GPT-4o (2024-08-06)
GPT-4o (2024-08-06)Alternatives?
CheaperGPT-6.1 Solmax+53%-9%$0.72Remove unsupported parameters+5BetterGPT-6 Lunalow+35%-95%$0.005Function calling only with none · Chat Completions+3
OpenMuse Spark Openxhigh+44%-54%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
CheaperGemini 3.8 Flashhigh+52%-66%*$1.24Sampling parameters are ignored+1CheaperGemini 3.6 Flashhigh+48%-66%*$1.60GPT-6.1 Solmax+53%-9%$0.72Remove unsupported parameters+5Gemini 3.8 Flashhigh+52%-66%*$1.24Sampling parameters are ignored+1Gemini 3.6 Flashhigh+48%-66%*$1.60GPT-6 Solmax+47%-9%$1.04
Qwen3.8 Max (0902)thinking+47%-31%$5.41GPT-6 Lunalow+35%-95%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+31%-90%$0.01
MiMo v2.5thinkingOpen+34%-96%$0.019Llama 4 Mavericknon-thinkingOpen+10%-93%$0.038GPT-5 Minihigh+24%-84%$0.053Muse Spark OpenxhighOpen+44%-54%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
DeepSeek V4.1 Flash 1017maxOpen+43%-88%$0.26Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen+43%+37%$2.00Sampling parameters are fixed+3Qwen3.8 FlashthinkingOpen+42%-95%$0.37max_tokens range · QwenCloud+5Kimi K2.6thinkingOpen+41%-61%$0.80GPT-6 Astramedium+51%—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium+49%—$0.21Remove unsupported parameters+5GPT-5.6 Solmedium+45%—$0.50GPT-5.5medium+44%—$0.90Prompts with >272K input tokensGPT-6 Solmedium+43%—$0.25GPT-5.3 Codexxhigh+39%—$1.75 / $14DeprecatedGPT-6 Lunamedium+38%—$0.017Function calling only with none · Chat Completions+3GPT-5.6 Terramedium+36%—$0.18Prompts with >272K input tokensAll OpenAI models →History
17 versionsBenchmarks
in Vision & DocumentsFAQ
How much does GPT-4o (2024-08-06) cost?›
$2.50 per 1M input tokens and $10 per 1M output tokens; cached input $1.25 per 1M.
Is GPT-4o (2024-08-06) free to use?›
There is no free API; the cheapest paid price is $2.50 per 1M input tokens.
How good is GPT-4o (2024-08-06), and what is it best at?›
#333 of 334 in Chat & Knowledge, #132 of 239 in Coding, #151 of 242 in Agents & Tool Use, #180 of 245 in Writing & Language, #103 of 124 in Vision & Documents.
Is GPT-4o (2024-08-06) better than Qwen3 VL 8B (Reasoning)?›
On MMMU-Pro (vision), GPT-4o (2024-08-06) scores 56.3 vs 56.6 — about the same.
How can I use GPT-4o (2024-08-06)?›
Through the API of Azure, OpenAI.
What is the context window of GPT-4o (2024-08-06)?›
128K tokens, with up to 16K output tokens.
When was GPT-4o (2024-08-06) released? Is there a newer version?›
Released 2024-08-06. It is deprecated by the lab.
Is GPT-4o (2024-08-06) open source?›
No, GPT-4o (2024-08-06) is a closed model available through an API. The closest open-weights option here is Muse Spark Open.
Can GPT-4o (2024-08-06) read images?›
It accepts text and images, PDF files as input.
What is GPT-4o (2024-08-06)?›
GPT-4o (2024-08-06) is a closed language model from OpenAI, released Aug 2024.
What are the best alternatives to GPT-4o (2024-08-06)?›
GPT-6.1 Sol (cheaper), GPT-6 Luna (better), Muse Spark Open (open weights).