Models & Pricing

GPT-5.5 vs GPT-5.4

Choose two or three models. Copy the URL to share your selection.

ComparisonGPT-5.5
gpt-5.5
GPT-5.4
gpt-5.4
TypeChatChat
Best forChat, writing, coding and reasoning tasksChat, writing, coding and reasoning tasks
TokenRex price$5.00 in / $30.00 out per 1M tokens$2.50 in / $15.00 out per 1M tokens
Cached input / 1M tokens$0.50 per 1M tokens$0.25 per 1M tokens
Cache write / 1M tokensNo extra feeNo extra fee
Cached outputNot offered · standard output rate appliesNot offered · standard output rate applies
Market price$5.00 in / $30.00 out per 1M tokens$2.50 in / $15.00 out per 1M tokens
Context window (provider)1,050,000 tokens1,050,000 tokens
Input token limit (provider)Within the context windowWithin the context window
Maximum output128,000 tokens128,000 tokens
Knowledge cutoffDec 01, 2025Aug 31, 2025
Vendor input modalitiesNot verifiedNot verified
Vendor output modalitiesNot verifiedNot verified
TokenRex endpointsPOST /v1/chat/completionsPOST /v1/chat/completions
TokenRex inputText, Image/PDF content through the chat bridgeText, Image/PDF content through the chat bridge
TokenRex outputTextText
Benchmarks
Benchmark evidence2 source-linked results5 source-linked results
FrontierCode v1.1 (Extended)
51.37%

Cognition FrontierCode 1.1; GPT-5.5; medium effort; codex harness; Extended subset (150 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.5137. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Cognition · FrontierCode 1.1 original leaderboard
—
FrontierCode v1.1 (Main)
36.6%

Cognition FrontierCode 1.1; GPT-5.5; medium effort; codex harness; Main subset (100 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.366. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Cognition · FrontierCode 1.1 original leaderboard
—
SWE-Bench Pro (Public)—
57.7%

Published reasoning effort: xhigh. SWE-Bench Pro (Public) | 57.7% | 54.4% | 52.4% | 45.7% | Published model-family result, not a test of TokenRex or its default effort.

OpenAI - Introducing GPT-5.4 mini and nano
Terminal-Bench 2.0—
75.1%

Published reasoning effort: xhigh. Terminal-Bench 2.0 | 75.1% | 60.0% | 46.3% | 38.2% | Published model-family result, not a test of TokenRex or its default effort.

OpenAI - Introducing GPT-5.4 mini and nano
Toolathlon—
54.6%

Published reasoning effort: xhigh. Toolathlon | 54.6% | 42.9% | 35.5% | 26.9% | Published model-family result, not a test of TokenRex or its default effort.

OpenAI - Introducing GPT-5.4 mini and nano
GPQA Diamond—
93%

Published reasoning effort: xhigh. GPQA Diamond | 93.0% | 88.0% | 82.8% | 81.6% | Published model-family result, not a test of TokenRex or its default effort.

OpenAI - Introducing GPT-5.4 mini and nano
OSWorld-Verified—
75%

Published reasoning effort: xhigh. OSWorld-Verified | 75.0% | 72.1% | 39.0% | 42.0% | Published model-family result, not a test of TokenRex or its default effort.

OpenAI - Introducing GPT-5.4 mini and nano

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

GPT-5.5

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.

GPT-5.4

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.

Popular comparisons

Open the cost calculator →