Models

GPT-6 Astra (batch)

openai ↗ · 1050K ctx · 6 providers · updated 2026-09-12 06:15 UTC

Cheapest
$10.00 via OpenRouter
Avg price
$17.14 /1M
providers
6
Tokens (24h)
113B
Volume (24h)
$1.13M est.
(3 × $5.00 + $25.00) ÷ 4 = $10.00/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $5.00, 3:1 $10.00, 1:1 $15.00, output only $25.00 per 1M.

The board shows this model's cheapest measured offer ($10.00/1M); the smaller figure under it is the mean of the 7 offers listed below ($17.14/1M). Add those up and divide — it matches. 24h token volume (113B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here. Cross-check — Vercel AI Gateway: —% of gateway token volume, 7.09% of spend (2026-09-12; share-of-traffic, daily, data CC BY 4.0).

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $5.00$25.00 API-measured
requesty Requesty $5.00$25.00 API-measured
azure_ai Pricebook (LiteLLM) $10.00$50.00 Official list
azure Pricebook (LiteLLM) $10.00$50.00 Official list
openai Pricebook (LiteLLM) $10.00$50.00 Official list
openrouter Pricebook (LiteLLM) $10.00$50.00 Official list
0g-network 0G Router $10.00$50.00 API-measured

Volume trend

131B 7d d-6 · 71B tokensd-5 · 63B tokensd-4 · 87B tokensd-3 · 124B tokensd-2 · 122B tokensd-1 · 131B tokensd-0 · 113B tokens

Last 7 days: 71B → 113B (+60%); range 63B–131B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gpt-6-astra.json. Free reuse requires attribution to tkx.org.

FAQ

How much does GPT-6 Astra (batch) cost?

Cheapest measured offer right now: $5/1M input, $25/1M output via openrouter-best — across 6 tracked providers, refreshed hourly.

Who serves GPT-6 Astra (batch)?

6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is GPT-6 Astra (batch) used?

GPT-6 Astra (batch) routed 113B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings