Home › Frontier and closed › openai

GPT-5.4 Mini openai

Closed weights API only frontier listed on OpenRouter 2026-03-17 (224d ago) · source Last verified 2026-10-27 06:57 UTC Docs ↗ OpenRouter ↗

Release timeline

Stages observed by the nightly radar: announced → API only → weights public → served by third parties. Each entry carries the source it was seen at.

  1. 2026-03-17 · API only source
    seeded from the earliest dated observation when first seen · observed 2026-10-07 20:20 UTC

Description

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

via OpenRouter listing · observed 2026-10-27 06:57 UTC. The listing text is the provider's own description, not an assessment.

Where to run 2 providers · 5 endpoints

Hosted endpoints observed for GPT-5.4 Mini, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.38/M.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
OpenAI
openrouter
openai/gpt-5.4-mini 391K unknown $0.38 $2.25 — — yes live 2026-10-27
Azure
openrouter
openai/gpt-5.4-mini 391K unknown $0.75 $4.50 — — yes live 2026-10-27
OpenAI
openrouter
openai/gpt-5.4-mini 391K unknown $0.75 $4.50 — — yes live 2026-10-27
Azure
openrouter
openai/gpt-5.4-mini 391K unknown $0.82 $4.95 — — yes live 2026-10-27
OpenAI
openrouter
openai/gpt-5.4-mini 391K unknown $1.50 $9.00 — — yes live 2026-10-27

No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.07/M (source, observed 2026-10-27).

Facts

Context length400,000 tokens (391K) · OpenRouter listing
Modalitiesfile + image + text → text
Max completion tokens128,000
Knowledge cutoff2025-08-31
Supported parametersinclude_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity
OpennessClosed weights · closed lab
StageAPI only
Confidencemedium
Pricing (USD per M tokens) in $0.75 · out $4.50 · cache read $0.07
OpenRouter list price (cheapest live endpoint) · source · observed 2026-10-27 06:57 UTC

Open alternatives 5

Nearest open-weights models by modality, context and price on this watch list. Not a quality ranking.

ModelOrgParamsContext$/M inLicenseWhy it is here
Qwen3.5-4B Qwen 4.66B 256K — apache-2.0 vision input
Qwen3.5-397B-A17B Qwen 403B 256K $0.39 apache-2.0 cheaper input price ($0.39/M vs $0.75/M), vision input
Kimi-K2.6 moonshotai 1.03T 256K $0.39 other cheaper input price ($0.39/M vs $0.75/M), vision input
Kimi-K2.5 moonshotai 1.03T 256K $0.45 other cheaper input price ($0.45/M vs $0.75/M), vision input
Qwen3-VL-8B-Instruct Qwen 8.77B 256K $0.25 apache-2.0 cheaper input price ($0.25/M vs $0.75/M), vision input

Get alerts

Watch the release radar

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.

Sources

Radar run: 2026-10-27 06:57 UTC · Last verified 2026-10-27 06:57 UTC