Skip to main content
Van Data Team

Current model · OpenAI

GPT Image 2.6 Sunburst benchmarks, pricing and specs

GPT Image 2.6 Sunburst is an OpenAI model released on November 4, 2026 that takes text and image input and produces image. It costs $5 per 1M input tokens. It scores 1409 Elo on Arena Text-to-Image, #2 of 10 current models (Arena, measured November 4, 2026).

Per 1M input tokens
$5Listed today
Arena Text-to-Image
1409 Elo#2 of 10 current models

Data verified November 6, 2026 · Dataset 2026-11-06

Share this

Specs

Key facts

Provider
OpenAI
Model family
GPT Image
Release date
November 4, 2026
Status
Current
Access
API only
API model id
gpt-image-2.6-sunburst
Context window
Not reported
Max output
Not reported
Input
text, image
Output
image
Task families
image
Declared capabilities
image generation, image editing, image to image

Charts

Against every current image model

Where GPT Image 2.6 Sunburst lands among the current models of its task, on every independent benchmark, on price and on context.

Where it stands

On Arena Text-to-Image, GPT Image 2.6 Sunburst ranks #2 of 10 current image models. Each bar is the share of current models it beats.

GPT Image 2.6 Sunburst among the current image models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text-to-Image

#2of 10

1,409 Elo · ahead of 89%

Arena Image Edit

#3of 9

1,476 Elo · ahead of 75%

Scores fromArena · 2026-11-06

Price

GPT Image 2.6 Sunburst pricing

It is tied for the most expensive of 6 current image models priced per 1M input tokens.

UnitPrice (USD)TierAppliesSource
1M input tokens$5standardCurrent
1M output tokensNot reportedstandardCurrent
1M input tokens$1.25cachedCurrent
1M input tokens$8standard image inputCurrent
1M output tokens$30standard image outputCurrent

Benchmarks

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. OpenAI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Arena Text-to-Image1409 Elo#2 of 10November 4, 2026Arena · 2026-11-06
Arena Image Edit1476 Elo#3 of 9November 4, 2026Arena · 2026-11-06

Fit

Strengths, cautions and best uses

Strengths
  • OpenAI's higher-quality model in Images 2.6, with more consistent characters, products and brand details across edits at medium or high quality
  • Makes animated GIFs and SVG files, takes a complexity setting for how much the model plans a scene and supports markup-guided edits; OpenAI says Images 2.6 generates 50% faster than before
  • Token rates match GPT Image 2.5: $5 per 1M text input tokens, $8 per 1M image input tokens and $30 per 1M image output tokens
Cautions
  • Arena's first ratings put it below GPT Image 2.5 Sunburst: 1409 against 1427 for generation and 1476 against 1517 for editing, on fewer than 4,000 votes so far
  • OpenAI's pricing page lists no batch rate for 2.6 yet, while GPT Image 2.5 costs half in batch
Best for
  • Detailed compositions, brand-consistent edits and animated GIFs where quality matters most

From benchmark to production

Building on GPT Image 2.6 Sunburst?

Public scores rarely hold on your own data. We test it against the alternatives on your real tasks, then build the agent or pipeline around the model that wins.

AI Model Cost AuditLaunch price $100, regular price $150What the audit includes

Book the cost auditAI agent development

Alternatives

Alternatives to GPT Image 2.6 Sunburst

The closest current image models by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

On score and price

GPT Image 2.6 Sunburst beside the 4 alternatives listed below, on Arena Text-to-Image and on price per 1M input tokens.

GPT Image 2.6 Sunburst and its alternatives on score and price.

Arena Text-to-Image

Measured November 4, 2026, higher is better

GPT Image 2.6 Sunburst
1,409
Gemini 3 Pro Image
1,246
GPT Image 2.5 Flare
1,399
GPT Image 2.5 Sunburst
1,427
Nano Banana 2.1
1,325

Price per 1M input tokens

Listed today, lower is better

GPT Image 2.6 Sunburst
$5
Gemini 3 Pro Image
$2
GPT Image 2.5 Flare
$5
GPT Image 2.5 Sunburst
$5
Nano Banana 2.1
Not listed

Further reading

More on GPT Image 2.6 Sunburst

Compare GPT Image 2.6 Sunburst with

All model comparisons

Other GPT Image models

FAQ

GPT Image 2.6 Sunburst FAQ

How much does GPT Image 2.6 Sunburst cost?

GPT Image 2.6 Sunburst costs $5 per 1M input tokens at the standard tier. It is tied for the most expensive of 6 current image models priced per 1M input tokens. Source: OpenAI, verified November 6, 2026.

How does GPT Image 2.6 Sunburst score on independent benchmarks?

GPT Image 2.6 Sunburst scores 1409 Elo on Arena Text-to-Image, #2 of 10 current models (Arena, measured November 4, 2026) and 1476 Elo on Arena Image Edit, #3 of 9 current models (Arena, measured November 4, 2026). These are independent evaluations, not OpenAI's own launch figures.

Is GPT Image 2.6 Sunburst open source or API only?

GPT Image 2.6 Sunburst is available through OpenAI's API only; its weights are not published.

What are the best alternatives to GPT Image 2.6 Sunburst?

The closest current alternatives by price and measured performance are Gemini 3 Pro Image (60% cheaper per 1M input tokens, $2 vs $5), GPT Image 2.5 Flare (same price per 1M input tokens, $5), GPT Image 2.5 Sunburst (same price per 1M input tokens, $5) and Nano Banana 2.1 (84 points lower on Arena Text-to-Image, 1325 vs 1409).

Sources

Sources

All 255 sources behind the benchmarks, with their versions, licenses and notes, are in the source catalog.

Cite this page

Van Data Team. "GPT Image 2.6 Sunburst Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-11-06. https://vandatateam.com/ai-model-benchmarks/gpt-image-2-6-sunburst

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether GPT Image 2.6 Sunburst fits your workload?

Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls
Compare all modelsBook a consultation