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
GPT-6 Astra (max)GPT-6 Astra (max) (Flex)GPT-6 Astra (xhigh)GPT-6 Astra (high)GPT-6.1 Sol (max)Intelligence Index
Total 87 models
Fastest
GPT-6.1 Sol (max) (Ultrafast)GPT-5.4 mini (xhigh)GPT-5.4 mini (medium)GPT-5.4 mini (non-reasoning)GPT-4o (Nov)Output speed
Total 87 models
Lowest Price
GPT-6 Luna (max) (Flex)GPT-5 nano (minimal)GPT-5 nano (medium)GPT-5 nano (high)GPT-6 Luna (max)Blended price (per 1M tokens)
Total 87 models
OpenAI offers 87 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 output speed, the fastest models are GPT-6.1 Sol (max) (Ultrafast) (333 t/s), GPT-5.4 mini (xhigh) (226 t/s), and GPT-5.4 mini (medium) (200 t/s). Speed varies significantly across models, with a 87% difference between the fastest and slowest.
- For latency, GPT-5.4 nano (non-reasoning) (0.65s), GPT-5.6 Terra (non-reasoning) (0.76s), and GPT-5.4 mini (non-reasoning) (0.78s) 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 (low) (1M), GPT-5.5 (xhigh) (1M), and GPT-5.4 (non-reasoning) (1M) support the largest context windows on OpenAI.
Intelligence Evaluations
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
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
GPT-6 Astra (max) | 1M | Proprietary | 57 | $6.24 | 71 | 268.74 | 275.77 | -- | |||
GPT-6 Astra (max) (Fast) | 1M | Proprietary | 57 | $12.49 | -- | -- | -- | -- | |||
GPT-6 Astra (max) (Ultrafast) | 1M | Proprietary | 57 | $37.47 | -- | -- | -- | -- | |||
GPT-6 Astra (max) (Flex) | 1M | Proprietary | 57 | $3.12 | 98 | 259.91 | 265.00 | -- | |||
GPT-6 Astra (xhigh) | 1M | Proprietary | 55 | $3.66 | 68 | 158.59 | 165.92 | -- | |||
GPT-6 Astra (high) | 1M | Proprietary | 55 | $3.24 | 63 | 43.97 | 51.94 | -- | |||
GPT-6.1 Sol (max) | 1M | Proprietary | 55 | $1.27 | 81 | 278.01 | 284.18 | -- | |||
GPT-6.1 Sol (max) (Fast) | 1M | Proprietary | 55 | $2.54 | 140 | 149.85 | 153.42 | -- | |||
GPT-6.1 Sol (max) (Flex) | 1M | Proprietary | 55 | $0.64 | 117 | 213.63 | 217.91 | -- | |||
GPT-6.1 Sol (max) (Ultrafast) | 1M | Proprietary | 55 | $7.63 | 333 | 57.04 | 58.55 | -- | |||
GPT-6.1 Sol (xhigh) | 1M | Proprietary | 52 | $0.76 | 70 | 106.40 | 113.59 | -- | |||
GPT-6 Astra (medium) | 1M | Proprietary | 51 | $2.73 | 59 | 4.57 | 13.04 | -- | |||
GPT-6.1 Terra (max) | 1M | Proprietary | 51 | $0.96 | 91 | 77.96 | 83.46 | -- | |||
GPT-6.1 Sol (high) | 1M | Proprietary | 50 | $0.59 | 70 | 40.76 | 47.91 | -- | |||
GPT-6.1 Sol (medium) | 1M | Proprietary | 46 | $0.36 | 59 | 3.62 | 12.11 | -- | |||
GPT-6.1 Terra (xhigh) | 1M | Proprietary | 45 | $0.40 | 91 | 17.50 | 23.00 | -- | |||
GPT-6 Astra (low) | 1M | Proprietary | 43 | $1.42 | 48 | 2.71 | 13.06 | -- | |||
GPT-6.1 Terra (high) | 1M | Proprietary | 42 | $0.26 | 91 | 5.66 | 11.16 | -- | |||
GPT-6.1 Terra (medium) | 1M | Proprietary | 38 | $0.17 | 91 | 1.65 | 7.15 | -- | |||
GPT-6.1 Sol (low) | 1M | Proprietary | 35 | $0.16 | 61 | 2.36 | 10.58 | -- | |||
GPT-6.1 Terra (non-reasoning) | 1M | Proprietary | 30 | $0.23 | 91 | 1.00 | 6.49 | -- | |||
GPT-6.1 Terra (low) | 1M | Proprietary | 29 | $0.07 | 91 | 1.29 | 6.79 | -- | |||
GPT-6 Luna (max) | 1M | Proprietary | 28 | $0.15 | 124 | 76.60 | 80.62 | -- | |||
GPT-6 Luna (max) (Flex) | 1M | Proprietary | 28 | $0.08 | 64 | 166.42 | 174.24 | -- | |||
GPT-6 Luna (xhigh) | 1M | Proprietary | 23 | $0.10 | 123 | 16.80 | 20.88 | -- | |||
GPT-6 Luna (high) | 1M | Proprietary | 21 | $0.07 | 122 | 13.72 | 17.82 | -- | |||
GPT-6 Luna (medium) | 1M | Proprietary | 18 | $0.04 | -- | -- | -- | -- | |||
GPT-6 Luna (low) | 1M | Proprietary | 10 | $0.01 | 119 | 2.43 | 6.63 | -- | |||
GPT-6 Luna (non-reasoning) | 1M | Proprietary | 9 | $0.07 | 116 | 0.89 | 5.18 | -- | |||
GPT-6 Sol (low) | 1.05M | Proprietary | -- | -- | 110 | 1.59 | 6.12 | -- | |||
GPT-5.6 Luna (low) | 1M | Proprietary | -- | -- | 119 | 1.42 | 5.63 | -- | |||
GPT-5 nano (minimal) | 400k | Proprietary | -- | -- | 144 | 0.84 | 4.32 | -- | |||
GPT-5 nano (minimal) private | 400k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.6 Sol (low) | 1M | Proprietary | -- | -- | 80 | 1.99 | 8.22 | -- | |||
o3 | 200k | Proprietary | -- | -- | 164 | 7.24 | 10.28 | -- | |||
GPT-5.5 (xhigh) | 1.05M | Proprietary | -- | -- | 91 | 61.42 | 66.93 | -- | |||
GPT-5.6 Terra (medium) | 1M | Proprietary | -- | -- | 111 | 1.62 | 6.14 | -- | |||
GPT-5 mini (high) | 400k | Proprietary | -- | -- | 116 | 63.09 | 67.42 | -- | |||
GPT-5.4 mini (medium) | 272k | Proprietary | -- | -- | 200 | 7.00 | 9.50 | -- | |||
GPT-4.1 | 1M | Proprietary | -- | -- | 165 | 0.94 | 3.96 | -- | |||
GPT-5.6 Luna (max) | 1M | Proprietary | -- | -- | 127 | 108.65 | 112.60 | -- | |||
GPT-5 (high) | 400k | Proprietary | -- | -- | 106 | 64.64 | 69.34 | -- | |||
GPT-5.4 (non-reasoning) | 1.05M | Proprietary | -- | -- | 75 | 0.89 | 7.58 | -- | |||
GPT-5.2 (xhigh) | 400k | Proprietary | -- | -- | 76 | 99.54 | 106.10 | -- | |||
GPT-5.1 (high) | 400k | Proprietary | -- | -- | 133 | 39.14 | 42.88 | -- | |||
GPT-6 Sol (high) | 1.05M | Proprietary | -- | -- | 113 | 10.04 | 14.46 | -- | |||
GPT-5.4 (low) | 1.05M | Proprietary | -- | -- | 73 | 2.08 | 8.96 | -- | |||
GPT-5.6 Luna (medium) | 1M | Proprietary | -- | -- | 114 | 2.28 | 6.67 | -- | |||
GPT-5.3 Codex (xhigh) | 400k | Proprietary | -- | -- | 95 | 55.75 | 61.01 | -- | |||
o1 | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.4 Pro (xhigh) | 1.05M | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5 (medium) | 400k | Proprietary | -- | -- | 103 | 27.95 | 32.78 | -- | |||
GPT-5.5 (medium) | 1.05M | Proprietary | -- | -- | 83 | 4.90 | 10.92 | -- | |||
GPT-5.2 (non-reasoning) | 400k | Proprietary | -- | -- | 71 | 0.79 | 7.80 | -- | |||
GPT-5.6 Sol (medium) | 1M | Proprietary | -- | -- | 80 | 3.76 | 10.00 | -- | |||
GPT-5.5 (non-reasoning) | 1.05M | Proprietary | -- | -- | 81 | 1.01 | 7.19 | -- | |||
GPT-6 Sol (medium) | 1.05M | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.6 Sol (non-reasoning) | 1M | Proprietary | -- | -- | 84 | 0.97 | 6.94 | -- | |||
GPT-5 (low) | 400k | Proprietary | -- | -- | 95 | 7.32 | 12.58 | -- | |||
GPT-5.6 Terra (high) | 1M | Proprietary | -- | -- | 117 | 2.19 | 6.46 | -- | |||
o4-mini (high) | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.2 (medium) | 400k | Proprietary | -- | -- | 81 | 5.21 | 11.36 | -- | |||
GPT-5.6 Luna (xhigh) | 1M | Proprietary | -- | -- | 122 | 36.67 | 40.78 | -- | |||
GPT-5.4 nano (medium) | 400k | Proprietary | -- | -- | 173 | 6.05 | 8.93 | -- | |||
GPT-5.6 Sol (high) | 1M | Proprietary | -- | -- | 83 | 10.34 | 16.35 | -- | |||
GPT-4o (Aug) | 128k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-4o (Aug) | 128k | Proprietary | -- | -- | 136 | 1.01 | 4.70 | -- | |||
GPT-5 nano (medium) | 400k | Proprietary | -- | -- | 161 | 32.97 | 36.07 | -- | |||
GPT-6 Sol (Daybreak Blue, max) | 1.05M | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.6 Terra (non-reasoning) | 1M | Proprietary | -- | -- | 117 | 0.76 | 5.03 | -- | |||
GPT-5.6 Terra (xhigh) | 1M | Proprietary | -- | -- | 116 | 9.98 | 14.29 | -- | |||
GPT-4.1 mini | 1M | Proprietary | -- | -- | 161 | 0.81 | 3.92 | -- | |||
GPT-5.4 (xhigh) | 1.05M | Proprietary | -- | -- | 101 | 148.82 | 153.76 | -- | |||
GPT-5.6 Luna (high) | 1M | Proprietary | -- | -- | 121 | 9.87 | 14.00 | -- | |||
GPT-5.4 mini (non-reasoning) | 272k | Proprietary | -- | -- | 183 | 0.78 | 3.51 | -- | |||
GPT-5.5 (high) | 1.05M | Proprietary | -- | -- | 92 | 15.25 | 20.68 | -- | |||
GPT-4o mini | 128k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-4o mini | 128k | Proprietary | -- | -- | 105 | 0.84 | 5.58 | -- | |||
GPT-5.4 mini (xhigh) | 400k | Proprietary | -- | -- | 226 | 115.18 | 117.39 | -- | |||
GPT-5 mini (minimal) | 400k | Proprietary | -- | -- | 110 | 0.97 | 5.51 | -- | |||
GPT-5 mini (minimal) private | 400k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.6 Terra (max) | 1M | Proprietary | -- | -- | 132 | 104.03 | 107.83 | -- | |||
GPT-4o (Nov) | 128k | Proprietary | -- | -- | 178 | 1.01 | 3.82 | -- | |||
GPT-5.4 nano (non-reasoning) | 400k | Proprietary | -- | -- | 166 | 0.65 | 3.66 | -- | |||
GPT-5 mini (medium) | 400k | Proprietary | -- | -- | 114 | 13.14 | 17.52 | -- | |||
GPT-5 (minimal) | 400k | Proprietary | -- | -- | 86 | 1.17 | 6.95 | -- | |||
GPT-5 (minimal) private | 400k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.5 Instant (June 2026) | 400k | Proprietary | -- | -- | 166 | 0.88 | 15.90 | 12.02 | |||
GPT-6 Sol (max) | 1.05M | Proprietary | -- | -- | 112 | 105.58 | 110.06 | -- | |||
GPT-5.5 (low) | 1.05M | Proprietary | -- | -- | 87 | 1.81 | 7.59 | -- | |||
o3-pro | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-5.6 Terra (low) | 1M | Proprietary | -- | -- | 118 | 1.57 | 5.80 | -- | |||
GPT-5.1 (non-reasoning) | 400k | Proprietary | -- | -- | 108 | 1.18 | 5.81 | -- | |||
GPT-6 Sol (non-reasoning) | 1.05M | Proprietary | -- | -- | 108 | 0.85 | 5.49 | -- | |||
GPT-5.4 nano (xhigh) | 400k | Proprietary | -- | -- | 164 | 47.02 | 50.08 | -- | |||
GPT-5.6 Sol (max) | 1M | Proprietary | -- | -- | 82 | 105.33 | 111.42 | -- | |||
GPT-5.6 Sol (xhigh) | 1M | Proprietary | -- | -- | 82 | 32.68 | 38.75 | -- | |||
GPT-6 Sol (xhigh) | 1.05M | Proprietary | -- | -- | 116 | 35.72 | 40.05 | -- | |||
GPT-5.6 Luna (non-reasoning) | 1M | Proprietary | -- | -- | 117 | 0.80 | 5.09 | -- | |||
GPT-5 nano (high) | 400k | Proprietary | -- | -- | 149 | 71.99 | 75.34 | -- | |||
GPT-5.5 Instant (May 2026) | 400k | Proprietary | -- | -- | -- | -- | -- | -- | |||
o1-pro | 200k | Proprietary | -- | -- | -- | -- | -- | -- | |||
GPT-4o (May) | 128k | Proprietary | -- | -- | 139 | 1.08 | 4.67 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about OpenAI
OpenAI offers 87 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 Astra (low), GPT-6.1 Terra (high), GPT-6.1 Terra (medium), GPT-6.1 Sol (low), GPT-6.1 Terra (non-reasoning), GPT-6.1 Terra (low), GPT-6 Luna (max), GPT-6 Luna (max) (Flex), GPT-6 Luna (xhigh), GPT-6 Luna (high), 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-5.6 Luna (max), 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-5.6 Terra (max), GPT-4o (Nov), GPT-5.4 nano (non-reasoning), GPT-5 mini (medium), GPT-5 (minimal), GPT-5.5 Instant (June 2026), GPT-6 Sol (max), 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 fastest model on OpenAI by output speed is GPT-6.1 Sol (max) (Ultrafast) at 332.7 tokens per second.
The model with the lowest time to first answer token on OpenAI is GPT-5.4 nano (non-reasoning) at 0.65s. Lower latency means faster initial response time.
The most affordable model on OpenAI by blended price is GPT-6 Luna (max) (Flex) at $0.04 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on OpenAI vary up to 229x across models, from $0.04 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 87 models on OpenAI support JSON mode for structured output.
Yes, all 87 models on OpenAI support function calling (tool use).
Yes, OpenAI offers 66 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 Astra (low), GPT-6.1 Terra (high), GPT-6.1 Terra (medium), GPT-6.1 Sol (low), GPT-6.1 Terra (low), GPT-6 Luna (max), GPT-6 Luna (max) (Flex), GPT-6 Luna (xhigh), GPT-6 Luna (high), 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-5.6 Luna (max), 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-5.6 Terra (max), GPT-5 mini (medium), GPT-5.5 Instant (June 2026), GPT-6 Sol (max), 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), output speed (for throughput-intensive tasks), 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.