GPT-4
openai/gpt-4By OpenAI · family: gpt · released 2023-03-14 · knowledge: 2023-11
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding46
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability6/10
Agents46
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit5/15
- Provider availability6/10
JSON / structured output30
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume0/20
Cost efficiency14
- Headline price (log-scaled)14/95
- Has prompt-cache pricing0/5
Long context0
- Context ≥ 100K0/100
Production-readiness79
- Number of independent providers30/40
- Has published per-token price20/20
- Context window ≥ 8K8/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $180 $0.18 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $360 $0.04 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $90.00 $0.09 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $300 $0.30 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $396 $0.40 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from openai · gpt-4
Available on 6 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| OpenAI openai | gpt-4 | $30.00 | $60.00 | 8K | 2023-11-06 |
| Azure Cognitive Services azure-cognitive-services | gpt-4 | $60.00 | $120.00 | 8K | 2023-03-14 |
| Azure azure | gpt-4 | $60.00 | $120.00 | 8K | 2023-03-14 |
| Kilo Gateway kilo | openai/gpt-4 | $30.00 | $60.00 | 8K | 2023-03-14 |
| Cloudflare AI Gateway cloudflare-ai-gateway | openai/gpt-4 | $30.00 | $60.00 | 8K | 2023-11-06 |
| LLM Gateway llmgateway | gpt-4 | $30.00 | $60.00 | 8K | 2023-11-06 |
Data inconsistencies across providers
- context_window varies: 8191, 8192
- release_date varies (span 237d): 2023-03-14, 2023-11-06
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does GPT-4 cost?
GPT-4 costs $30.00 per 1M input tokens and $60.00 per 1M output tokens, sourced from openai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of GPT-4?
GPT-4 has a context window of 8K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.
Does GPT-4 support tool calling?
Yes. GPT-4 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does GPT-4 support structured output / JSON mode?
No. GPT-4 does not support structured output / JSON-schema-constrained decoding. If your workflow requires it, look at the /capabilities/structured-output list for alternatives.
Can GPT-4 accept image input?
No. GPT-4 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is GPT-4 open-weight?
No. GPT-4 is a proprietary model — only OpenAI (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to GPT-4?
If GPT-4 doesn't fit, consider GPT OSS 120B, GPT OSS 20B, GPT-5.2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More OpenAI models
- GPT OSS 120B$0.04 in / $0.16 out
- GPT OSS 20B$0.03 in / $0.14 out
- GPT-5.2$1.75 in / $14.00 out
- GPT-5 Mini$0.25 in / $2.00 out
- GPT-5$1.25 in / $10.00 out
Capability lists this model is in
Last updated:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.