impulse

GPT-6 Astra

Frontier lab

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.

API id gpt-6-astraReleased 3 Sep 2026 (Sep 2026)
Input / 1M
$10.00
at OpenAI
Output / 1M
$50.00
at OpenAI
Context window
922K
tokens
Max output
128K
tokens per reply
Hosts
8
15 listings
Released
Sep 2026
3 Sep 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$10.00$50.00
Cached input
90% off input
$1.00
Cache write, 5 minutes$12.50
Batch
50% off
$5.00$25.00
Flex
50% off
$5.00$25.00
Priority
100% more
$20.00$100.00
Prompts over 272K tokens$20.00$75.00
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$5,940
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$4,440
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$7,440
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$18,000
Use your own numbers

Where to run it

8 hosts serve GPT-6 Astra. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-6-astra
$10.00 / $50.00
databricks-gpt-6-astra
$10.00 / $50.00
global
global.openai.gpt-6-astra
$10.00 / $50.00
gpt-6-astra
$10.00 / $50.00
Retires 11 Jan 2028
gpt-6-astra
$10.00 / $50.00
GMI CloudInference
gpt-6-astra
$10.00 / $50.00
PerplexityGateway
gpt-6-astra
$10.00 / $50.00
gpt-6-astra
$13.50 / $67.50
+35% vs headline
GitHub CopilotSubscription
gpt-6-astra
In the subscription
ChatGPTSubscription
gpt-6-astra
In the subscription
Show 5 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
openai.gpt-6-astra
$11.00 / $55.00
+10% vs headline
us
us.openai.gpt-6-astra
$11.00 / $55.00
+10% vs headline
Azure OpenAI
2026-09-03
gpt-6-astra-2026-09-03
$10.00 / $50.00
Retires 11 Jan 2028
us
gpt-6-astra
$11.00 / $55.00
+10% vs headline
Retires 11 Jan 2028
eu
gpt-6-astra
$12.00 / $60.00
+20% vs headline
Retires 11 Jan 2028

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
xhighmax
Features
Computer useParallel 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-6.2 Astra
    OpenAI · on OpenAI
    $8.00 / $40.00
    Has every key capability
    20% less
  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    76% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    80% less

Other frontier labs

  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
    20% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    80% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    85% less
  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    60% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    80% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    89% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    91% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    97% less

Model line

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

  1. Nov 2026GPT-6.2 AstraLatest$8.00 / $40.00
  2. Sep 2026GPT-6 AstraThis page$10.00 / $50.00

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-6-astra", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-6 Astra cost?

On OpenAI, GPT-6 Astra costs $10.00 per million input tokens and $50.00 per million output tokens. Cached input costs $1.00 per million tokens.

Which APIs offer GPT-6 Astra?

GPT-6 Astra runs on 8 APIs: OpenAI, Databricks, Amazon Bedrock, Azure OpenAI, Azure AI Foundry, GMI Cloud, Perplexity and Kyma API.

What is GPT-6 Astra's context window?

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

Is GPT-6 Astra being retired?

Azure OpenAI retires it on 11 Jan 2028. 7 hosts keep serving it.

Is there a newer version of GPT-6 Astra?

Yes. GPT-6.2 Astra is the newest model in this line, released on 17 Nov 2026.

What are cheaper alternatives to GPT-6 Astra?

Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (20% less), Claude Fable 5.2 on Anthropic (20% less), Gemini 4 Carbon on Google AI Studio (80% less) and Kimi K3.1 Pro on Databricks (80% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-6 Astra released?

OpenAI released it on 3 Sep 2026.

What is GPT-6 Astra's API model id?

Use gpt-6-astra with OpenAI. Other hosts use their own ids: databricks-gpt-6-astra on Databricks, global.openai.gpt-6-astra on Amazon Bedrock.

Sources

Raw catalog entry for gpt-6-astra on OpenAI
{
  "cache_creation_input_token_cost": 0.0000125,
  "cache_creation_input_token_cost_above_12hr": 0.000025,
  "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015,
  "cache_creation_input_token_cost_above_12hr_batches": 0.0000125,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 0.00005,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 0.000025,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 0.000025,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003,
  "cache_creation_input_token_cost_above_12hr_flex": 0.0000125,
  "cache_creation_input_token_cost_above_12hr_priority": 0.00005,
  "cache_creation_input_token_cost_above_272k_tokens": 0.000025,
  "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000125,
  "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00005,
  "cache_creation_input_token_cost_flex": 0.00000625,
  "cache_creation_input_token_cost_priority": 0.000025,
  "cache_read_input_token_cost": 0.000001,
  "cache_read_input_token_cost_above_272k_tokens": 0.000002,
  "cache_read_input_token_cost_above_272k_tokens_flex": 0.000001,
  "cache_read_input_token_cost_above_272k_tokens_priority": 0.000004,
  "cache_read_input_token_cost_batches": 5e-7,
  "cache_read_input_token_cost_above_272k_tokens_batches": 0.000001,
  "cache_creation_input_token_cost_batches": 0.00000625,
  "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000125,
  "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015,
  "cache_creation_input_token_cost_ultrafast": 0.000075,
  "cache_read_input_token_cost_above_272k_tokens_ultrafast": 0.000012,
  "cache_read_input_token_cost_flex": 5e-7,
  "cache_read_input_token_cost_priority": 0.000002,
  "cache_read_input_token_cost_ultrafast": 0.000006,
  "input_cost_per_token": 0.00001,
  "input_cost_per_token_above_272k_tokens": 0.00002,
  "input_cost_per_token_above_272k_tokens_flex": 0.00001,
  "input_cost_per_token_above_272k_tokens_priority": 0.00004,
  "input_cost_per_token_batches": 0.000005,
  "input_cost_per_token_above_272k_tokens_batches": 0.00001,
  "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012,
  "input_cost_per_token_flex": 0.000005,
  "input_cost_per_token_priority": 0.00002,
  "input_cost_per_token_ultrafast": 0.00006,
  "litellm_provider": "openai",
  "max_input_tokens": 922000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.00005,
  "output_cost_per_token_above_272k_tokens": 0.000075,
  "output_cost_per_token_above_272k_tokens_flex": 0.0000375,
  "output_cost_per_token_above_272k_tokens_priority": 0.00015,
  "output_cost_per_token_batches": 0.000025,
  "output_cost_per_token_above_272k_tokens_batches": 0.0000375,
  "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045,
  "output_cost_per_token_flex": 0.000025,
  "output_cost_per_token_priority": 0.0001,
  "output_cost_per_token_ultrafast": 0.0003,
  "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
  },
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/chat/completions",
    "/v1/batch",
    "/v1/responses"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_computer_use": true,
  "supports_function_calling": true,
  "supports_max_reasoning_effort": true,
  "supports_minimal_reasoning_effort": false,
  "supports_native_streaming": true,
  "supports_none_reasoning_effort": false,
  "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
}