LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5.3 Codex Spark

openai·openai/gpt-5.3-codex-spark·GA·Closed·gpt-codex-spark series
Coding-optimized GPT model for repository edits, reviews, and agentic software work

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$1.75 / $14.00
Blended $4.81 · Cache read $0.18
Lowest paid·OpenAIFirst-party
$1.75 / $14.00
Blended $4.81 · 1× spread
1 more $0 channels
Context
128,000
Output limit
32,000
Knowledge cutoff
2025-08-31
Released / updated
2026-02-05 / 2026-02-05
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-5.3 Codex Spark by openai is offered by 3 providers on this page. Public prices are shown for 2 of them. Its official list price is $1.75 per 1M input tokens and $14.00 per 1M output tokens. No paid channel is priced below the official list price. 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.

The context window is 128,000 tokens, with an output limit of 32,000 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 2025-08-31.

Available at 3 providers2 with public prices · 1 free

  • ProviderInput / Output
  • PoeGateway
    Free
    Context 128,000Output limit 16,384
  • OpenAIOfficialFirst-party
    $1.75 / $14.00
    Cache read $0.18Context 128,000Output limit 32,000
  • OpenCodeGateway
    $1.75 / $14.00
    Cache read $0.18Context 128,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGatewayFree——128,00016,384
OpenAIOfficialFirst-party$1.75$14.00$0.18—128,00032,000
OpenCodeGateway$1.75$14.00$0.18—128,000128,000

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 = noneeffort = loweffort = mediumeffort = higheffort = xhigh

1 / 3 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1OpenAI · Official$861.00
2OpenCode$861.00

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

The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$14.00$02026-08-052026-08-13
2026-08-13Input list $1.75Output list $14.00Min blended $4.81

Related models

GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40GPT-5.3 Codexsame lab$1.75 / $14.00GPT-5.4same lab$2.50 / $15.00
Data partly from models.dev (MIT) · OpenAI official docs ↗