LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

o3

openai·openai/o3·GA·Closed·o series
Deliberate o-series reasoner for hard math, coding, and multi-step analysis

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$2.00 / $8.00
Blended $3.50 · Cache read $0.50
Lowest paid·PoeGateway
$1.82 / $7.27
Blended $3.18 · 5.2× spread
Context
200,000
Output limit
100,000
Knowledge cutoff
2024-05
Released / updated
2025-04-16 / 2025-04-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

o3 by openai is offered by 25 providers on this page. Public prices are shown for 24 of them. Its official list price is $2.00 per 1M input tokens and $8.00 per 1M output tokens. Prices vary about 5.2× across the providers that host it.

Median output speed is 138 tokens per second, with 8.51s to the first token.

The context window is 200,000 tokens, with an output limit of 100,000 tokens. 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.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed138 tok/s
TTFT8.51 s

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

Available at 25 providers24 with public prices

  • ProviderInput / Output
  • PoeGateway
    $1.82 / $7.27
    Cache read $0.45Context 200,000Output limit 100,000
  • OpenAIOfficialFirst-party
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • LLM GatewayGateway
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • Azure Cognitive ServicesCloud
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • 302.AIGateway
    $2.00 / $8.00
    Context 200,000Output limit 100,000
  • DigitalOceanCloud
    openai-o3
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • LowRouterGateway
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • NanoGPTGateway
    $2.00 / $8.00
    Cache read $1.00Context 200,000Output limit 100,000
  • DevPass (LLM Gateway)Gateway
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
  • NEAR AI CloudGateway
    $2.00 / $8.00
    Cache read $0.50Context 200,000Output limit 100,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$1.82$7.27$0.45—200,000100,000
OpenAIOfficialFirst-party$2.00$8.00$0.50—200,000100,000
LLM GatewayGateway$2.00$8.00$0.50—200,000100,000
Azure Cognitive ServicesCloud$2.00$8.00$0.50—200,000100,000
302.AIGateway$2.00$8.00——200,000100,000
DigitalOcean
openai-o3
Cloud$2.00$8.00$0.50—200,000100,000
LowRouterGateway$2.00$8.00$0.50—200,000100,000
NanoGPTGateway$2.00$8.00$1.00—200,000100,000
DevPass (LLM Gateway)Gateway$2.00$8.00$0.50—200,000100,000
NEAR AI CloudGateway$2.00$8.00$0.50—200,000100,000

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 = loweffort = mediumeffort = highToggle (on / off)

2 / 25 providers expose no reasoning control (reasoning_options: []).

Experimental modes4 items

ModeProviderInputOutputCache readCache write
fastOpenAI$3.50$14.00$0.88—
flexOpenAI$1.00$4.00$0.25—
fastVercel AI Gateway$3.50$14.00$0.88—
flexVercel AI Gateway$1.00$4.00$0.25—

Your usage cost

Common scenarios
1Poe$563.63
2OpenAI · Official$620.00
3LLM Gateway$620.00
4Azure Cognitive Services$620.00
5DigitalOcean$620.00
6LowRouter$620.00
Switch to Poe to save $56.37/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
$8.00$02026-08-052026-10-22
2026-10-22Input list $2.00Output list $8.00Min blended $3.18

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—81.3percent correctSource ↗

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

Artificial Analysis evaluations10 items

GPQA Diamond82.7%
Humanity's Last Exam20.1%
MMMU-Pro70.1%
CritPt1.1%
LiveCodeBench80.8%
Terminal-Bench Hard37.1%
AIME 202588.3%
τ²-Bench Telecom80.7%
AA-LCR74.7%
IFBench71.4%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

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 / $1.20o1same lab$15.00 / $60.00o3-minisame lab$1.10 / $4.40
Data partly from models.dev (MIT) · OpenAI official docs ↗