Claude 3.5 Sonnet vs GPT-5.1 Codex High

    Comparison

    As of August 20, 2026, GPT-5.1 Codex High is 38% cheaper per million tokens than Claude 3.5 Sonnet. Claude 3.5 Sonnet is $3.00 / $15.00 per million input/output tokens versus GPT-5.1 Codex High at $1.25 / $10.00. Sources: https://platform.claude.com/docs/en/about-claude/pricing and https://developers.openai.com/api/docs/pricing

    Sources: Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); OpenAI API pricing (https://developers.openai.com/api/docs/pricing)

    Claude 3.5 Sonnet

    Anthropic

    $18.00blended / 1M

    Input

    $3.00

    Output

    $15.00

    200K ctx|Proprietary
    38%
    cheaper
    Better value

    GPT-5.1 Codex High

    OpenAI

    $11.25blended / 1M

    Input

    $1.25

    Output

    $10.00

    400K ctx|Proprietary
    Save $6.75 per million tokens by choosing GPT-5.1 Codex High over Claude 3.5 Sonnet.

    Claude 3.5 Sonnet vs GPT-5.1 Codex High comparison

    Token pricing, specs, and benchmarks side by side

    Metric
    Claude 3.5 Sonnet
    GPT-5.1 Codex High
    Provider
    Provider
    Anthropic
    OpenAI
    License
    Proprietary
    Proprietary
    Release Date
    2024-06-21
    2025-11-12
    Pricing (per 1M tokens)
    Input Price+140%
    $3.00
    $1.25
    Output Price+50%
    $15.00
    $10.00
    Blended (1M + 1M)
    $18.00
    $11.25
    Model Details
    Context Window
    200K
    400K
    Max Output Tokens
    200K
    128K
    Knowledge Cutoff
    April 2024
    N/A
    Throughput
    78 tok/s
    50 tok/s
    Benchmarks
    59.4%
    54.0%
    6.5%
    96.7%
    90.4%
    68.3%
    92%
    71.1%
    17.5%
    87.1%
    96.4%
    91.6%
    76.1%
    27.5%
    60%
    Benchmark Wins
    Claude 3.5 Sonnet 0|1 GPT-5.1 Codex High

    Verdict

    Claude 3.5 Sonnet vs GPT-5.1 Codex High: the bottom line

    GPT-5.1 Codex High offers both lower pricing and stronger benchmark performance across the board, making it the clear value leader in this comparison.

    Claude 3.5 Sonnet vs GPT-5.1 Codex High FAQ

    Which is cheaper, Claude 3.5 Sonnet or GPT-5.1 Codex High?

    As of August 20, 2026, GPT-5.1 Codex High is 38% cheaper on blended LLM API pricing. GPT-5.1 Codex High costs $1.25 per million input tokens and $10.00 per million output tokens ($11.25 blended 1M-in + 1M-out). Claude 3.5 Sonnet costs $3.00 / $15.00 per million tokens ($18.00 blended). Sources: https://platform.claude.com/docs/en/about-claude/pricing and https://developers.openai.com/api/docs/pricing. The cheapest LLM for your app still depends on how many output tokens you generate.

    How much does Claude 3.5 Sonnet vs GPT-5.1 Codex High cost per million tokens?

    Claude 3.5 Sonnet Claude API pricing from Anthropic is $3.00 input and $15.00 output per million tokens via Anthropic. GPT-5.1 Codex High OpenAI API pricing is $1.25 input and $10.00 output per million tokens via OpenAI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.

    Which is better for coding, Claude 3.5 Sonnet or GPT-5.1 Codex High?

    Claude 3.5 Sonnet has a published SWE-bench Verified score of 49%. GPT-5.1 Codex High does not have that eval on this page yet.

    What is the context window for Claude 3.5 Sonnet vs GPT-5.1 Codex High?

    Claude 3.5 Sonnet supports a 200K token context window, while GPT-5.1 Codex High supports 400K tokens. GPT-5.1 Codex High offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.

    Which model performs better on benchmarks, Claude 3.5 Sonnet or GPT-5.1 Codex High?

    GPT-5.1 Codex High leads on 1 of 1 shared benchmarks versus Claude 3.5 Sonnet's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.

    Is Claude 3.5 Sonnet or GPT-5.1 Codex High better for production use?

    Both Claude 3.5 Sonnet and GPT-5.1 Codex High are production API models. For cost-sensitive production traffic, GPT-5.1 Codex High has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.

    Can I switch between Claude 3.5 Sonnet and GPT-5.1 Codex High in my app?

    Yes. Call Claude 3.5 Sonnet through Anthropic and GPT-5.1 Codex High through OpenAI with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.

    How accurate is this Claude 3.5 Sonnet vs GPT-5.1 Codex High pricing data?

    List rates are the latest published Claude API pricing from Anthropic and OpenAI API pricing, quoted per million tokens. Official rate sheets: https://platform.claude.com/docs/en/about-claude/pricing and https://developers.openai.com/api/docs/pricing. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.

    What is the output token limit for Claude 3.5 Sonnet and GPT-5.1 Codex High?

    Claude 3.5 Sonnet supports up to 200K output tokens per request, while GPT-5.1 Codex High supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.

    Which model has better throughput, Claude 3.5 Sonnet or GPT-5.1 Codex High?

    Claude 3.5 Sonnet runs at approximately 78 tokens/second while GPT-5.1 Codex High runs at 50 tokens/second. Claude 3.5 Sonnet is faster in raw throughput. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.

    How do I switch the models in this Claude 3.5 Sonnet vs GPT-5.1 Codex High comparison?

    Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Claude 3.5 Sonnet or GPT-5.1 Codex High from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.

    Claude 3.5 Sonnet vs GPT-5.1 Codex High pricing

    This comparison covers API pricing, context window, throughput, and benchmark scores. Claude 3.5 Sonnet costs $3.00/M input and $15.00/M output. GPT-5.1 Codex High costs $1.25/M input and $10.00/M output.

    Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.

    The index

    All Large Language Models

    280 models across 33 providers. Search or jump to a lab — every model page stays linked here.

    Baidu

    1 models

    Inception

    1 models

    inclusionAI

    1 models

    LG AI Research

    1 models

    Nous Research

    1 models

    Sakana AI

    1 models

    StepFun

    1 models

    Tencent

    1 models

    Thinking Machines

    1 models

    Unisound

    1 models

    Upstage

    1 models

    Next step

    You found the model. Now ship the product.

    Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.