GPT-Image 2.5 Sunburst vs gpt-oss-120b
At a Glance
| Compare |  GPT-Image 2.5 SunburstOpenAI | gpt-oss-120bOpenAI |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $5.00Openai ↗ · Sep 9, 2026 | $0.037Deepinfra ↗ · Sep 21, 2026 |
| Output priceFrom · USD / 1M tokens | $30.00Openai ↗ · Sep 9, 2026 | $0.17Deepinfra ↗ · Sep 21, 2026 |
| Context windowMaximum documented tokens | Not reported | 131K |
| Model facts checked | Sep 9, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | GPT-Image-2.5 Sunburst | gpt-oss-120b |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Family | Gpt Image 2 5 | Gpt Oss 120b |
| Model | GPT-Image-2.5 Sunburst | gpt-oss-120b |
| Version | GPT-Image-2.5 Sunburst | gpt-oss-120b |
| Lifecycle | active | active |
| Released | 2026-09-08 | Unknown |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Image | Text |
| Context window | Unknown | 131K |
| Total parameters | Unknown | 116.8B |
| Active parameters | Unknown | 5.1B |
| License | Unknown | apache-2.0 |
| Open weights | Unknown | Yes |
| API available | Yes | Yes |
| Self-hostable | Unknown | Yes |
| Provider access | Openai (Standard) | Cerebras (Standard), Deepinfra (Standard), Fireworks Ai (Serverless, Standard), Groq (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Serverless, Standard) |
| Capabilities | image-editing, image-generation, inpainting | chat, generation, reasoning, tools |
| Default usage-tier rate limits | Tier 1: 100,000 TPM, 5 IPM, Tier 2: 250,000 TPM, 20 IPM, Tier 3: 800,000 TPM, 50 IPM, Tier 4: 3,000,000 TPM, 150 IPM, Tier 5: 8,000,000 TPM, 250 IPM | Unknown |
| Default snapshot | gpt-image-2.5-sunburst-2026-09-08 | Unknown |
| Model positioning | Most capable GPT Image model for editing precision | Unknown |
| Quality settings | low, medium, high, xhigh, max, auto | Unknown |
| Supported API routes | v1/images/generations, v1/images/edits | Unknown |
| Unsupported API routes | v1/assistants, v1/audio/speech, v1/audio/transcriptions, v1/audio/translations, v1/batch, v1/chat/completions, v1/completions, v1/embeddings, v1/fine-tuning, v1/moderations, v1/realtime, v1/realtime/transcription_sessions, v1/realtime/translations, v1/responses, v1/videos | Unknown |
GPT-Image 2.5 Sunburst Capabilities
gpt-oss-120b Capabilities
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
GPT-6 AstraOpenAI | vs | GPT-Image-2.5 SunburstOpenAI | family variantsimage |
Claude Fable 5.1Anthropic | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
 Gemini 3.1 ProGoogle DeepMind | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peers |
 DeepSeek-V4.1-FlashDeepSeek | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
GPT-Image-2.5 SunburstOpenAI | vs | Grok 4.6xAI | cross-developer peersimage |
GPT-Image-2.5 SunburstOpenAI | vs |  Qwen3.8-MaxQwen | cross-developer peersimage |
 Kimi-K3Moonshot AI | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
 MiniMax-M3MiniMax | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
GPT-Image-2.5 SunburstOpenAI | vs |  GLM-5.3Z.ai | cross-developer peers |
GPT-Image-2.5 SunburstOpenAI | vs |  Hy4 previewTencent | cross-developer peers |
Seed 2.1 ProByteDance Seed | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
 Mistral Large 3Mistral AI | vs | GPT-Image-2.5 SunburstOpenAI | cross-developer peersimage |
Primary Evidence
Sources and Freshness
Questions
GPT-Image 2.5 Sunburst vs gpt-oss-120b FAQs
Is GPT-Image 2.5 Sunburst or gpt-oss-120b better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both GPT-Image 2.5 Sunburst and gpt-oss-120b, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
GPT-Image 2.5 Sunburst is $5.00 and gpt-oss-120b is $0.037 per million tokens, so gpt-oss-120b is cheaper on this metric. GPT-Image 2.5 Sunburst is $30.00 and gpt-oss-120b is $0.17 per million tokens, so gpt-oss-120b is cheaper on this metric.
Which has a larger context window, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
Neither model has a larger sourced context window in this comparison. GPT-Image 2.5 Sunburst is — and gpt-oss-120b is 131K.
Which performs better in benchmarks, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can GPT-Image 2.5 Sunburst or gpt-oss-120b be self-hosted?+
gpt-oss-120b is the only model in this pair currently marked as self-hostable. GPT-Image 2.5 Sunburst is of unknown open-weight status; gpt-oss-120b is open weight.
Can GPT-Image 2.5 Sunburst and gpt-oss-120b understand images?+
GPT-Image 2.5 Sunburst is documented with image input; gpt-oss-120b is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
Neither has a larger sourced maximum output. GPT-Image 2.5 Sunburst is — and gpt-oss-120b is —.
Do GPT-Image 2.5 Sunburst and gpt-oss-120b support reasoning and tool use?+
GPT-Image 2.5 Sunburst: image input. gpt-oss-120b: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
GPT-Image 2.5 Sunburst has 1 sourced provider route; gpt-oss-120b has 7, so gpt-oss-120b has broader tracked availability.
Which offers better value, GPT-Image 2.5 Sunburst or gpt-oss-120b?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.