A capable but aging flagship that has been outpaced by cheaper, faster successors in OpenAI's own lineup.
82
Coding
80
Writing
83
Research
10
Images
22
Value
80
Long Context
Use this when
Complex multi-step tasks requiring deep reasoning, long document analysis, or sophisticated code generation where cost is secondary to quality.
Skip this if
You're cost-sensitive or need real-time speed — GPT-4o Mini, Claude Haiku, or Gemini Flash deliver far better value per dollar for most standard tasks.
Pricing
$10.00/1M in
$30.00/1M out
→0%since May 2026
Context
128k tokens
Speed
Balanced
GPT-4 Turbospecs & pricing
Verified Sep 4, 2026 against the AI Gateway catalog
GPT-4 Turbo is available via the OpenAI API. It has largely been succeeded by GPT-4o, which is faster, supports vision natively, and is cheaper. Organizations should evaluate whether migrating to GPT-4o or o3 makes more sense before building new workflows on this model.
128K context window handles full codebases, long legal documents, and lengthy transcripts
Strong instruction-following with reliable JSON mode and function calling
Broad world knowledge with an April 2024 training cutoff
Consistent output quality on complex, multi-turn reasoning tasks
Weaknesses
At $10/$30 per million tokens, it's significantly more expensive than Claude Sonnet 4.6 or Gemini 1.5 Pro for comparable output quality
Largely superseded by GPT-4o and newer OpenAI models that are faster and cheaper
No native image generation capability; multimodal input only, no output
Real-world use cases
What people actually use GPT-4 Turbo for.
Analyzing a 100-page legal contract and extracting key clauses with citations
Generating a full REST API with authentication, error handling, and test coverage from a detailed spec
Synthesizing research across multiple long academic papers into a structured literature review
How GPT-4 Turbo compares
The nearest models people weigh against it, and what actually separates them.
vs GPT-4 Turbo (older v1106) — Against GPT-4 Turbo (older v1106) (OpenAI), GPT-4 Turbo lands within a few percent on price. Which one wins depends on whether context depth or latency is your constraint.
vs GPT-4 Turbo Preview — Against GPT-4 Turbo Preview (OpenAI), GPT-4 Turbo lands within a few percent on price. Which one wins depends on whether context depth or latency is your constraint.
vs GPT-5 — Against GPT-5 (OpenAI), GPT-4 Turbo costs about 72% more per token and gives up 3.1x on context. GPT-5 is the one to check first if the price difference matters more than the ceiling.
Price History
GPT-4 Turbo pricing over time
→0% since May 31
90 data points · tracked daily since May 31, 2026
Ready to try it?
Start using GPT-4 Turbo
Complex multi-step tasks requiring deep reasoning, long document analysis, or sophisticated code generation where cost is secondary to quality.. Start free — no card required.
GPT-4 Turbo (v1106) is an older snapshot of OpenAI's flagship GPT-4 Turbo model released in November 2023, offering a 128K context window with strong general-purpose reasoning and instruction-following capabilities. It predates later GPT-4 Turbo updates and GPT-4o, making it a legacy choice for workflows locked to this specific version.
Verdict
A reliable but outdated GPT-4 snapshot that only makes sense when version pinning is a hard requirement.
Quality score
66%
Pricing
$10.00/1M in
$30.00/1M out
Speed
Balanced
3/5 speed
Context
128k tokens
This is a pinned model snapshot (v1106) and will not receive capability updates. OpenAI may deprecate older snapshots over time. Knowledge cutoff is April 2023. Not recommended for new deployments given the superior cost-performance of GPT-4o and GPT-4.1.
Legacy128K ContextPinned SnapshotGPT-4Premium
Best for
Teams requiring a pinned, stable version of GPT-4 Turbo for reproducible outputs in long-document analysis or complex instruction pipelines.
GPT-4 Turbo Preview is an early access version of GPT-4 Turbo, OpenAI's then-flagship model featuring a 128K context window and knowledge improvements over the original GPT-4. It was designed to deliver GPT-4-class reasoning at reduced cost compared to the original GPT-4.
Verdict
A once-capable flagship now overshadowed by faster, cheaper, and smarter successors.
Quality score
67%
Pricing
$10.00/1M in
$30.00/1M out
Speed
Balanced
3/5 speed
Context
128k tokens
This is a 'preview' variant that OpenAI has largely deprecated in favor of gpt-4-turbo and gpt-4o. The endpoint may be retired or redirected by OpenAI without notice. Check the OpenAI model deprecation schedule before building production applications on this model.
GPT-4Long ContextLegacyPremiumOpenAI
Best for
Complex multi-step reasoning, long-document analysis, and professional writing tasks requiring strong instruction-following.
GPT-5 is OpenAI's flagship multimodal model, superseding GPT-4o with significantly improved reasoning, instruction-following, and knowledge breadth. It handles text, images, and complex multi-step tasks with state-of-the-art performance across most benchmarks.
Verdict
OpenAI's best general-purpose model — a strong flagship pick that punches above its price on input costs while delivering top-tier reasoning and multimodal capability.
Quality score
87%
Pricing
$1.25/1M in
$10.00/1M out
Speed
Balanced
3/5 speed
Context
400k tokens
Pricing is asymmetric: cheap on input ($1.25/1M) but expensive on output ($10/1M), so it favors read-heavy or summarization tasks over verbose generation. The 400K context window is one of the largest available at this price tier. Supersedes GPT-4o, which remains available at lower cost for lighter workloads.
FlagshipMultimodalLong ContextOpenAIReasoning
Best for
High-stakes professional tasks requiring deep reasoning, precise instruction-following, and reliable multimodal understanding.
GPT-4 Turbo costs $10 per million input tokens and $30 per million output tokens on the API. A month of 10M input and 2M output tokens runs about $160.00 at list price, before any batch or caching discounts.
What is the context window of GPT-4 Turbo?
GPT-4 Turbo has a 128k tokens context window, with up to 4k tokens of output per response. That is the total of prompt plus response the model can hold in one request.
What is the knowledge cutoff of GPT-4 Turbo?
GPT-4 Turbo's training data runs through December 2023, and the model was released on April 9, 2024. For anything after that date it needs web search or documents in the prompt.
What is GPT-4 Turbo best for?
GPT-4 Turbo is best for complex multi-step tasks requiring deep reasoning, long document analysis, or sophisticated code generation where cost is secondary to quality.. It is a strong fit when that workflow matters more than the tradeoffs around premium pricing and balanced speed.
When should I avoid GPT-4 Turbo?
You're cost-sensitive or need real-time speed — GPT-4o Mini, Claude Haiku, or Gemini Flash deliver far better value per dollar for most standard tasks.
What is a cheaper alternative to GPT-4 Turbo?
GPT-5 (OpenAI) at $1.25/1M/1M input against GPT-4 Turbo's $10.00/1M/1M — roughly 72% less per token all in. OpenAI's best general-purpose model — a strong flagship pick that punches above its price on input costs while delivering top-tier reasoning and multimodal capability. Compare it first if GPT-4 Turbo's pricing is the thing stopping you.
What is a faster alternative to GPT-4 Turbo?
GPT-4 Turbo (older v1106) — balanced against GPT-4 Turbo's balanced, with 128k tokens of context. Worth the swap when response time is what your users notice rather than the last few points of reasoning depth.
Newsletter
Get notified when GPT-4 Turbo pricing changes
We track pricing daily. When this model drops or spikes, you'll know first.
No spam. Useful updates only. Affiliate disclosures always clearly labeled.