Home › Frontier and closed › openai
GPT-5.4 Nano openai
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.
- 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 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
via OpenRouter listing · observed 2026-10-26 07:08 UTC. The listing text is the provider's own description, not an assessment.
Where to run 2 providers · 4 endpoints
Hosted endpoints observed for GPT-5.4 Nano, 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: $0.10/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenAI openrouter | openai/gpt-5.4-nano | 391K | unknown | $0.10 | $0.63 | — | — | yes | live | 2026-10-26 |
| Azure openrouter | openai/gpt-5.4-nano | 391K | unknown | $0.20 | $1.25 | — | — | yes | live | 2026-10-26 |
| OpenAI openrouter | openai/gpt-5.4-nano | 391K | unknown | $0.20 | $1.25 | — | — | yes | live | 2026-10-26 |
| Azure openrouter | openai/gpt-5.4-nano | 391K | unknown | $0.22 | $1.38 | — | — | yes | live | 2026-10-26 |
No third-party providers observed beyond the lab's own endpoints. Cache-read price $0.02/M (source, observed 2026-10-26).
Facts
| Context length | 400,000 tokens (391K) · OpenRouter listing |
|---|---|
| Modalities | file + image + text → text |
| Max completion tokens | 128,000 |
| Knowledge cutoff | 2025-08-31 |
| Supported parameters | include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity |
| Openness | Closed weights · closed lab |
| Stage | API only |
| Confidence | medium |
| Pricing (USD per M tokens) |
in $0.20 · out $1.25 · cache read $0.02 OpenRouter list price (cheapest live endpoint) · source · observed 2026-10-26 07:08 UTC |
Open alternatives 5
Nearest open-weights models by modality, context and price on this watch list. Not a quality ranking.
| Model | Org | Params | Context | $/M in | License | Why it is here |
|---|---|---|---|---|---|---|
| Qwen3-VL-8B-Instruct | Qwen | 8.77B | 256K | $0.25 | apache-2.0 | vision input |
| Qwen3.6-27B | Qwen | 27.8B | 256K | $0.20 | apache-2.0 | vision input |
| Kimi-K3 | moonshotai | 2.78T | 1M | $0.16 | other | cheaper input price ($0.161/M vs $0.2/M), vision input |
| Qwen3.5-27B | Qwen | 27.8B | 256K | $0.20 | apache-2.0 | cheaper input price ($0.195/M vs $0.2/M), vision input |
| Qwen3.5-9B | Qwen | 9.65B | 256K | $0.08 | apache-2.0 | cheaper input price ($0.08/M vs $0.2/M), vision input |
Get alerts
Watch the release radar
- /feeds/upcoming.xml(RSS 2.0) · upcoming and just-released models, one item per entry
- /feeds/upcoming.json(JSON Feed 1.1) · same, JSON Feed 1.1
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
Sources
- openrouter openai/gpt-5.4-nano · observed 2026-10-26 07:08 UTC
Radar run: 2026-10-26 07:08 UTC · Last verified 2026-10-26 07:08 UTC