LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5

openai·openai/gpt-5·GA·Closed·gpt series
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$1.25 / $10.00
Blended $3.44 · Cache read $0.13
Lowest paid·OpenCodeGateway
$1.07 / $8.50
Blended $2.93 · 2.3× spread
Context
400,000
Output limit
128,000
Knowledge cutoff
2024-09-30
Released / updated
2025-08-07 / 2025-08-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-5 by openai is offered by 41 providers on this page. Public prices are shown for 38 of them. Its official list price is $1.25 per 1M input tokens and $10.00 per 1M output tokens. Prices vary about 2.3× across the providers that host it.

Median output speed is 106 tokens per second, with 77.18s to the first token.

The context window is 400,000 tokens at the reference host, but hosts report different limits, from 128,000 to 400,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-09-30.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier High

Intelligence—
Value—
Output speed106 tok/s
TTFT77.18 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 41 providers38 with public prices

  • ProviderInput / Output
  • OpenCodeGateway
    $1.07 / $8.50
    Cache read $0.11Context 400,000Output limit 128,000
  • PoeGateway
    $1.14 / $9.09
    Cache read $0.11Context 400,000Output limit 128,000
  • OpenAIOfficialFirst-party
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • 302.AIGateway
    $1.25 / $10.00
    Context 400,000Output limit 128,000
  • 302.AIGateway
    gpt-5-thinking
    $1.25 / $10.00
    Context 400,000Output limit 128,000
  • DigitalOceanCloud
    openai-gpt-5
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • LowRouterGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • NanoGPTGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenCodeGateway$1.07$8.50$0.11—400,000128,000
PoeGateway$1.14$9.09$0.11—400,000128,000
OpenAIOfficialFirst-party$1.25$10.00$0.13—400,000128,000
LLM GatewayGateway$1.25$10.00$0.13—400,000128,000
LLM GatewayGateway$1.25$10.00$0.13—400,000128,000
302.AIGateway$1.25$10.00——400,000128,000
302.AI
gpt-5-thinking
Gateway$1.25$10.00——400,000128,000
DigitalOcean
openai-gpt-5
Cloud$1.25$10.00$0.13—400,000128,000
LowRouterGateway$1.25$10.00$0.13—400,000128,000
NanoGPTGateway$1.25$10.00$0.13—400,000128,000

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.

Reasoning control

effort = minimaleffort = loweffort = mediumeffort = higheffort = noneeffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 41 providers.

3 / 41 providers expose no reasoning control (reasoning_options: []).

Experimental modes5 items

ModeProviderInputOutputCache readCache write
fastOpenAI$2.50$20.00$0.25—
flexOpenAI$0.63$5.00$0.063—
fastDatabricks$2.50$20.00$0.25—
fastVercel AI Gateway$2.50$20.00$0.25—
flexVercel AI Gateway$0.63$5.00$0.063—

Your usage cost

Common scenarios
1OpenCode$523.44
2Poe$559.09
3OpenAI · Official$615.00
4LLM Gateway$615.00
5LLM Gateway$615.00
6DigitalOcean$615.00
Switch to OpenCode to save $91.56/mo (15%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$10.00$02026-08-052026-10-17
2026-10-17Input list $1.25Output list $10.00Min blended $2.93

Benchmark2 items

NameConditionsScoreMetricSource
Aider Polyglot—88percent correctSource ↗
SWE-Bench Prodataset: public41.78resolve 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—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Kimi K2.6cheaper alternative$0.95 / $4.00GPT-5.6 Lunacheaper alternative$0.20 / $1.20GPT-4o Transcribesame lab—GPT-5 Chat (latest)same lab—
Data partly from models.dev (MIT) · OpenAI official docs ↗