Pick GPT-5.3-Codex for dedicated coding agent or cli and ide integration. Pick Mercury 2.5 Preview for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation or coding accuracy (95.7%, 91st percentile among cost-optimized models). On a tight budget at scale, Mercury 2.5 Preview is the value pick.
GPT-5.3-Codex (OpenAI) and Mercury 2.5 Preview (Inception Labs) are two of the models people most often weigh against each other in 2026. GPT-5.3-Codex is openAI's coding-specialized agent model for autonomous software engineering. Mercury 2.5 Preview is inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences
Price: Mercury 2.5 Preview is about 44× cheaper on input ($0.04/$0.15 per 1M tokens vs $1.75/$14 per 1M tokens) — a large enough gap that at scale it can be the single biggest line item in the decision.
Context window: GPT-5.3-Codex holds 1.5× more — 400K (~600 pages) vs 260K tokens (~390 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
Recency: Mercury 2.5 Preview is the newer model by about 7 months (released August 31, 2026), usually meaning fresher training data and capabilities.
Specifications
Spec
GPT-5.3-Codex
Mercury 2.5 Preview
Provider
OpenAI (US)
Inception Labs (US)
Released
February 5, 2026
August 31, 2026
Context window
400K (~600 pages)
260K tokens (~390 pages)
Price (in/out)
$1.75/$14 per 1M tokens
$0.04/$0.15 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text, code
text
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Dedicated coding agent: GPT-5.3-Codex — OpenAI's coding-specialized agent model for autonomous software engineering — and it carries the larger 400K context.
CLI and IDE integration: GPT-5.3-Codex — GPT-5.3-Codex lists cLI and IDE integration among its strengths; Mercury 2.5 Preview does not.
Autonomous software tasks: GPT-5.3-Codex — GPT-5.3-Codex lists autonomous software tasks among its strengths; Mercury 2.5 Preview does not.
Very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation: Mercury 2.5 Preview — Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality — and it runs cheaper at $0.04/$0.15 per 1M tokens.
Coding accuracy (95.7%, 91st percentile among cost-optimized models): Mercury 2.5 Preview — At $0.04/$0.15 per 1M tokens it undercuts GPT-5.3-Codex ($1.75/$14 per 1M tokens), and that gap compounds at volume.
Mathematics accuracy (97.0%, 97th percentile): Mercury 2.5 Preview — Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality — and it is the newer of the two.
Lowest cost at scale: Mercury 2.5 Preview — At $0.04/$0.15 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input: GPT-5.3-Codex — Its 400K window is about 1.5× larger than Mercury 2.5 Preview's 260K tokens, fitting roughly 600 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume: Mercury 2.5 Preview — At $0.04/$0.15 per 1M tokens it undercuts GPT-5.3-Codex, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases: GPT-5.3-Codex — Larger 400K window fits more in one prompt.
Anyone whose priority is dedicated coding agent: GPT-5.3-Codex — It is specifically built for that.
Anyone whose priority is very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation: Mercury 2.5 Preview — That is its strongest area.
GPT-5.3-Codex: where it fits
OpenAI's coding-specialized agent model for autonomous software engineering. Released February 5, 2026 by OpenAI, it is built for dedicated coding agent, cLI and IDE integration, autonomous software tasks, and tool calling.
Its trade-offs are real: coding-specialized, narrower general use, and retired in favor of GPT-5.5 Codex. At $1.75 in / $14 out per million tokens, it sits in the mid price band.
Mercury 2.5 Preview: where it fits
Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality. Released August 31, 2026 by Inception Labs, it is built for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation, coding accuracy (95.7%, 91st percentile among cost-optimized models), mathematics accuracy (97.0%, 97th percentile), and tunable reasoning levels with parallel tool calls and schema-aligned JSON output.
Its trade-offs: 260K context window is far shorter than frontier 1M-token models, no vision or audio modalities, positioned only against cost-optimized models (GPT-5.6 Luna Low, Gemini 3.5 Flash-Lite), not frontier-class, and current $0.04/$0.15 pricing includes a limited-time launch promotion on OpenRouter (list price is $0.20/$0.75, may rise after Sept 8, 2026). At $0.04 in / $0.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
GPT-5.3-Codex and Mercury 2.5 Preview overlap enough that the right pick depends on your specific job. Mercury 2.5 Preview costs less per token; GPT-5.3-Codex holds the larger context; and each leads in its own area — GPT-5.3-Codex for dedicated coding agent, Mercury 2.5 Preview for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation. Rather than crowning one, run the same hard task through both once and let the results decide.
Frequently asked questions
Is GPT-5.3-Codex or Mercury 2.5 Preview better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, GPT-5.3-Codex leans toward dedicated coding agent while Mercury 2.5 Preview leans toward very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, GPT-5.3-Codex or Mercury 2.5 Preview?
Mercury 2.5 Preview is cheaper — $1.75/$14 per 1M tokens vs $0.04/$0.15 per 1M tokens, roughly 44× apart on input.
Which has the bigger context window?
GPT-5.3-Codex — 400K vs 260K tokens, about 1.5× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both GPT-5.3-Codex and Mercury 2.5 Preview together?
Yes — a multi-model platform like LumiChats gives you GPT-5.3-Codex, Mercury 2.5 Preview and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, GPT-5.3-Codex or Mercury 2.5 Preview?
Mercury 2.5 Preview — released August 31, 2026, about 7 months after GPT-5.3-Codex.
GPT-5.3-Codex vs Mercury 2.5 Preview
OpenAI · US | Inception Labs · US · Updated June 2026
Quick verdict
Pick GPT-5.3-Codex for dedicated coding agent or cli and ide integration. Pick Mercury 2.5 Preview for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation or coding accuracy (95.7%, 91st percentile among cost-optimized models). On a tight budget at scale, Mercury 2.5 Preview is the value pick.
GPT-5.3-Codex (OpenAI) and Mercury 2.5 Preview (Inception Labs) are two of the models people most often weigh against each other in 2026. GPT-5.3-Codex is openAI's coding-specialized agent model for autonomous software engineering. Mercury 2.5 Preview is inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
▸Price: Mercury 2.5 Preview is about 44× cheaper on input ($0.04/$0.15 per 1M tokens vs $1.75/$14 per 1M tokens) — a large enough gap that at scale it can be the single biggest line item in the decision.
▸Context window: GPT-5.3-Codex holds 1.5× more — 400K (~600 pages) vs 260K tokens (~390 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
▸Recency: Mercury 2.5 Preview is the newer model by about 7 months (released August 31, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
Spec
GPT-5.3-Codex
Mercury 2.5 Preview
Provider
OpenAI (US)
Inception Labs (US)
Released
February 5, 2026
August 31, 2026
Context window
400K (~600 pages)
260K tokens (~390 pages)
Price (in/out)
$1.75/$14 per 1M tokens
$0.04/$0.15 per 1M tokens
Open weight?
No — API only
No — API only
Modalities
text, code
text
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Dedicated coding agent
GPT-5.3-Codex
OpenAI's coding-specialized agent model for autonomous software engineering — and it carries the larger 400K context.
CLI and IDE integration
GPT-5.3-Codex
GPT-5.3-Codex lists cLI and IDE integration among its strengths; Mercury 2.5 Preview does not.
Autonomous software tasks
GPT-5.3-Codex
GPT-5.3-Codex lists autonomous software tasks among its strengths; Mercury 2.5 Preview does not.
Very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation
Mercury 2.5 Preview
Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality — and it runs cheaper at $0.04/$0.15 per 1M tokens.
Coding accuracy (95.7%, 91st percentile among cost-optimized models)
Mercury 2.5 Preview
At $0.04/$0.15 per 1M tokens it undercuts GPT-5.3-Codex ($1.75/$14 per 1M tokens), and that gap compounds at volume.
Mathematics accuracy (97.0%, 97th percentile)
Mercury 2.5 Preview
Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality — and it is the newer of the two.
Lowest cost at scale
Mercury 2.5 Preview
At $0.04/$0.15 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input
GPT-5.3-Codex
Its 400K window is about 1.5× larger than Mercury 2.5 Preview's 260K tokens, fitting roughly 600 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Mercury 2.5 Preview
At $0.04/$0.15 per 1M tokens it undercuts GPT-5.3-Codex, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ GPT-5.3-Codex
Larger 400K window fits more in one prompt.
Anyone whose priority is dedicated coding agent
→ GPT-5.3-Codex
It is specifically built for that.
Anyone whose priority is very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation
→ Mercury 2.5 Preview
That is its strongest area.
GPT-5.3-Codex: where it fits
OpenAI's coding-specialized agent model for autonomous software engineering. Released February 5, 2026 by OpenAI, it is built for dedicated coding agent, cLI and IDE integration, autonomous software tasks, and tool calling.
Its trade-offs are real: coding-specialized, narrower general use, and retired in favor of GPT-5.5 Codex. At $1.75 in / $14 out per million tokens, it sits in the mid price band.
Mercury 2.5 Preview: where it fits
Inception Labs' August 31, 2026 diffusion-based language model preview, refining tokens in parallel for roughly 10x the throughput of comparable autoregressive models at cost-optimized-tier quality. Released August 31, 2026 by Inception Labs, it is built for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation, coding accuracy (95.7%, 91st percentile among cost-optimized models), mathematics accuracy (97.0%, 97th percentile), and tunable reasoning levels with parallel tool calls and schema-aligned JSON output.
Its trade-offs: 260K context window is far shorter than frontier 1M-token models, no vision or audio modalities, positioned only against cost-optimized models (GPT-5.6 Luna Low, Gemini 3.5 Flash-Lite), not frontier-class, and current $0.04/$0.15 pricing includes a limited-time launch promotion on OpenRouter (list price is $0.20/$0.75, may rise after Sept 8, 2026). At $0.04 in / $0.15 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
GPT-5.3-Codex and Mercury 2.5 Preview overlap enough that the right pick depends on your specific job. Mercury 2.5 Preview costs less per token; GPT-5.3-Codex holds the larger context; and each leads in its own area — GPT-5.3-Codex for dedicated coding agent, Mercury 2.5 Preview for very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both GPT-5.3-Codex and Mercury 2.5 Preview without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
Is GPT-5.3-Codex or Mercury 2.5 Preview better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, GPT-5.3-Codex leans toward dedicated coding agent while Mercury 2.5 Preview leans toward very high inference throughput (1,107 tok/s) via diffusion-based parallel token generation, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, GPT-5.3-Codex or Mercury 2.5 Preview?
Mercury 2.5 Preview is cheaper — $1.75/$14 per 1M tokens vs $0.04/$0.15 per 1M tokens, roughly 44× apart on input.
Which has the bigger context window?
GPT-5.3-Codex — 400K vs 260K tokens, about 1.5× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both GPT-5.3-Codex and Mercury 2.5 Preview together?
Yes — a multi-model platform like LumiChats gives you GPT-5.3-Codex, Mercury 2.5 Preview and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, GPT-5.3-Codex or Mercury 2.5 Preview?
Mercury 2.5 Preview — released August 31, 2026, about 7 months after GPT-5.3-Codex.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.