Quick:
openai
Active
GPT-4o mini
Model Spec
openai:gpt-4o-mini
Modalities
Input
text
image
pdf
Output
text
Capabilities
Chat
Tools
Vision
Streaming
JSON
Pricing Components
| Component | Price | Conditions | Source |
|---|---|---|---|
| tool.web_search | $10.00 / 1,000 calls | Standard | — |
| tool.web_search_preview | $10.00 / 1,000 calls | Standard | — |
| tool.web_search_preview.non_reasoning | $25.00 / 1,000 calls | Standard | — |
| tool.file_search | $2.50 / 1,000 calls | Standard | — |
| storage.file_search | $0.10 / 1 gb_days | Standard | file_search_storage_gb_day |
| tool.code_interpreter | $0.03 / 1 sessions | Standard | — |
| tool.code_interpreter.4gb | $0.12 / 1 sessions | Standard | — |
| tool.code_interpreter.16gb | $0.48 / 1 sessions | Standard | — |
| tool.code_interpreter.64gb | $1.92 / 1 sessions | Standard | — |
| token.input | $0.15 / 1M tokens | Standard | — |
| token.output | $0.60 / 1M tokens | Standard | — |
| token.cache_read | $0.08 / 1M tokens | Standard | — |
Specifications
Context Window
128,000 tokens
Max Output
16,384 tokens
Input Cost
$0.15/M
Output Cost
$0.60/M
History
Raw JSONTimeline is based on collected llm_db history snapshots and may be incomplete.
2026-07-02
changed
-
extra.description
(add)
— → Small omni GPT for cheap multimodal assistance and production-scale traffic
2026-05-27
changed
-
cost.cache_read
(replace)
0.08 → 0.075
2026-04-20
changed
-
capabilities.rerank
(add)
— → false
2026-04-15
changed
-
capabilities.json.native
(remove)
false → —
-
capabilities.json.strict
(remove)
false → —
-
capabilities.streaming.text
(remove)
true → —
2026-04-05
changed
-
modalities.input
(replace)
[2 items] → [3 items]
2026-03-27
changed
-
execution
(add)
— → {2 fields}
2026-03-14
introduced
snapshots 64bf744 -> 98a92b8 • generated 2026-07-29T03:34:55
6020
of 6154 models
1 / 121
Page 1 of 121