Model Catalog › openai
gpt-4
gpt-4
CHAT
Frontier tier
Chat
Proprietary (API-only)
gpt-4 (gpt-4) is a chat model from openai with a 8.2K-token context window; proprietary (API-only); capabilities tools; input text; output text.
8.2KContext
4.1KMax output
$30$ / 1M in
6.7Intelligence
41.704tok / s
Pricing
- Input
- $30 / 1M tokens
- Output
- $60 / 1M tokens
- Currency
- USD
- Note
- Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.
Benchmarks
- Intelligence index
- 6.7
- Coding
- 13.1
Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-09-26.
Performance
- Throughput
- 41.704 tokens/s
- Latency (TTFT)
- 1.152 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.
Specifications
- Context window
- 8,192 tokens (8.2K)
- Max output
- 4,096 tokens
- Weights
- Proprietary (API-only)
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- 2023-11
- Release date
- 2023-11-06
Provenance
committedlitellmmodels-devopenai-api
Last verified: 2026-10-30
Markdown · Vendor JSON · Full catalog · All openai models