GPT-5 API prices
Compare routes under the same recorded conditions.
Official pricing source ↗Compare request billing schedules
2 current routes have qualified request schedules. Prompt length, cache lifetime and search affect costs; base prices are not fixed rates.
Fixed-rate channel comparison
No current fixed-rate quote for this selection.
Expired, missing or out-of-scope prices are not zero, and another version is not silently substituted.
Find other candidates by use →Change billing and configuration scope
All quotes, filters and usage tools
History · Billing and conditions
GPT-5 API pricing: official and providers: 2 routes have qualified request billing schedules; compare by exact API. No current fixed-rate quote. Conditional base rates are not unconditional prices; costs depend on request usage and unpriced components.
Latest recorded source check: —
Recorded changes
No changes recorded yet. The first successful check establishes a baseline; it does not count as a price drop or a newly launched endpoint.
Showing up to 100 recent events. Prices for unavailable endpoints are retained for reference. Failed source checks do not establish that a price stayed unchanged.
Find lower-cost alternatives
Find lower-cost alternatives
Choose your existing model to find lower reference costs with matching declared technical constraints. Output quality remains unverified.
Loading verified quotes…
Users’ choices · GPT-5
Describe your work to find related tasks.
Public scores by use
The same model scores differently by use. Once you pick a use, the site applies that use’s quality gate before comparing cost.
Text
- Answer from sources1421
- Chinese1454
- Classify1410
- Extract fields1410
- General text1435
- Multi-turn1421
- Summarize1413
- Translate & rewrite1425
- Write1372
Code & tools
- Code1472
- Web & frontend1418
Industry
- Business & finance1415
- Legal & government1461
- Medical & health1460
Vision & research
- Image understanding1208
- Search grounding1133
Scores come from Arena public-preference leaderboards (CC BY 4.0), latest published 2026-11-20. They describe the model, not your task’s success rate or a quantized channel. Arena ↗
View independent evaluation on Artificial Analysis ↗ · external link; we do not copy its scores or prices.
Declared model facts
Declared fields from the OpenRouter model catalog, bound to exact API IDs; not our tests, price approval or account availability.
- Input
- Text · Image · File
- Output
- Text
- Context
- 400K
- Reasoning parameter
- Supported
- Knowledge cutoff
- 2024-09-30
- Open-weights clue
- Not declared
Per-API facts · 2 versions
- openai/gpt-5 · text / image / file → text · 400K · reasoning
- openai/gpt-5:batch · text / image / file → text · 400K · reasoning
Source: https://openrouter.ai/api/v1/models, captured 2026-11-21T09:20:20.905Z, raw SHA-256: 19214ba490361282… . Unstated facts stay unknown and are not inferred from names or sibling models.
Classification sources
Source declarations for registered versions; not task quality, current account availability or price approval. Unknown versions do not inherit sibling classifications.
openai/gpt-5-2025-08-07
Classification not established
Model variants
Snapshots and routing variants remain distinct. Choose an exact ID in the comparison before deciding; model quality and access conditions need your own review.
openai/gpt-5
Compare costs →openai/gpt-5-2025-08-07
Compare costs →openai/gpt-5:batch
Compare costs →