jishie

GPT-6 Astra

venice/openai-gpt-6-astra · family gpt · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$20.00
Blended $/1M (3:1)
$10
Input $/1M
$50
Output $/1M
$60.00
1M in + 1M out
$1 −90%
Cache read $/1M
#7497 of 7,708
Cheapest rank
Provider
Venice AI (venice)
Kind
text (outputs text)
Context
1,050,000 tokens
Max output
128,000 tokens
Capabilities
tools reasoning text image

Same model, other providers

“GPT-6 Astra” is offered by 21 providers — cheapest-effective first. Ofox is the cheapest at $16.00 blended.

ProviderInputOutputBlendedContext
Ofox$8$40$16.001.1M
Venice AI (this)$10$50$20.001.1M
Kilo Gateway$10$50$20.001.1M
302.AI$10$50$20.001.1M
OpenRouter$10$50$20.001.1M
Azure$10$50$20.001.1M
Cloudflare AI Gateway$10$50$20.001.1M
Vercel AI Gateway$10$50$20.001.1M
Neon$10$50$20.001.1M
AIHubMix$10$50$20.001.1M
Merge Gateway$10$50$20.001.1M
Opper$10$50$20.001.1M
GitHub Copilot$10$50$20.001.1M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Venice AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"openai-gpt-6-astra","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Venice AI models · model index · JSON