Compare model

openai / Chat

GPT-6 Astra

openai/gpt-6-astra

OpenAI's most capable model for complex reasoning, coding and research — balanced thinking

Catalog status

Enabled

Research checked

2026-10-07

Price / performance

What it costs to get this result

FrontierCode v1.1 (Extended) · Source-reported results, not a composite ranking. Prices use the average of TokenBazaar input and output rates per million tokens; actual spend depends on usage. Test configurations differ.

GPT-6 Astra60.25% · 43 sourced models

Blended price / 1M tokens · log scale

● Current model● Other modelsDashed line: price/score frontier among plotted models
Compare sourced models on this benchmark

Benchmark results

6 reported results

Results are source-attributed, not TokenBazaar measurements. Different tests and thinking variants are not interchangeable.

6 of 6 results

FrontierMath Tier 4 (v2)

Math · Third-party report

Test conditions and source

Third-party reproduction of OpenAI’s announcement table; reported maximum effort unless noted, not a TokenBazaar run. Direct launch page could not be fetched during this audit.

Tested model: openai/gpt-6-astra

Vellum · GPT-6 Astra launch-table analysis · Checked 2026-10-06

97.6%

ARC-AGI-3

Reasoning · Third-party report

Test conditions and source

Semi-private ARC-AGI-3, Provider Adapter harness, high reasoning: 99.9%. Standard harness at max reasoning instead reports 62.7%; opaque state reuse and compaction materially change the result.

Tested model: openai/gpt-6-astra

ARC Prize · GPT-6 Astra evaluated results · Checked 2026-10-06

99.9%

ExploitBench

Coding · Third-party report

Test conditions and source

Third-party reproduction of OpenAI’s announcement table; reported maximum effort unless noted, not a TokenBazaar run. Direct launch page could not be fetched during this audit. Evaluated without production safeguards.

Tested model: openai/gpt-6-astra

Vellum · GPT-6 Astra launch-table analysis · Checked 2026-10-06

100%

Terminal-Bench-Science 0.1

Agentic · Third-party report

Test conditions and source

Third-party reproduction of OpenAI’s announcement table; reported maximum effort unless noted, not a TokenBazaar run. Direct launch page could not be fetched during this audit.

Tested model: openai/gpt-6-astra

Vellum · GPT-6 Astra launch-table analysis · Checked 2026-10-06

64.6%

FrontierCode v1.1 (Extended)

Coding · Third-party report

Test conditions and source

Cognition FrontierCode 1.1; GPT-6 Astra; medium effort; codex harness; Extended subset (150 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.6025. Publisher evaluation, not a TokenBazaar measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Tested model: openai/gpt-6-astra

Cognition · FrontierCode 1.1 original leaderboard · Checked 2026-10-07

60.25%

FrontierCode v1.1 (Main)

Coding · Third-party report

Test conditions and source

Cognition FrontierCode 1.1; GPT-6 Astra; medium effort; codex harness; Main subset (100 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.4883. Publisher evaluation, not a TokenBazaar measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Tested model: openai/gpt-6-astra

Cognition · FrontierCode 1.1 original leaderboard · Checked 2026-10-07

48.83%

Model specifications

Context window

1.05M

Published provider limit

Maximum output

128K

Published provider limit

Knowledge cutoff

Apr 30, 2026

Upstream model

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image

Output

Text
Exact model ID
openai/gpt-6-astra
Model type
Chat
Context window
1,050,000 tokens
Maximum output
128,000 tokens
Knowledge cutoff
Apr 30, 2026

A context window is the total conversation budget, not a separate maximum input allowance; generated output and reasoning can use that budget. Published provider limits are not independently tested TokenBazaar request limits.

Versions and thinking levels

Choose from 4 enabled versions. The exact ID determines the version and its price; benchmark scores do not carry over between variants.

GPT-6 AstraSelected₹480.00 in / ₹2400.00 out per 1M tokens
GPT-6 Astra Deep₹480.00 in / ₹2400.00 out per 1M tokens
GPT-6 Astra Fast₹480.00 in / ₹2400.00 out per 1M tokens
GPT-6 Astra Max₹480.00 in / ₹2400.00 out per 1M tokens

Features and tool support

TokenBazaar’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Reasoning configuration

The catalog version determines the requested reasoning effort.

Selected effort: medium (default catalog version). Reasoning level is not a measured intelligence or speed score.

Coding and agent workflows

Text/code generation and customer-managed tool loops.

Coding benchmark results do not establish a hosted terminal, sandbox, autonomous browser or guaranteed task success.

Streaming answers

Available

Incremental text through TokenBazaar’s chat endpoint; Claude also has native Messages access.

Customer-defined function tools

Limited

Only customer-defined function tools are forwarded. Model/protocol compatibility applies; your application authorizes and executes every tool.

Forced or named tool selection

Limited

The chat route accepts auto, none and required. A named-tool choice is not forwarded; exact model compatibility is not independently tested.

Images and PDFs

Limited

The chat bridge accepts image/PDF content. Provider input modalities are listed separately; file size, content and model limits still apply.

Hosted web search / browsing

Not exposed

No provider-hosted web search or web-fetch tool is exposed. Customer-owned search can be implemented as an authorized function tool.

Hosted code execution / computer use

Not exposed

No built-in execution environment or computer-control tool is provided. Code generation is not code execution.

Hosted file search / persistent assistants

Not exposed

No hosted file-search index, Assistants endpoint or persistent provider agent is exposed.

Batch / fine-tuning / cached-price discounts

Not exposed

No public batch or fine-tuning endpoint, or separate cached-token discount, is offered here.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenBaazar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.