PRICE~z-ai/glm-flash-latest output_per_mtok increased from 0.60 to 0.939mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.20 to 0.959mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00589mPRICEz-ai/glm-5.2 cached_input_per_mtok decreased from 0.32 to 0.269mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00779mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00779mPRICE~moonshotai/kimi-latest input_per_mtok increased from 1.34 to 1.3940mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0038 to 0.001140mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008640mPRICEgoogle/gemma-4-26b-a4b-it cached_input_per_mtok decreased from 0.05 to 0.03840mPRICEgoogle/gemma-4-26b-a4b-it output_per_mtok decreased from 0.30 to 0.2340mPRICEgoogle/gemma-4-26b-a4b-it input_per_mtok decreased from 0.09 to 0.06840mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.01240mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.01240mPRICE~z-ai/glm-flash-latest output_per_mtok decreased from 0.90 to 0.601hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0058 to 0.00381hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.47 to 1.201hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00381hPRICEz-ai/glm-5.2 cached_input_per_mtok increased from 0.26 to 0.321hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.0171hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.0171hPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802hPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002hPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.50 to 1.342hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.00582hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.472hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.00582hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.006 to 0.022hPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.50 to 0.602hPRICEz-ai/glm-5.3-flash cached_input_per_mtok increased from 0.011 to 0.032hPRICEz-ai/glm-5.3-flash output_per_mtok decreased from 0.90 to 0.502hPRICEz-ai/glm-5.3-flash input_per_mtok increased from 0.026 to 0.152hPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.006 to 0.022hPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.50 to 0.602hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.00772hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.00772hPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok increased from 0.27 to 0.302hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0038 to 0.0132hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.0132hPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.42 to 0.502h

OpenAI — AI inference benchmarks

US · serverless · 2 benchmarked models · 1 region
#6 GLOBALAdd to compare
Overall90.4Rel.100.0%Tools100.0%JSON100.0%TTFT1040 msP952453 msTok/s96Price$2.60 / $15.60Δ30d↓ 0.8request shape: default temp · max_completion_tokens · no-reasoning tools● last run 2h ago · 8 runs in 24h

Provider vs market

Percentile across 8 ranked providers
Reliability 100.0%P100
Tools 100.0%P100
Structured 100.0%P100
TTFT 1040 msP13
Throughput 96 tok/sP38
Cost $15.60P13

Price vs performance

OpenAI highlighted vs peers
879196100$4.37$8.74$13.10$17.47Output price $/M →Score ↑Cerebras — $0.75/M out · score 99.0Groq — $0.45/M out · score 98.2Mistral — $4.50/M out · score 93.2Scaleway — $1.81/M out · score 92.4Cortecs — $1.23/M out · score 92.2OpenAI — $15.60/M out · score 90.4OpenAITogether — $1.12/M out · score 85.8OpenRouter — $1.20/M out · score 84.4

30-day trend

Measured daily series
Score90.4
TTFT1134 ms
Tools100.0%
Reliability100.0%
Price$30.00

Key positioning

Derived from benchmark percentiles
Strengths
  • Reliability (P100)
  • Tools (P100)
  • Structured (P100)
Weaknesses
  • TTFT (P13)
  • Throughput (P38)
  • Cost (P13)
Best suited for

OpenAI in the registry

  • HeadquartersUS
  • API protocolsopenai chat completions, openai responses
  • Catalogued endpoints1
  • Websiteopenai.com
  • Last verified2026-10-02

Observed models & declared pricing

Read from OpenAI's own catalogue by continuous discovery — declared data, not benchmark results.

ModelObserved
babbage-0022026-10-02
chat-latest2026-10-02
chatgpt-image-latest2026-10-02
computer-use-preview2026-10-02
computer-use-preview-2025-03-112026-10-02
davinci-0022026-10-02
gpt-3.5-turbo2026-10-02
gpt-3.5-turbo-01252026-10-02
gpt-3.5-turbo-11062026-10-02
gpt-3.5-turbo-16k2026-10-02
gpt-3.5-turbo-instruct2026-10-02
gpt-3.5-turbo-instruct-09142026-10-02
gpt-42026-10-02
gpt-4-06132026-10-02
gpt-4-turbo2026-10-02
gpt-4-turbo-2024-04-092026-10-02
gpt-4.12026-10-02
gpt-4.1-2025-04-142026-10-02
gpt-4.1-mini2026-10-02
gpt-4.1-mini-2025-04-142026-10-02
gpt-4.1-nano2026-10-02
gpt-4.1-nano-2025-04-142026-10-02
gpt-4o2026-10-02
gpt-4o-2024-05-132026-10-02
gpt-4o-2024-08-062026-10-02
gpt-4o-2024-11-202026-10-02
gpt-4o-mini2026-10-02
gpt-4o-mini-2024-07-182026-10-02
gpt-4o-mini-search-preview2026-10-02
gpt-4o-mini-search-preview-2025-03-112026-10-02

All providers · How we benchmark