AIモデルインテリジェンス

gpt-image-2

openai/gpt-image-2

提供： OpenAI · ファミリー: gpt-image · リリース 2026-04-21

$5.00
入力 / 100万トークン
$30.00
出力 / 100万トークン
Unknown
コンテキスト長
Unknown
最大出力

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

機能一覧

✗ ツール呼び出し✗ 推論? 構造化出力✓ 添付✗ オープンウェイト✗ 温度制御
モダリティ: 入力 text, image · 出力 image

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding7
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability7/10
Agents7
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit0/15
  • Provider availability7/10
JSON / structured output0
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control0/10
  • Price-friendly for high-volume0/20
Cost efficiency29
  • Headline price (log-scaled)24/95
  • Has prompt-cache pricing5/5
Long context0
  • Context ≥ 100K0/100
Vision67
  • Accepts image input50/50
  • Context window (10K → 1M)0/30
  • Has published price10/10
  • Provider availability7/10
Production-readiness74
  • Number of independent providers35/40
  • Has published per-token price20/20
  • Context window ≥ 8K0/15
  • No data inconsistencies across providers4/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$40.00
$0.04 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$80.00
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$25.00
$0.03 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$70.00
$0.07 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$78.00
$0.08 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

料金詳細

推奨料金 (提供元): openai · gpt-image-2

$5.00
入力
$30.00
出力
$1.25
キャッシュ読み取り

最安プロバイダー: kenari · Unknown 入力 + Unknown 出力

7 か所で利用可能

プロバイダープロバイダーモデルID入力 / 1M出力 / 1Mコンテキストリリース日
OpenAI
openai
gpt-image-2$5.00$30.00Unknown2026-04-21
Azure
azure
gpt-image-2$5.00$30.00Unknown2026-04-21
Vercel AI Gateway
vercel
openai/gpt-image-2$5.00$30.00Unknown2026-04-21
Poe
poe
openai/gpt-image-2$5.05$32.32Unknown2026-04-21
FastRouter
fastrouter
openai/gpt-image-2UnknownUnknown128K2026-04-21
Kenari
kenari
gpt-image-2UnknownUnknown272K2026-04-21
DigitalOcean
digitalocean
openai-gpt-image-2UnknownUnknownUnknown2025-04-24

プロバイダー間でデータに差異

  • context_window varies: 0, 128000, 272000
  • release_date varies (span 362d): 2025-04-24, 2026-04-21
  • modalities varies across offerings

プロバイダーごとに本モデルの値が異なります。上部の「主要数値」は代表的プロバイダーを使用しています。詳細は表をご確認ください。

Frequently asked questions

How much does gpt-image-2 cost?

gpt-image-2 costs $5.00 per 1M input tokens and $30.00 per 1M output tokens, sourced from openai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

Does gpt-image-2 support tool calling?

No. gpt-image-2 does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does gpt-image-2 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for gpt-image-2 in our data source. Verify with OpenAI's official documentation before relying on it in production.

Can gpt-image-2 accept image input?

Yes. gpt-image-2 accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check OpenAI's docs for the exact rule.

Is gpt-image-2 open-weight?

No. gpt-image-2 is a proprietary model — only OpenAI (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to gpt-image-2?

If gpt-image-2 doesn't fit, consider gpt-oss-120b, GPT-5.5, GPT-5.4. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More OpenAI models

Capability lists this model is in

See also

最終更新：

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.