OpenAI models: which of the 30 GPT and Codex options fits

Prices from official vendor price lists · October 2026
OpenAI has 30 models in this rating, led by GPT-6 Astra and GPT-6.1 Sol. Output prices run from $0.3 to $180 per 1M tokens, and context windows reach 1.05M. 1 ships open weights.
OpenAI
Services found: 30
#AI modelCapabilitiesAPI $/1M (in / out)Context windowPrice / moOutput $/1MOverviewVisit site
21

gpt-oss-safeguard-20b

OpenAI
Text & chatStructured JSON outputCode execution
$0.075 / $0.3131.1K tokensAPI only0.3View
22

GPT-5.2-Codex

OpenAI
Text & chatVisionCoding
$1.75 / $14400K tokensAPI only14View
23

GPT-5.1-Codex-Mini

OpenAI
Text & chatVisionCoding
$0.25 / $2400K tokensAPI only2View
24

GPT-5.4 Image 2

OpenAI
VisionImage generationStructured JSON output
$8 / $15272K tokensAPI only15View
25

GPT-5.1-Codex

OpenAI
Text & chatVisionCoding
$1.25 / $10400K tokensAPI only10View
26

GPT-5.5 Pro

OpenAI
Text & chatVisionReasoning
$30 / $1801.05M tokensAPI only180View
27

GPT-5.1-Codex-Max

OpenAI
Text & chatVisionCoding
$1.25 / $10400K tokensAPI only10View
28

GPT Audio Mini

OpenAI
Text & chatAudioStructured JSON output
$0.6 / $2.4128K tokensAPI only2.4View
29

GPT-5 Image Mini

OpenAI
VisionImage generationStructured JSON output
$2.5 / $2400K tokensAPI only2View
30

GPT-5.4 Pro

OpenAI
Text & chatVisionReasoning
$30 / $1801.05M tokensAPI only180View

Browse by need

Reasoning models169 modelsCoding assistants17 modelsVision and images156 modelsLong context 1M+82 modelsFree tier available80 modelsOpen weights88 models

OpenAI fields the broadest capability spread in this rating: text and reasoning across the GPT-6 and GPT-5.6 generations, a dedicated Codex model, realtime speech, image generation and the open-weight gpt-oss line. GPT-6 Astra sits at the top at $10 input and $50 output per 1M tokens.

The 5.6 family is where most production traffic belongs. Sol, Terra and Luna split the mid tier by price and speed, all on a 1.05M context window, so you can move between them without re-engineering prompts. Fast mode doubles the rate for lower latency; batch halves it for work that can wait.

Deepest toolingThe widest ecosystem of SDKs, agent frameworks and integrations.
Split mid tierSol, Terra and Luna let you tune price against speed without changing vendor.
No free API tierEvaluation costs money here, unlike Google, Alibaba or DeepSeek.

Models from this vendor

30 OpenAI models in this rating. Prices are input and output per 1M tokens from the vendor official price list; for dirhams multiply by 3.6725. Tap a card to open the model page.

GPT-6 Astra
#1
OpenAI
in $10out $501.05M tokensText & chatVision
GPT-6.1 Sol
#2
OpenAI
in $2out $101.05M tokensText & chatVision
GPT-6 Sol
#3
OpenAI
in $2out $101.05M tokensText & chatVision
GPT-6 Luna
#4
OpenAI
in $0.1out $0.51.05M tokensText & chatVision
GPT-5.6 Sol
#5
OpenAI
in $4out $201.05M tokensText & chatVision
GPT-5.6 Terra
#6
OpenAI
in $2out $121.05M tokensText & chatVision
GPT-5.5
#7
OpenAI
in $5out $301.05M tokensText & chatVision
GPT-5.6 Luna
#8
OpenAI
in $0.2out $1.21.05M tokensText & chatVision

How to choose

  • Split the mid tier deliberately: Luna for routing, Terra for general work, Sol when quality matters.
  • Use Fast mode only on user-facing paths; it doubles the rate for latency alone.
  • Check the long-context threshold — above 272K tokens input doubles and output rises by half.
  • Pin snapshot versions rather than floating aliases if behaviour stability matters.

Common mistakes

Running everything on AstraAt $50 output it is four times Terra for work Terra handles identically.
Missing the deprecation calendarOpenAI retires models on a published schedule; floating aliases change under you.

Who this suits

Product teamsThe widest SDK and agent-framework ecosystem, so integration cost is lowest.
Voice productsRealtime models with 128K context and mature barge-in handling.
CodingGPT-5.3-Codex at $1.75 input sits well below the general flagships.

Related filters

Text & chat228 models for text generation and chat
Vision156 models that read images
Reasoning169 models that think before answering
Tool calling166 models that call your functions
Alibaba (Qwen)34 models in this rating
Google DeepMind17 models in this rating
Anthropic13 models in this rating

Frequently asked questions

Which OpenAI model is cheapest?

gpt-oss-safeguard-20b at $0.075 input, and GPT-5.6 Luna at $0.20 among the hosted mainline models.

Is GPT-6 Astra worth the price?

For work where errors are subtle and expensive, yes. For routine generation Terra costs a quarter as much.

Does OpenAI offer open weights?

The gpt-oss line is downloadable; the flagship models are not.

Is there an OpenAI free API tier?

No. The consumer ChatGPT has one; the API does not.

What is Fast mode?

A priority lane at double the standard rate, formerly called Priority processing.

Frequently searched

By capabilityReasoningCodingVisionLong context 1M+Free tierOpen weightsLow latencyRealtime voiceImage generation
By vendorAnthropic (13)OpenAI (30)Google DeepMind (17)xAI (8)Meta (6)DeepSeek (9)Mistral AI (11)Alibaba (Qwen) (34)Z.ai (12)Moonshot AI (5)
Popular modelsClaude Fable 5.1GPT-6 AstraClaude Opus 5Claude Fable 5GPT-5.6 SolGLM 5.3Grok 4.6Kimi K3GPT-5.6 Terra
By deliveryBatch APIPrompt cachingPriority tierFrontier tierProprietary APITool callingStructured JSONWeb searchMultilingual

Ratings 1

Avg. score 5

Rate this page

Help us improve