GPT · Flagship · 400K context window
$0.6450 per call at 3,000 input / 5,000 output tokens.
Per call
$0.6450
10K calls/mo
$6,450
Cache savings
0% off input
Batch savings
50% off all
Adjust token counts, volume, and discount toggles to model your chain of thought spend. Prices verified daily against provider pricing pages.
Call GPT 5 Pro with the OpenAI Python SDK:
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-5-pro",
max_tokens=5000,
messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.6450 per call at standard rates
# Input: $15.00/MTok
# Output: $120.00/MTokPer-call cost for all models scoring 50+ on chain of thought benchmarks. Hover for details.
Cheapest viable option: Claude Sonnet 5 at $0.0560/call (91% less, 90/100 quality).
Reasoning tasks invert the usual ratio: the model produces far more tokens than it consumes, because the intermediate steps are the work. Output pricing dominates completely, and models that reason at length cost more than their headline rate suggests. Comparing reasoning models on input price is actively misleading; compare them on output.
For GPT 5 Pro specifically, that means output tokens cost 8.0x more than input, at $120.00 vs $15.00 per MTok. At this use case’s 3,000/5,000 token split, output accounts for 93% of the $0.6450 per-call cost.
| Direction | $/MTok | Tokens per call |
|---|---|---|
| Input | $15.00 | 3,000 |
| Output | $120.00 | 5,000 |
Caching drops input cost from $15.00 to $15.00/MTok. For repeated system prompts, that saves $0.0000 per call.
Submit requests asynchronously and receive 50% off all token costs. This works best for offline pipelines where latency requirements are flexible.
| Monthly volume | Cost per call | Standard monthly | Cached monthly | You save with caching |
|---|---|---|---|---|
| 10,000 calls | $0.6450 | $6,450 | $6,450 | $0.0000 |
| 50,000 calls | $0.6450 | $32,250 | $32,250 | $0.0000 |
| 100,000 calls | $0.6450 | $64,500 | $64,500 | $0.0000 |
| 500,000 calls | $0.6450 | $322,500 | $322,500 | $0.0000 |
| 1,000,000 calls | $0.6450 | $645,000 | $645,000 | $0.0000 |
Benchmark data for chain of thought is pending for GPT 5 Pro. Test against your own evaluation suite before moving to production.
GPT 5 Pro scores by task type. Chain of Thought highlighted.
| Task type | Confidence score | Rank out of 72 |
|---|
Confidence scores are a third-party benchmark snapshot from week 29 of 2026. This snapshot is 10 weeks old, so treat the scores as directional and validate against your own evals.
6 models score 80+ on chain of thought benchmarks, sorted by input rate. Cheapest: Claude Sonnet 5 (91% less, 90/100 quality).
| Model | Provider | Input $/MTok | Output $/MTok | Quality | Per call | vs GPT |
|---|---|---|---|---|---|---|
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 90/100 | $0.0560 | 91% cheaper |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 90/100 | $0.0660 | 90% cheaper |
| GPT 5.6 Sol | GPT | $4.00 | $20.00 | 96/100 | $0.1120 | 83% cheaper |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 97/100 | $0.1400 | 78% cheaper |
| GPT 5.5 | GPT | $5.00 | $30.00 | 95/100 | $0.1650 | 74% cheaper |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 98/100 | $0.2800 | 57% cheaper |
Provider
GPT
Tier
Flagship
Context
400K tokens
Released
Not published
Backfilled on 2026-09-23. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date not published in a machine-readable source. Not yet benchmarked, so never recommended.
| Model | Tier | Input $/MTok | Output $/MTok | Context |
|---|---|---|---|---|
| GPT 5.5 | Flagship | $5.00 | $30.00 | 1,050K |
| GPT 5.4 | Mid-tier | $2.50 | $15.00 | 1,050K |
| GPT 5.6 Sol | Flagship | $4.00 | $20.00 | 922K |
| GPT 5.6 Terra | Mid-tier | $2.00 | $12.00 | 922K |
| GPT 5.6 Luna | Fast / Budget | $0.20 | $1.20 | 922K |
| GPT 3.5 Turbo | Fast / Budget | $0.50 | $1.50 | 16.385K |
| GPT 3.5 Turbo (0125) | Fast / Budget | $0.50 | $1.50 | 16.385K |
| GPT 4 (0613) | Flagship | $30.00 | $60.00 | 8.192K |
| GPT 4 Turbo (2024-04-09) | Flagship | $10.00 | $30.00 | 128K |
| GPT 4.1 | Mid-tier | $2.00 | $8.00 | 1,047.576K |
| GPT 4.1 Mini | Fast / Budget | $0.40 | $1.60 | 1,047.576K |
| GPT 4.1 Nano | Fast / Budget | $0.10 | $0.40 | 1,047.576K |
| GPT 4o | Mid-tier | $2.50 | $10.00 | 128K |
| GPT 4o (2024-05-13) | Flagship | $5.00 | $15.00 | 128K |
| GPT 4o Mini | Fast / Budget | $0.15 | $0.60 | 128K |
| GPT 5 | Mid-tier | $1.25 | $10.00 | 272K |
| GPT 5 Mini | Fast / Budget | $0.25 | $2.00 | 272K |
| GPT 5 Nano | Fast / Budget | $0.05 | $0.40 | 272K |
| GPT 5.1 | Mid-tier | $1.25 | $10.00 | 272K |
| GPT 5.2 | Mid-tier | $1.75 | $14.00 | 272K |
| GPT 5.2 Pro | Flagship | $21.00 | $168.00 | 272K |
| GPT 5.4 Mini | Fast / Budget | $0.75 | $4.50 | 272K |
| GPT 5.4 Nano | Fast / Budget | $0.20 | $1.25 | 272K |
| GPT 5.4 Pro | Flagship | $30.00 | $180.00 | 1,050K |
| GPT 5.5 Pro | Flagship | $30.00 | $180.00 | 1,050K |
| GPT 6 Astra | Flagship | $10.00 | $50.00 | 922K |
| GPT 6 Luna | Fast / Budget | $0.10 | $0.50 | 922K |
| GPT 6 Sol | Flagship | $2.00 | $10.00 | 922K |
| o1 | Flagship | $15.00 | $60.00 | 200K |
| o1 Pro | Flagship | $150.00 | $600.00 | 200K |
| o3 | Mid-tier | $2.00 | $8.00 | 200K |
| o3 Mini | Fast / Budget | $1.10 | $4.40 | 200K |
| o3 Pro | Flagship | $20.00 | $80.00 | 200K |
| o4 Mini | Fast / Budget | $1.10 | $4.40 | 200K |
You can compare GPT 5 Pro head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.
See how GPT 5 Pro costs change across different workload types.
Code Generation
$0.5100/call
Unit Test Generation
$0.6450/call
SQL Generation
$0.1425/call
API Generation
$0.7650/call
Code Refactoring
$0.5400/call
Code Review
$0.3150/call
PR Review
$0.4800/call
Security Review
$0.3900/call
Bug Detection
$0.3150/call
Document Summarization
$0.2700/call
PDF Summarization
$0.4050/call
Meeting Notes
$0.3600/call
Email Summarization
$0.1050/call
Chatbot
$0.1500/call
RAG Pipeline
$0.2700/call
Customer Support Bot
$0.1650/call
FAQ Bot
$0.1185/call
Data Extraction
$0.1800/call
JSON Extraction
$0.1410/call
Invoice Parsing
$0.1020/call
Resume Parsing
$0.1335/call
Legal Analysis
$0.6300/call
Math Reasoning
$0.3825/call
Financial Analysis
$0.6000/call
Content Moderation
$0.0195/call
Sentiment Analysis
$0.0195/call
Categorization
$0.0300/call
Intent Detection
$0.0165/call
Copywriting
$0.2475/call
Blog Writing
$0.9750/call
Marketing Copy
$0.3720/call
Product Descriptions
$0.1875/call
A typical chain of thought call using GPT 5 Pro costs about $0.6450 per call. This estimate uses 3,000 input tokens and 5,000 output tokens at standard rates. Standard rates are $15.00 per million input tokens and $120.00 per million output tokens.
Our benchmark data does not yet include a chain of thought ranking for GPT 5 Pro. We recommend testing it against your own evaluation criteria before production usage.
The most affordable model for chain of thought above 80/100 quality is Claude Sonnet 5. It comes from Claude at $2.00 per million input tokens. Output costs $10.00 per million tokens with a quality score of 90/100. Switching from GPT 5 Pro to Claude Sonnet 5 saves about 91% per API call.
Three strategies lower GPT 5 Pro costs for this task type effectively. Prompt caching gives a 0% discount on input tokens when reusing system prompts. The batch API gives 50% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.6450 to about $0.3225 per call.
GPT has 34 other models alongside GPT 5 Pro today: GPT 5.5 at $5.00/$30.00 per million tokens (flagship), GPT 5.4 at $2.50/$15.00 per million tokens (mid-tier), GPT 5.6 Sol at $4.00/$20.00 per million tokens (flagship), GPT 5.6 Terra at $2.00/$12.00 per million tokens (mid-tier), GPT 5.6 Luna at $0.20/$1.20 per million tokens (fast / budget), GPT 3.5 Turbo at $0.50/$1.50 per million tokens (fast / budget), GPT 3.5 Turbo (0125) at $0.50/$1.50 per million tokens (fast / budget), GPT 4 (0613) at $30.00/$60.00 per million tokens (flagship), GPT 4 Turbo (2024-04-09) at $10.00/$30.00 per million tokens (flagship), GPT 4.1 at $2.00/$8.00 per million tokens (mid-tier), GPT 4.1 Mini at $0.40/$1.60 per million tokens (fast / budget), GPT 4.1 Nano at $0.10/$0.40 per million tokens (fast / budget), GPT 4o at $2.50/$10.00 per million tokens (mid-tier), GPT 4o (2024-05-13) at $5.00/$15.00 per million tokens (flagship), GPT 4o Mini at $0.15/$0.60 per million tokens (fast / budget), GPT 5 at $1.25/$10.00 per million tokens (mid-tier), GPT 5 Mini at $0.25/$2.00 per million tokens (fast / budget), GPT 5 Nano at $0.05/$0.40 per million tokens (fast / budget), GPT 5.1 at $1.25/$10.00 per million tokens (mid-tier), GPT 5.2 at $1.75/$14.00 per million tokens (mid-tier), GPT 5.2 Pro at $21.00/$168.00 per million tokens (flagship), GPT 5.4 Mini at $0.75/$4.50 per million tokens (fast / budget), GPT 5.4 Nano at $0.20/$1.25 per million tokens (fast / budget), GPT 5.4 Pro at $30.00/$180.00 per million tokens (flagship), GPT 5.5 Pro at $30.00/$180.00 per million tokens (flagship), GPT 6 Astra at $10.00/$50.00 per million tokens (flagship), GPT 6 Luna at $0.10/$0.50 per million tokens (fast / budget), GPT 6 Sol at $2.00/$10.00 per million tokens (flagship), o1 at $15.00/$60.00 per million tokens (flagship), o1 Pro at $150.00/$600.00 per million tokens (flagship), o3 at $2.00/$8.00 per million tokens (mid-tier), o3 Mini at $1.10/$4.40 per million tokens (fast / budget), o3 Pro at $20.00/$80.00 per million tokens (flagship), o4 Mini at $1.10/$4.40 per million tokens (fast / budget). The right choice depends on whether your chain of thought workload prioritizes quality, cost, or speed.
GPT 5 Pro supports a context window of 400K tokens per API call. This sets the maximum combined length of your input prompt and generated response. For chain of thought, typical calls use 3,000 input and 5,000 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.
This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.