theserverless.dev InferenceList

Models / OpenAI

OpenAI: GPT-6 Astra

openai/gpt-6-astra

text imageContext 1.1M

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

Price

Input$10

per 1M tokens

Output$50

per 1M tokens

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
OpenAI openai/flex — $5/1M $25/1M 1.1M 100% Live openrouter-endpoints
Amazon Bedrock amazon-bedrock/global — $10/1M $50/1M 1.1M 100% Live openrouter-endpoints
AtlasCloud — fp8 $10/1M $50/1M 1.1M — Listed atlascloud
Azure azure — $10/1M $50/1M 1.1M 100% Live openrouter-endpoints
Inference.net — — $10/1M $50/1M 922K — Listed inferencenet
NEAR AI — — $10/1M $50/1M 1.1M — Listed nearai
OpenAI openai — $10/1M $50/1M 1.1M 83% Live openrouter-endpoints
Phala — — $10/1M $50/1M 272K — Listed phala
Amazon Bedrock amazon-bedrock/us-west-2 — $11/1M $55/1M 1.1M — Live openrouter-endpoints
Azure azure/us — $11/1M $55/1M 1.1M — Live openrouter-endpoints
OpenAI openai/fast — $20/1M $100/1M 1.1M — Live openrouter-endpoints
OpenAI openai/ultrafast — $60/1M $300/1M 1.1M 100% Live openrouter-endpoints

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$60.00 at list price for this workload

Cache

Cache read$1

per 1M tokens

Cache write$12.5

per 1M tokens

Tiers

Web search
$0.01 per request
Above 272,000 prompt tokens
in $20 · out $75 · cache read $2 · cache write $25
Every rate
UnitInputOutputFlatConfidence
token $10/1M $50/1M Not published— official

Price history

OpenAI: GPT-6 Astra
55 0 2026-09-15: $102026-09-16: $102026-09-17: $102026-09-18: $102026-09-19: $102026-09-20: $102026-09-21: $102026-09-22: $102026-09-23: $102026-09-24: $102026-09-25: $102026-09-26: $102026-09-27: $102026-09-28: $102026-09-29: $102026-09-30: $102026-10-01: $102026-10-02: $102026-10-03: $102026-10-04: $102026-10-05: $102026-10-06: $102026-10-07: $102026-10-08: $102026-10-09: $102026-10-10: $102026-10-11: $102026-10-12: $102026-10-13: $102026-10-14: $102026-10-15: $102026-10-16: $102026-10-17: $102026-10-18: $102026-10-19: $102026-10-20: $102026-10-21: $102026-10-22: $102026-10-23: $102026-10-24: $102026-10-25: $102026-10-26: $102026-10-27: $102026-10-28: $102026-10-29: $102026-10-30: $10 2026-09-15 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-09-15 token $10 $50 Not published—
2026-09-16 token $10 $50 Not published—
2026-09-17 token $10 $50 Not published—
2026-09-18 token $10 $50 Not published—
2026-09-19 token $10 $50 Not published—
2026-09-20 token $10 $50 Not published—
2026-09-21 token $10 $50 Not published—
2026-09-22 token $10 $50 Not published—
2026-09-23 token $10 $50 Not published—
2026-09-24 token $10 $50 Not published—
2026-09-25 token $10 $50 Not published—
2026-09-26 token $10 $50 Not published—
2026-09-27 token $10 $50 Not published—
2026-09-28 token $10 $50 Not published—
2026-09-29 token $10 $50 Not published—
2026-09-30 token $10 $50 Not published—
2026-10-01 token $10 $50 Not published—
2026-10-02 token $10 $50 Not published—
2026-10-03 token $10 $50 Not published—
2026-10-04 token $10 $50 Not published—
2026-10-05 token $10 $50 Not published—
2026-10-06 token $10 $50 Not published—
2026-10-07 token $10 $50 Not published—
2026-10-08 token $10 $50 Not published—
2026-10-09 token $10 $50 Not published—
2026-10-10 token $10 $50 Not published—
2026-10-11 token $10 $50 Not published—
2026-10-12 token $10 $50 Not published—
2026-10-13 token $10 $50 Not published—
2026-10-14 token $10 $50 Not published—
2026-10-15 token $10 $50 Not published—
2026-10-16 token $10 $50 Not published—
2026-10-17 token $10 $50 Not published—
2026-10-18 token $10 $50 Not published—
2026-10-19 token $10 $50 Not published—
2026-10-20 token $10 $50 Not published—
2026-10-21 token $10 $50 Not published—
2026-10-22 token $10 $50 Not published—
2026-10-23 token $10 $50 Not published—
2026-10-24 token $10 $50 Not published—
2026-10-25 token $10 $50 Not published—
2026-10-26 token $10 $50 Not published—
2026-10-27 token $10 $50 Not published—
2026-10-28 token $10 $50 Not published—
2026-10-29 token $10 $50 Not published—
2026-10-30 token $10 $50 Not published—

Alternatives

Parameters (11)
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
Call this model

OpenRouter id openai/gpt-6-astra. InferenceList does not send the request.

curl
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-6-astra","messages":[{"role":"user","content":"Hello"}]}'

JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "openai/gpt-6-astra",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "openai/gpt-6-astra", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON