary | |||
GPT-6.1 Sol (max) (Ultrafast) | 55 | $7.63 | 5.4 | 32.57 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Sol (xhigh) | 52 | $0.76 | 10.3 | 82.55 | 0.8% | 1M | Proprietary | |||
GPT-6 Astra (medium) | 52 | $2.73 | 7.5 | 7.07 | 1.5% | 1M | Proprietary | |||
GPT-6.1 Terra (max) | 51 | $0.96 | 14.3 | 176.31 | 1.0% | 1M | Proprietary | |||
GPT-6.1 Sol (high) | 50 | $0.59 | 7.8 | 40.91 | 0.7% | 1M | Proprietary | |||
GPT-6.1 Sol (medium) | 46 | $0.36 | 4.6 | 5.20 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Terra (xhigh) | 45 | $0.40 | 6.5 | 35.53 | 0.8% | 1M | Proprietary | |||
GPT-6 Sol (max) | 44 | $2.47 | 7.8 | 61.41 | 0.0% | 1M | Proprietary | |||
GPT-6 Astra (low) | 43 | $1.42 | 3.7 | 3.67 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Terra (high) | 42 | $0.26 | 4.3 | 12.70 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Terra (medium) | 38 | $0.17 | 2.9 | 5.11 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Sol (low) | 35 | $0.16 | 2.0 | 3.14 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Terra (max) | 32 | $3.73 | 11.0 | 84.97 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Terra (non-reasoning) | 31 | $0.23 | 2.4 | 2.13 | 0.0% | 1M | Proprietary | |||
GPT-6.1 Terra (low) | 29 | $0.0713 | 1.2 | 2.81 | 0.0% | 1M | Proprietary | |||
GPT-6 Luna (max) | 28 | $0.15 | 12.2 | 86.56 | 0.0% | 1M | Proprietary | |||
GPT-6 Luna (max) (Flex) | 28 | $0.076 | 28.8 | 151.84 | 23.6% | 1M | Proprietary | |||
GPT-5.6 Luna (max) | 24 | $0.33 | 9.3 | 64.85 | 0.0% | 1M | Proprietary | |||
GPT-6 Luna (xhigh) | 23 | $0.10 | 7.5 | 20.35 | 0.0% | 1M | Proprietary | |||
GPT-6 Luna (high) | 21 | $0.0729 | 5.8 | 13.37 | 0.7% | 1M | Proprietary | |||
GPT-6 Luna (medium) | 18 | $0.0422 | 3.6 | 6.49 | 0.0% | 1M | Proprietary | |||
GPT-6 Luna (low) | 10 | $0.0051 | 0.6 | 3.34 | 0.7% | 1M | Proprietary | |||
GPT-6 Luna (non-reasoning) | 9 | $0.0714 | 1.9 | 1.61 | 0.0% | 1M | Proprietary | |||
GPT-6 Sol (low) | -- | -- | -- | 2.12 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Luna (low) | -- | -- | -- | 2.68 | 0.0% | 1M | Proprietary | |||
GPT-5 nano (minimal) | -- | -- | -- | 1.43 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Sol (low) | -- | -- | -- | 3.23 | 0.0% | 1M | Proprietary | |||
o3 | -- | -- | -- | 7.12 | 0.0% | 200k | Proprietary | |||
GPT-5.5 (xhigh) | -- | -- | -- | 37.83 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Terra (medium) | -- | -- | -- | 2.77 | 0.0% | 1M | Proprietary | |||
GPT-5 mini (high) | -- | -- | -- | 48.98 | 2.7% | 400k | Proprietary | |||
GPT-5.4 mini (medium) | -- | -- | -- | 8.83 | 0.0% | 272k | Proprietary | |||
GPT-4.1 | -- | -- | -- | 3.00 | 0.0% | 1M | Proprietary | |||
GPT-5 (high) | -- | -- | -- | 53.74 | 2.3% | 400k | Proprietary | |||
GPT-5.4 (non-reasoning) | -- | -- | -- | 1.79 | 0.0% | 1M | Proprietary | |||
GPT-5.2 (xhigh) | -- | -- | -- | 92.63 | 0.0% | 400k | Proprietary | |||
GPT-5.1 (high) | -- | -- | -- | 38.68 | 0.0% | 400k | Proprietary | |||
GPT-6 Sol (high) | -- | -- | -- | 8.73 | 0.0% | 1M | Proprietary | |||
GPT-5.4 (low) | -- | -- | -- | 3.34 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Luna (medium) | -- | -- | -- | 3.29 | 0.0% | 1M | Proprietary | |||
GPT-5.3 Codex (xhigh) | -- | -- | -- | 46.26 | 0.7% | 400k | Proprietary | |||
o1 | -- | -- | -- | -- | -- | 200k | Proprietary | |||
GPT-5.4 Pro (xhigh) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
GPT-5 (medium) | -- | -- | -- | 24.02 | 2.2% | 400k | Proprietary | |||
GPT-5.5 (medium) | -- | -- | -- | 8.32 | 0.0% | 1M | Proprietary | |||
GPT-5.2 (non-reasoning) | -- | -- | -- | 1.68 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Sol (medium) | -- | -- | -- | 7.00 | 0.0% | 1M | Proprietary | |||
GPT-5.5 (non-reasoning) | -- | -- | -- | 1.66 | 0.0% | 1M | Proprietary | |||
GPT-6 Sol (medium) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
GPT-5.6 Sol (non-reasoning) | -- | -- | -- | 2.10 | 0.0% | 1M | Proprietary | |||
GPT-5 (low) | -- | -- | -- | 9.08 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Terra (high) | -- | -- | -- | 5.87 | 0.0% | 1M | Proprietary | |||
GPT-5.2 (medium) | -- | -- | -- | 9.35 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Luna (xhigh) | -- | -- | -- | 33.14 | 0.0% | 1M | Proprietary | |||
GPT-5.4 nano (medium) | -- | -- | -- | 7.19 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Sol (high) | -- | -- | -- | 12.73 | 0.0% | 1M | Proprietary | |||
GPT-4o (Aug) | -- | -- | -- | 2.10 | 0.0% | 128k | Proprietary | |||
GPT-5 nano (medium) | -- | -- | -- | 28.12 | 0.0% | 400k | Proprietary | |||
GPT-6 Sol (Daybreak Blue, max) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
GPT-5.6 Terra (non-reasoning) | -- | -- | -- | 1.54 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Terra (xhigh) | -- | -- | -- | 24.40 | 0.0% | 1M | Proprietary | |||
GPT-4.1 mini | -- | -- | -- | 1.57 | 0.0% | 1M | Proprietary | |||
GPT-5.4 (xhigh) | -- | -- | -- | 133.38 | 2.3% | 1M | Proprietary | |||
GPT-5.6 Luna (high) | -- | -- | -- | 11.33 | 0.0% | 1M | Proprietary | |||
GPT-5.4 mini (non-reasoning) | -- | -- | -- | 1.53 | 2.5% | 272k | Proprietary | |||
GPT-5.5 (high) | -- | -- | -- | 17.55 | 0.0% | 1M | Proprietary | |||
GPT-4o mini | -- | -- | -- | 2.44 | 2.5% | 128k | Proprietary | |||
GPT-5.4 mini (xhigh) | -- | -- | -- | 114.89 | 2.4% | 400k | Proprietary | |||
GPT-5 mini (minimal) | -- | -- | -- | 1.86 | 0.0% | 400k | Proprietary | |||
GPT-4o (Nov) | -- | -- | -- | 2.06 | 0.0% | 128k | Proprietary | |||
GPT-5.4 nano (non-reasoning) | -- | -- | -- | 1.30 | 0.0% | 400k | Proprietary | |||
GPT-5 mini (medium) | -- | -- | -- | 12.72 | 0.0% | 400k | Proprietary | |||
GPT-5 (minimal) | -- | -- | -- | 2.36 | 0.0% | 400k | Proprietary | |||
GPT-5.5 Instant (June 2026) | -- | -- | -- | 1.88 | 0.0% | 400k | Proprietary | |||
GPT-5.5 (low) | -- | -- | -- | 2.66 | 0.0% | 1M | Proprietary | |||
o3-pro | -- | -- | -- | -- | -- | 200k | Proprietary | |||
GPT-5.6 Terra (low) | -- | -- | -- | 2.74 | 0.0% | 1M | Proprietary | |||
GPT-5.1 (non-reasoning) | -- | -- | -- | 2.19 | 0.0% | 400k | Proprietary | |||
GPT-6 Sol (non-reasoning) | -- | -- | -- | 1.68 | 0.0% | 1M | Proprietary | |||
GPT-5.4 nano (xhigh) | -- | -- | -- | 79.90 | 0.0% | 400k | Proprietary | |||
GPT-5.6 Sol (max) | -- | -- | -- | 54.66 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Sol (xhigh) | -- | -- | -- | 23.46 | 0.0% | 1M | Proprietary | |||
GPT-6 Sol (xhigh) | -- | -- | -- | 20.82 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Luna (non-reasoning) | -- | -- | -- | 1.48 | 0.0% | 1M | Proprietary | |||
GPT-5 nano (high) | -- | -- | -- | 60.43 | 0.0% | 400k | Proprietary | |||
GPT-5.5 Instant (May 2026) | -- | -- | -- | -- | -- | 400k | Proprietary | |||
o1-pro | -- | -- | -- | -- | -- | 200k | Proprietary | |||
GPT-4o (May) | -- | -- | -- | 2.08 | 0.0% | 128k | Proprietary | |||
Key definitions
Frequently Asked Questions
Common questions about OpenAI
OpenAI offers 88 models that we track: GPT-6 Astra (max), GPT-6 Astra (max) (Flex), GPT-6 Astra (xhigh), GPT-6 Astra (high), GPT-6.1 Sol (max), GPT-6.1 Sol (max) (Fast), GPT-6.1 Sol (max) (Flex), GPT-6.1 Sol (max) (Ultrafast), GPT-6.1 Sol (xhigh), GPT-6 Astra (medium), GPT-6.1 Terra (max), GPT-6.1 Sol (high), GPT-6.1 Sol (medium), GPT-6.1 Terra (xhigh), GPT-6 Sol (max), GPT-6 Astra (low), GPT-6.1 Terra (high), GPT-6.1 Terra (medium), GPT-6.1 Sol (low), GPT-5.6 Terra (max), GPT-6.1 Terra (non-reasoning), GPT-6.1 Terra (low), GPT-6 Luna (max), GPT-6 Luna (max) (Flex), GPT-5.6 Luna (max), GPT-6 Luna (xhigh), GPT-6 Luna (high), GPT-6 Luna (medium), GPT-6 Luna (low), GPT-6 Luna (non-reasoning), GPT-6 Sol (low), GPT-5.6 Luna (low), GPT-5 nano (minimal), GPT-5.6 Sol (low), o3, GPT-5.5 (xhigh), GPT-5.6 Terra (medium), GPT-5 mini (high), GPT-5.4 mini (medium), GPT-4.1, GPT-5 (high), GPT-5.4 (non-reasoning), GPT-5.2 (xhigh), GPT-5.1 (high), GPT-6 Sol (high), GPT-5.4 (low), GPT-5.6 Luna (medium), GPT-5.3 Codex (xhigh), GPT-5 (medium), GPT-5.5 (medium), GPT-5.2 (non-reasoning), GPT-5.6 Sol (medium), GPT-5.5 (non-reasoning), GPT-5.6 Sol (non-reasoning), GPT-5 (low), GPT-5.6 Terra (high), GPT-5.2 (medium), GPT-5.6 Luna (xhigh), GPT-5.4 nano (medium), GPT-5.6 Sol (high), GPT-4o (Aug), GPT-5 nano (medium), GPT-5.6 Terra (non-reasoning), GPT-5.6 Terra (xhigh), GPT-4.1 mini, GPT-5.4 (xhigh), GPT-5.6 Luna (high), GPT-5.4 mini (non-reasoning), GPT-5.5 (high), GPT-4o mini, GPT-5.4 mini (xhigh), GPT-5 mini (minimal), GPT-4o (Nov), GPT-5.4 nano (non-reasoning), GPT-5 mini (medium), GPT-5 (minimal), GPT-5.5 Instant (June 2026), GPT-5.5 (low), GPT-5.6 Terra (low), GPT-5.1 (non-reasoning), GPT-6 Sol (non-reasoning), GPT-5.4 nano (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (xhigh), GPT-6 Sol (xhigh), GPT-5.6 Luna (non-reasoning), GPT-5 nano (high), and GPT-4o (May).
The most intelligent model available on OpenAI is GPT-6 Astra (max) with an Intelligence Index score of 57.
The model with the lowest time per task on OpenAI is GPT-6 Luna (low) at 0.6 minutes per Intelligence Index task. Time per task is the output tokens per task divided by end-to-end output speed, so lower means a task finishes sooner.
The model with the lowest time to first answer token on OpenAI is GPT-5.4 nano (non-reasoning) at 1.25s. Lower latency means faster initial response time.
The most affordable model on OpenAI by blended price is GPT-6 Luna (max) (Flex) at $0.0385 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on OpenAI vary up to 229.1x across models, from $0.0385 per 1M tokens for GPT-6 Luna (max) (Flex) to $8.82 per 1M tokens for GPT-6.1 Sol (max) (Ultrafast).
Yes, OpenAI offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 88 models on OpenAI support JSON mode for structured output.
Yes, all 88 models on OpenAI support function calling (tool use).
Yes, OpenAI offers 67 reasoning models: GPT-6 Astra (max), GPT-6 Astra (max) (Flex), GPT-6 Astra (xhigh), GPT-6 Astra (high), GPT-6.1 Sol (max), GPT-6.1 Sol (max) (Fast), GPT-6.1 Sol (max) (Flex), GPT-6.1 Sol (max) (Ultrafast), GPT-6.1 Sol (xhigh), GPT-6 Astra (medium), GPT-6.1 Terra (max), GPT-6.1 Sol (high), GPT-6.1 Sol (medium), GPT-6.1 Terra (xhigh), GPT-6 Sol (max), GPT-6 Astra (low), GPT-6.1 Terra (high), GPT-6.1 Terra (medium), GPT-6.1 Sol (low), GPT-5.6 Terra (max), GPT-6.1 Terra (low), GPT-6 Luna (max), GPT-6 Luna (max) (Flex), GPT-5.6 Luna (max), GPT-6 Luna (xhigh), GPT-6 Luna (high), GPT-6 Luna (medium), GPT-6 Luna (low), GPT-6 Sol (low), GPT-5.6 Luna (low), GPT-5.6 Sol (low), o3, GPT-5.5 (xhigh), GPT-5.6 Terra (medium), GPT-5 mini (high), GPT-5.4 mini (medium), GPT-5 (high), GPT-5.2 (xhigh), GPT-5.1 (high), GPT-6 Sol (high), GPT-5.4 (low), GPT-5.6 Luna (medium), GPT-5.3 Codex (xhigh), GPT-5 (medium), GPT-5.5 (medium), GPT-5.6 Sol (medium), GPT-5 (low), GPT-5.6 Terra (high), GPT-5.2 (medium), GPT-5.6 Luna (xhigh), GPT-5.4 nano (medium), GPT-5.6 Sol (high), GPT-5 nano (medium), GPT-5.6 Terra (xhigh), GPT-5.4 (xhigh), GPT-5.6 Luna (high), GPT-5.5 (high), GPT-5.4 mini (xhigh), GPT-5 mini (medium), GPT-5.5 Instant (June 2026), GPT-5.5 (low), GPT-5.6 Terra (low), GPT-5.4 nano (xhigh), GPT-5.6 Sol (max), GPT-5.6 Sol (xhigh), GPT-6 Sol (xhigh), and GPT-5 nano (high). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on OpenAI, consider: intelligence (for quality-sensitive tasks), time per task (how quickly the model completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.