LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5 Nano

openai·openai/gpt-5-nano·GA·Closed·gpt-nano series
Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.05 / $0.40
Blended $0.14 · Cache read $0.005
Lowest paid·PoeGateway
$0.046 / $0.36
Blended $0.13 · 1.4× spread
Context
400,000
Output limit
128,000
Knowledge cutoff
2024-05-30
Released / updated
2025-08-07 / 2025-08-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-5 Nano by openai is offered by 33 providers on this page. Its official list price is $0.05 per 1M input tokens and $0.40 per 1M output tokens. Prices vary about 1.4× across the providers that host it.

Median output speed is 155 tokens per second, with 1.72s 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 2024-05-30.

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

Intelligence—
Value—
Output speed155 tok/s
TTFT1.72 s

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

Available at 33 providers33 with public prices

  • ProviderInput / Output
  • PoeGateway
    $0.046 / $0.36
    Cache read $0.0045Context 400,000Output limit 128,000
  • Jiekou.AIGateway
    $0.048 / $0.38
    Cache read $0.0047Context 400,000Output limit 128,000
  • OpenAIOfficialFirst-party
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • DigitalOceanCloud
    openai-gpt-5-nano
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • LowRouterGateway
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • NanoGPTGateway
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • DatabricksCloud
    databricks-gpt-5-nano
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
  • DevPass (LLM Gateway)Gateway
    $0.05 / $0.40
    Cache read $0.005Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$0.046$0.36$0.0045—400,000128,000
Jiekou.AIGateway$0.048$0.38$0.0047—400,000128,000
OpenAIOfficialFirst-party$0.05$0.40$0.005—400,000128,000
LLM GatewayGateway$0.05$0.40$0.005—400,000128,000
LLM GatewayGateway$0.05$0.40$0.005—400,000128,000
DigitalOcean
openai-gpt-5-nano
Cloud$0.05$0.40$0.005—400,000128,000
LowRouterGateway$0.05$0.40$0.005—400,000128,000
NanoGPTGateway$0.05$0.40$0.005—400,000128,000
Databricks
databricks-gpt-5-nano
Cloud$0.05$0.40$0.005—400,000128,000
DevPass (LLM Gateway)Gateway$0.05$0.40$0.005—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 33 providers.

1 / 33 providers expose no reasoning control (reasoning_options: []).

Experimental modes2 items

ModeProviderInputOutputCache readCache write
flexOpenAI$0.025$0.20$0.0025—
flexVercel AI Gateway$0.025$0.20$0.0025—

Your usage cost

Common scenarios
1Poe$22.36
2Jiekou.AI$23.36
3OpenAI · Official$24.60
4LLM Gateway$24.60
5LLM Gateway$24.60
6DigitalOcean$24.60
Switch to Poe to save $2.24/mo (9%). 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
$0.40$02026-08-052026-10-22
2026-10-22Input list $0.05Output list $0.40Min blended $0.13

Related models

GPT-5.4 nanosame series$0.20 / $1.25Gemma 4 31B ITcheaper alternative$0 / $0Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0GLM-4.7-Flashcheaper alternative$0 / $0Hy3cheaper alternative$0 / $0GPT-5 Minisame lab$0.25 / $2.00GPT-5 Prosame lab$15.00 / $120
Data partly from models.dev (MIT) · OpenAI official docs ↗