impulse

GPT-5.6

Frontier lab
API id gpt-5.6
Input / 1M
$4.00
at OpenAI
Output / 1M
$20.00
at OpenAI
Context window
922K
tokens
Max output
128K
tokens per reply
Hosts
2
4 listings
Released
-
date not published

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$4.00$20.00
Cached input
90% off input
$0.40
Cache write, 5 minutes$5.00
Batch
50% off
$2.00$10.00
Flex
50% off
$2.00$10.00
Priority
100% more
$8.00$40.00
Prompts over 272K tokens$8.00$30.00
Web search
$10.00 per 1,000 searches
Regional endpoints
10% more

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$2,376
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,776
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,976
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$7,200
Use your own numbers

Where to run it

2 hosts serve GPT-5.6. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-5.6
$4.00 / $20.00
gpt-5.6
$4.00 / $20.00
Show 2 more listings: regions, snapshots and variants
Azure OpenAI
us
gpt-5.6
$4.40 / $22.00
+10% vs headline
eu
gpt-5.6
$4.40 / $22.00
+10% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesTextPDFs
Produces
Text
Effort settings the source lists
nonexhigh
Features
Parallel tool callsPDF inputPrompt cachingTool searchBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    40% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    50% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    75% less

Other frontier labs

  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    50% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    50% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    63% less
  • Gemini 4 Argon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    50% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    50% less
  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    72% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    78% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    93% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedGPT-5.6Latest$4.00 / $20.00
  2. Apr 2026GPT-5.5$5.00 / $30.00
  3. Mar 2026GPT-5.4$2.50 / $15.00
  4. Dec 2025GPT-5.2$1.75 / $14.00
  5. Nov 2025GPT-5.1$1.25 / $10.00
  6. Aug 2025GPT-5$1.25 / $10.00
  7. Apr 2025GPT-4.1$2.00 / $8.00
  8. May 2023GPT-4$30.00 / $60.00

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-5.6", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-5.6 cost?

On OpenAI, GPT-5.6 costs $4.00 per million input tokens and $20.00 per million output tokens. Cached input costs $0.40 per million tokens.

Which APIs offer GPT-5.6?

GPT-5.6 runs on 2 APIs: OpenAI and Azure OpenAI.

What is GPT-5.6's context window?

922K tokens, with up to 128K tokens in one reply.

Is GPT-5.6 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of GPT-5.6?

No. GPT-5.6 is the newest model in its line.

What are cheaper alternatives to GPT-5.6?

Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (40% less), Gemini 4 Carbon on Google AI Studio (50% less), Claude Sonnet 5.5 on Anthropic (50% less) and Kimi K3.1 Pro on Databricks (50% less). Savings are on a mix of 3 input tokens to 1 output token.

What is GPT-5.6's API model id?

Use gpt-5.6 with OpenAI.

Sources

Raw catalog entry for gpt-5.6 on OpenAI
{
  "cache_creation_input_token_cost": 0.000005,
  "cache_creation_input_token_cost_above_12hr": 0.00001,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 0.00002,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 0.00001,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.00004,
  "cache_creation_input_token_cost_above_12hr_flex": 0.000005,
  "cache_creation_input_token_cost_above_12hr_priority": 0.00002,
  "cache_creation_input_token_cost_above_272k_tokens": 0.00001,
  "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005,
  "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002,
  "cache_creation_input_token_cost_flex": 0.0000025,
  "cache_creation_input_token_cost_priority": 0.00001,
  "cache_read_input_token_cost": 4e-7,
  "cache_read_input_token_cost_above_272k_tokens": 8e-7,
  "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7,
  "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016,
  "cache_read_input_token_cost_batches": 2e-7,
  "cache_read_input_token_cost_above_272k_tokens_batches": 4e-7,
  "cache_creation_input_token_cost_batches": 0.0000025,
  "cache_creation_input_token_cost_above_272k_tokens_batches": 0.000005,
  "cache_read_input_token_cost_flex": 2e-7,
  "cache_read_input_token_cost_priority": 8e-7,
  "input_cost_per_token": 0.000004,
  "input_cost_per_token_above_272k_tokens": 0.000008,
  "input_cost_per_token_above_272k_tokens_flex": 0.000004,
  "input_cost_per_token_above_272k_tokens_priority": 0.000016,
  "input_cost_per_token_batches": 0.000002,
  "input_cost_per_token_above_272k_tokens_batches": 0.000004,
  "input_cost_per_token_flex": 0.000002,
  "input_cost_per_token_priority": 0.000008,
  "litellm_provider": "openai",
  "max_input_tokens": 922000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.00002,
  "output_cost_per_token_above_272k_tokens": 0.00003,
  "output_cost_per_token_above_272k_tokens_flex": 0.000015,
  "output_cost_per_token_above_272k_tokens_priority": 0.00006,
  "output_cost_per_token_batches": 0.00001,
  "output_cost_per_token_above_272k_tokens_batches": 0.000015,
  "output_cost_per_token_flex": 0.00001,
  "output_cost_per_token_priority": 0.00004,
  "reasoning_contexts": [
    "auto",
    "current_turn",
    "all_turns"
  ],
  "reasoning_modes": [
    "standard",
    "pro"
  ],
  "regional_processing_uplift_multiplier_eu": 1.1,
  "regional_processing_uplift_multiplier_us": 1.1,
  "fedramp_uplift_multiplier": 1.1,
  "search_context_cost_per_query": {
    "search_context_size_high": 0.01,
    "search_context_size_low": 0.01,
    "search_context_size_medium": 0.01
  },
  "supported_endpoints": [
    "/v1/chat/completions",
    "/v1/batch",
    "/v1/responses"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": true,
  "supports_minimal_reasoning_effort": false,
  "supports_native_streaming": true,
  "supports_none_reasoning_effort": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_cache_breakpoint": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_tool_search": true,
  "supports_vision": true,
  "supports_web_search": true,
  "supports_xhigh_reasoning_effort": true
}