LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5-Codex

openai·openai/gpt-5-codex·GA·Closed·gpt-codex series
Coding-optimized GPT model for repository edits, reviews, and agentic software work

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·OpenCodeGateway
$1.07 / $8.50
Blended $2.93 · 1.2× spread
1 more $0 channels
Context
400,000
Output limit
128,000
Knowledge cutoff
2024-09-30
Released / updated
2025-09-15 / 2025-09-15
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-5-Codex by openai is offered by 12 providers on this page. Public prices are shown for 11 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenCode at $1.07 / $8.50 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 1.2× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 162 tokens per second, with 9.79s to the first token.

The context window is 400,000 tokens, with an output limit of 128,000 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 2024-09-30.

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

Intelligence—
Value—
Output speed162 tok/s
TTFT9.79 s

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

Available at 12 providers11 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-gpt-5-codex
    Free
    Context 400,000Output limit 128,000deprecated
  • OpenCodeGateway
    $1.07 / $8.50
    Cache read $0.11Context 400,000Output limit 128,000
  • PoeGateway
    $1.10 / $9.00
    Context 400,000Output limit 128,000deprecated
  • Jiekou.AIGateway
    $1.19 / $9.50
    Cache read $0.12Context 400,000Output limit 128,000
  • ZenMuxGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • Kilo GatewayGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • Vercel AI GatewayCloud
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • HeliconeGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • ImpossiblGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • AbacusGateway
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000deprecated
  • Azure Cognitive ServicesCloud
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
  • AzureCloud
    $1.25 / $10.00
    Cache read $0.13Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-gpt-5-codex
CloudFree——400,000128,000deprecated
OpenCodeGateway$1.07$8.50$0.11—400,000128,000
PoeGateway$1.10$9.00——400,000128,000deprecated
Jiekou.AIGateway$1.19$9.50$0.12—400,000128,000
ZenMuxGateway$1.25$10.00$0.13—400,000128,000
Kilo GatewayGateway$1.25$10.00$0.13$0400,000128,000
Vercel AI GatewayCloud$1.25$10.00$0.13—400,000128,000
HeliconeGateway$1.25$10.00$0.13—400,000128,000
ImpossiblGateway$1.25$10.00$0.13—400,000128,000
AbacusGateway$1.25$10.00$0.13—400,000128,000deprecated
Azure Cognitive ServicesCloud$1.25$10.00$0.13—400,000128,000
AzureCloud$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 = loweffort = mediumeffort = high

1 / 12 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1OpenCode$523.44
2Jiekou.AI$584.24
3ZenMux$615.00
4Helicone$615.00
5Impossibl$615.00
6Abacus$615.00

1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $2.93

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—38.9indexSource ↗
SciCode—40.9percent correctSource ↗
Terminal-Bench Hard—37.9success rateSource ↗

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

Related models

GPT-5.3 Codexsame series$1.75 / $14.00GPT-5.2 Codexsame series—GPT-5.1 Codexsame series—GPT-5 Chat (latest)same lab—GPT-5 Minisame lab$0.25 / $2.00
Data partly from models.dev (MIT)