Model comparison
GPT-5.3-Codex vs Microsoft MAI-Thinking-1
OpenAI against Microsoft, compared on context, price, and verified benchmark results.
Catalog record checked September 5, 2026Individual provider fields may changeEvidence confidence: High — see receipts below
OpenAI
GPT-5.3-Codex
Frontier
Microsoft
Microsoft MAI-Thinking-1
Frontier
| Specification | GPT-5.3-Codex | Microsoft MAI-Thinking-1 |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Tier | Frontier | Frontier |
| Context window | Winner: 400K | 256K |
| Max output | Winner: 128K | 64K |
| Input / 1M tokens | Winner: $1.75 | $2 |
| Output / 1M tokens | $14 | Winner: $8 |
| Weights | Closed | Closed |
| Parameters | Not disclosedUnverified | ~1T total / 35B active (sparse MoE) |
| Reasoning levels | none, low, medium, high, xhigh, max | low, medium, high |
| Modalities | text, image | text |
| API model id | gpt-5.3-codex | mai-thinking-1 |
| Released | February 5, 2026 | June 2, 2026 |
| Artificial Analysis Intelligence Index [high] (2026-08-14) | 52 | Not verifiedUnverified |
| Artificial Analysis Intelligence Index (2026-08-14) | Not verifiedUnverified | 55 |
| AIME 2025 (2026-08-12) | Not verifiedUnverified | 97 |
| SWE-bench Verified (2026-06) | Not verifiedUnverified | 73.5 |
| GPQA Diamond (2026-06) | Not verifiedUnverified | 84.2 |
| Terminal-Bench 2.0 (2026-06) | Not verifiedUnverified | 46 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
- 2026-08-14: Artificial AnalysisComposite index blending reasoning, knowledge, and coding evals into one 0–100 score. Comparability: directly comparable — AA occasionally rebaselines the index scale between snapshots — a score captured on one date is only comparable to same-snapshot scores (check measuredAt).
- 2026-08-12: Microsoft AI — Introducing MAI-Thinking-1 (vendor, 256k output)Competition mathematics: AIME 2025 exam problems, typically pass@1 with tools disallowed or single-attempt code execution per the harness. Comparability: comparable with caveat — 30-question total denominator: one problem = ~3.3 points. Tool-use policy (calculator/code interpreter) must match between compared models.
- 2026-06: Microsoft AI model page (vendor, as labeled: Terminal-Bench 2.0 — NOT comparable to 2.1 observations)Real GitHub issue resolution: does the model's patch pass the hidden tests. Comparability: comparable with caveat — Post-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
Pricing tiers: GPT-5.3-Codex: Standard $1.75/$14 per MTok; cached input $0.175/MTok; Fast mode $3.50/$28. Purpose-built for the Codex agent. · Microsoft MAI-Thinking-1: Global Standard $2.00/$8.00 per MTok, cached input $0.20 (Azure Retail Prices API, effective 2026-08-01, uniform across ~22 public regions; US Gov regions carry premiums). Still preview; Global Standard only, no PTU yet. 256K context with a 64K output cap that includes reasoning tokens. ~1T/35B sparse MoE; reasoning is always on (no effort levels). Microsoft's first true reasoning model, trained without OpenAI distillation.
GPT-5.3-Codex
GPT-5.3-Codex is OpenAI's coding-specialised model powering the Codex agent at $1.75/$14.
Best for
- Autonomous coding
- Repo-scale refactors
- Test generation
Watch out
Tuned for coding, not general chat; use GPT-5.6 for broad reasoning.
Microsoft MAI-Thinking-1
MAI-Thinking-1 is Microsoft's first in-house reasoning model, reducing dependence on OpenAI.
Best for
- Enterprise (Azure)
- Reasoning
- Microsoft ecosystem
Watch out
Foundry-gated preview; no MAI-2 exists yet. Of the Build 2026 MAI wave, only MAI-Thinking-1 and MAI-Cyber-1-Flash ($0.60/$3.50, released 2026-07-27) have published token meters.
When the cheaper one wins
Microsoft MAI-Thinking-1 is cheaper on output at $8 per million tokens against $14 for GPT-5.3-Codex — about 1.8×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerEvidence confidence: High
How strong and complete the evidence behind this comparison is — not a prediction of which model is better.
- Pricing verified on both sides — Input and output rates are verified for both models.
- 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
- 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
- Verified within the last 90 days — Newest catalog check was 6 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- GPT-5.3-Codex: OpenAI — Introducing GPT-5.3-Codex (accessed 2026-08-29)
- GPT-5.3-Codex: OpenAI API pricing (gpt-5.3-codex $1.75/$14) (accessed 2026-08-29)
- Microsoft MAI-Thinking-1: Azure Retail Prices API (MAI-Thinking-1 $2/$0.20 cached/$8) (accessed 2026-09-04)
- Microsoft MAI-Thinking-1: AzureSpeed — AI model pricing tracker (same figures) (accessed 2026-09-04)
- Microsoft MAI-Thinking-1: Microsoft — Introducing MAI-Thinking-1 (~1T total / 35B active MoE) (accessed 2026-09-05)
- Microsoft MAI-Thinking-1: Microsoft Foundry — MAI-Thinking-1 usage (256K context, 64K output cap) (accessed 2026-09-05)
Related comparisons
- Claude Fable 5.1 vs GPT-5.3-Codex
- Claude Fable 5.1 vs Microsoft MAI-Thinking-1
- Claude Fable 5 vs GPT-5.3-Codex
- Claude Fable 5 vs Microsoft MAI-Thinking-1
- Claude Mythos 5.1 vs GPT-5.3-Codex
- Claude Mythos 5.1 vs Microsoft MAI-Thinking-1
Diving deeper on one model? GPT-5.3-Codex · Microsoft MAI-Thinking-1
Common questions
GPT-5.3-Codex vs Microsoft MAI-Thinking-1
Answered from the verified figures on this page rather than general guidance.
Is GPT-5.3-Codex or Microsoft MAI-Thinking-1 cheaper for input?
GPT-5.3-Codex is cheaper at $1.75 per million input tokens, against $2 for Microsoft MAI-Thinking-1 — roughly 1.1× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.3-Codex has tiered pricing: Standard $1.75/$14 per MTok; cached input $0.175/MTok; Fast mode $3.50/$28. Purpose-built for the Codex agent. Microsoft MAI-Thinking-1 has tiered pricing: Global Standard $2.00/$8.00 per MTok, cached input $0.20 (Azure Retail Prices API, effective 2026-08-01, uniform across ~22 public regions; US Gov regions carry premiums). Still preview; Global Standard only, no PTU yet. 256K context with a 64K output cap that includes reasoning tokens. ~1T/35B sparse MoE; reasoning is always on (no effort levels). Microsoft's first true reasoning model, trained without OpenAI distillation.
Is GPT-5.3-Codex or Microsoft MAI-Thinking-1 cheaper for output?
Microsoft MAI-Thinking-1 is cheaper at $8 per million output tokens, against $14 for GPT-5.3-Codex — roughly 1.8× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.3-Codex has tiered pricing: Standard $1.75/$14 per MTok; cached input $0.175/MTok; Fast mode $3.50/$28. Purpose-built for the Codex agent. Microsoft MAI-Thinking-1 has tiered pricing: Global Standard $2.00/$8.00 per MTok, cached input $0.20 (Azure Retail Prices API, effective 2026-08-01, uniform across ~22 public regions; US Gov regions carry premiums). Still preview; Global Standard only, no PTU yet. 256K context with a 64K output cap that includes reasoning tokens. ~1T/35B sparse MoE; reasoning is always on (no effort levels). Microsoft's first true reasoning model, trained without OpenAI distillation.
Which has the larger context window, GPT-5.3-Codex or Microsoft MAI-Thinking-1?
GPT-5.3-Codex accepts 400K tokens against 256K for Microsoft MAI-Thinking-1. This only matters if you routinely send very long documents or large codebases.
Do GPT-5.3-Codex and Microsoft MAI-Thinking-1 support the same reasoning levels?
GPT-5.3-Codex exposes none, low, medium, high, xhigh, max, while Microsoft MAI-Thinking-1 exposes low, medium, high.
Should I use GPT-5.3-Codex or Microsoft MAI-Thinking-1?
Both sit in the frontier tier, so the choice usually comes down to price and context rather than capability. GPT-5.3-Codex suits autonomous coding; Microsoft MAI-Thinking-1 suits enterprise (azure).
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: GPT-5.3-Codex costs $1.75 per 1M tokens versus $2 for Microsoft MAI-Thinking-1 — a 1.1x difference at the headline tier.
- Context: GPT-5.3-Codex takes 400K against 256K for Microsoft MAI-Thinking-1 — only decisive if your prompts approach the smaller window.
- Measured capability: Microsoft MAI-Thinking-1 leads Artificial Analysis Intelligence Index 55 to 52 (measured 2026-08-14).
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.