System AI Gpt 6.2 Astra
system.ai.gpt-6-2-astraPricing
List prices at Databricks, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $8.00 | $40.00 | |
| Cached input 95% off input | $0.40 | 95% off input | |
| Cache write, 5 minutes | $10.00 | ||
| Priority 100% more | $16.00 | $80.00 | 100% more |
| Prompts over 272K tokens | $16.00 | $60.00 |
What it costs a month
At Databricks list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$4,716
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$3,456
- Coding agent1,000 requests a day, 40K in / 2K out, cached$5,616
- Overnight batch20,000 requests a day, 4K in / 0.4K out$28,800
Where to run it
1 host serve System AI Gpt 6.2 Astra. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DatabricksCloud system.ai.gpt-6-2-astra | $8.00 / $40.00 | system.ai.gpt-6-2-astra |
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
- ImagesText
- Produces
- Text
- Features
- Prompt caching
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 Databricks.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 50% less
- 63% less
- 70% less
- 81% less
Open-weight picks
- 75% less
- 87% less
- 88% less
- 89% less
Call it
Using Databricks's API.
from litellm import completion
response = completion(
model="databricks/system.ai.gpt-6-2-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does System AI Gpt 6.2 Astra cost?
On Databricks, System AI Gpt 6.2 Astra costs $8.00 per million input tokens and $40.00 per million output tokens. Cached input costs $0.40 per million tokens.
Which APIs offer System AI Gpt 6.2 Astra?
System AI Gpt 6.2 Astra runs on 1 API: Databricks.
What is System AI Gpt 6.2 Astra's context window?
922K tokens, with up to 128K tokens in one reply.
Is System AI Gpt 6.2 Astra being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to System AI Gpt 6.2 Astra?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (50% less), Gemini 4 Neon on Google AI Studio (63% less) and Kimi K3.1 Pro on Databricks (75% less). Savings are on a mix of 3 input tokens to 1 output token.
What is System AI Gpt 6.2 Astra's API model id?
Use system.ai.gpt-6-2-astra with Databricks.
Sources
Raw catalog entry for system.ai.gpt-6-2-astra on Databricks
{
"cache_creation_input_token_cost": 0.00001,
"cache_creation_input_token_cost_above_272k_tokens": 0.00002,
"cache_creation_input_token_cost_above_272k_tokens_priority": 0.00004,
"cache_creation_input_token_cost_priority": 0.00002,
"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_priority": 0.0000016,
"cache_read_input_token_cost_priority": 8e-7,
"input_cost_per_token": 0.000008,
"input_cost_per_token_above_272k_tokens": 0.000016,
"input_cost_per_token_above_272k_tokens_priority": 0.000032,
"input_cost_per_token_priority": 0.000016,
"litellm_provider": "databricks",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"metadata": {
"notes": "GPT-6.2 Astra on Databricks is available only through Unity Gateway with the model service name system.ai.gpt-6-2-astra. The Databricks pricing pages list no row for it yet, so prices are the Standard and Fast (priority) rates on the OpenAI pricing page for gpt-6.2-astra with OpenAI's 272K long context threshold, and no '*_dbu_cost_per_token' fields are published. Replace them with the Databricks DBU rates once Databricks publishes them."
},
"mode": "chat",
"output_cost_per_token": 0.00004,
"output_cost_per_token_above_272k_tokens": 0.00006,
"output_cost_per_token_above_272k_tokens_priority": 0.00012,
"output_cost_per_token_priority": 0.00008,
"source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
}