LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-4o (2024-11-20)

openai·openai/gpt-4o-2024-11-20·GA·Closed·gpt series
GPT model for general reasoning, writing, coding, and tool-assisted tasks

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$2.50 / $10.00
Blended $4.38 · Cache read $1.25
Lowest paid·OpenAIFirst-party
$2.50 / $10.00
Blended $4.38 · 1× spread
Context
128,000
Output limit
16,384
Knowledge cutoff
2023-09
Released / updated
2024-11-20 / 2024-11-20
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF

GPT-4o (2024-11-20) by openai is offered by 10 providers on this page. Its official list price is $2.50 per 1M input tokens and $10.00 per 1M output tokens. No paid channel is priced below the official list price.

The context window is 128,000 tokens, with an output limit of 16,384 tokens. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2023-09.

Available at 10 providers10 with public prices

  • ProviderInput / Output
  • OpenAIOfficialFirst-party
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • NanoGPTGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • Merge GatewayGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • Venice AIGateway
    openai-gpt-4o-2024-11-20
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • OpenRouterGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • Eden AIGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • Kilo GatewayGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • AI/ML APIGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • OrcaRouterGateway
    $2.50 / $10.00
    Cache read $1.25Context 128,000Output limit 16,384
  • AbacusGateway
    $2.50 / $10.00
    Context 128,000Output limit 16,384deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenAIOfficialFirst-party$2.50$10.00$1.25—128,00016,384
NanoGPTGateway$2.50$10.00$1.25—128,00016,384
Merge GatewayGateway$2.50$10.00$1.25—128,00016,384
Venice AI
openai-gpt-4o-2024-11-20
Gateway$2.50$10.00$1.25—128,00016,384
OpenRouterGateway$2.50$10.00$1.25—128,00016,384
Eden AIGateway$2.50$10.00$1.25—128,00016,384
Kilo GatewayGateway$2.50$10.00$1.25—128,00016,384
AI/ML APIGateway$2.50$10.00$1.25—128,00016,384
OrcaRouterGateway$2.50$10.00$1.25—128,00016,384
AbacusGateway$2.50$10.00——128,00016,384deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1OpenAI · Official$850.00
2NanoGPT$850.00
3Merge Gateway$850.00
4Venice AI$850.00
5OpenRouter$850.00
6Eden AI$850.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$10.00$02026-08-052026-08-13
2026-08-13Input list $2.50Output list $10.00Min blended $4.38

Benchmark4 items

NameConditionsScoreMetricSource
Aider Polyglot—18.2percent correctSource ↗
Artificial Analysis Coding Index—16.7indexSource ↗
SciCode—33.3percent correctSource ↗
Terminal-Bench Hard—8.3success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

GPT-6.2 Astra Prosame series—GPT-6.2 Sol Prosame series—GPT 6.1 Terra Prosame series—GPT-4.1 minicheaper alternative$0.40 / $1.60GPT-4o minicheaper alternative$0.15 / $0.60Grok 4.20 (Non-Reasoning)cheaper alternative$1.25 / $2.50Mistral Large 3cheaper alternative$0.50 / $1.50GPT-4o (2024-08-06)same lab$2.50 / $10.00
Data partly from models.dev (MIT) · OpenAI official docs ↗