GPT-5.3-Codex vs Claude Sonnet 4.6, API pricing and model comparison

Compare GPT-5.3-Codex vs Claude Sonnet 4.6 side by side by input/output token price, context window, benchmark signals, capabilities, and example monthly API cost.

Quick comparison summary

This page compares GPT-5.3-Codex vs Claude Sonnet 4.6 in one matrix. Current records: GPT-5.3-Codex on OpenRouter: $1.75/$14 per 1M tokens, 400K context window; Claude Sonnet 4.6 on Claude API: $3/$15 per 1M tokens, 1000K context window. Prices are estimates—verify official provider pages before production use.

GPT-5.3-Codex

openai/gpt-5.3-codex

OpenRouter

Input: $1.75 / 1M
Output: $14.00 / 1M
Context: 400k
Model page: Details

Claude Sonnet 4.6

claude-sonnet-4-6

Claude API

Input: $3.00 / 1M
Output: $15.00 / 1M
Context: 1m
Model page: Details

Comparison matrixLLM Table

Models to compare2/4

Model 1

400K

Select model344 models

Model 2

Select model344 models

OpenAI: GPT-5.3-Codex

OpenRouter

Cheapest (this scenario)

Input

$1.75 / 1M

Output

$14.00 / 1M

Context

400K

Monthly cost

$595.00

Benchmark

1,407LMArena WebDev Arena

VisionToolsJSONReasoningLong context

Anthropic: Claude Sonnet 4.6

Claude API

Input

$3.00 / 1M

Output

$15.00 / 1M

Context

1MLargest context

Monthly cost

$750.00

Benchmark

1,470Top benchmarkLMArena Text Arena

VisionToolsReasoningLong context

OpenAI: GPT-5.3-Codex

OpenRouter

Anthropic: Claude Sonnet 4.6

Claude API

Input

$1.75 / 1MCheapest (this scenario)

$3.00 / 1M

Output

$14.00 / 1MCheapest (this scenario)

$15.00 / 1M

Context

400K

1MLargest context

Benchmark

1,407

LMArena WebDev Arena

1,470Top benchmark

LMArena Text Arena

Monthly cost

$595.00Cheapest (this scenario)

$750.00

Capabilities

VisionToolsJSONReasoningLong context

VisionToolsReasoningLong context

FAQ

Model comparison notes

How do GPT-5.3-Codex vs Claude Sonnet 4.6 API prices compare?

Compare input and output prices per 1M tokens side by side. The same underlying model can list different prices by route (Direct API vs OpenRouter); this table uses the selected route records.

Which model looks cheaper?

Scenario cost depends on your input/output mix. The example monthly cost in the table uses default token volumes—adjust with the cost calculator for your traffic.

Are benchmark scores included?

Independent or provider-reported benchmark signals appear when available. Benchmarks do not replace price analysis—evaluate both for your quality requirements.

Related comparisons

Anthropic Claude Opus 4 7 Direct vs Anthropic Claude Sonnet 4 6 Direct vs Openai Openai GPT 5 3 Codex Openrouter Anthropic Claude Sonnet 4 6 Direct vs Google Gemini 2 5 PRO Direct vs Openai Openai GPT 5 3 Codex Openrouter Anthropic Claude Sonnet 4 6 Direct vs Openai GPT 5 5 Direct vs Openai Openai GPT 5 3 Codex Openrouter Anthropic Claude Sonnet 4 6 Direct vs Openai Openai GPT 5 3 Codex Openrouter vs X AI Grok 4 0709 Direct GPT 5 3 Codex vs Claude Sonnet 4 6 vs Qwen3 Coder Anthropic Anthropic Claude 3 5 Haiku Openrouter vs Anthropic Claude Opus 4 7 Direct vs Anthropic Claude Sonnet 4 6 Direct Anthropic Anthropic Claude 3 5 Haiku Openrouter vs Anthropic Claude Sonnet 4 6 Direct Anthropic Anthropic Claude 3 5 Haiku Openrouter vs Anthropic Claude Sonnet 4 6 Direct vs Google Gemini 2 5 PRO Direct

Popular comparisons

Open high-intent model matchups directly with ready-made links.