GPT-6.2 Astra
Model ranking
- Arena Score
- 1414.1633904154
- Arena reference rank
- 141
- Evaluation configuration
- GPT-6.2 Astra (Max)
- Source published
- 2026-11-19
- Votes
- 2398
- Confidence lower
- 1401.7604239276
- Confidence upper
- 1426.5663569033
- Last successful check
- 2026-11-22T14:00:05.877Z
- Last value/rank change
- 2026-11-22T09:30:20.053Z
- Methodology
- Human preference — Text / overall; checked every six hours.
Source: Arena / LMArena ↗ · CC BY 4.0. Selection and catalog matching by XPU LIVE.
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
Batch / short context Input $4USD / 1M tokensOutput $20USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Batch / short contextInput: $4 Output: $20 Cache Read: $0.2 Cache Write 30m: $5 Cache Write 12h: $10 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Batch / long context Input $8USD / 1M tokensOutput $30USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Batch / long contextInput: $8 Output: $30 Cache Read: $0.4 Cache Write 30m: $10 Cache Write 12h: $20 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Standard / short context Input $8USD / 1M tokensOutput $40USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Standard / short contextInput: $8 Output: $40 Cache Read: $0.4 Cache Write 30m: $10 Cache Write 12h: $20 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Standard / long context Input $16USD / 1M tokensOutput $60USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Standard / long contextInput: $16 Output: $60 Cache Read: $0.8 Cache Write 30m: $20 Cache Write 12h: $40 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Fast / short context Input $16USD / 1M tokensOutput $80USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Fast / short contextInput: $16 Output: $80 Cache Read: $0.8 Cache Write 30m: $20 Cache Write 12h: $40 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Ultrafast / short context Input $24USD / 1M tokensOutput $120USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Ultrafast / short contextInput: $24 Output: $120 Cache Read: $1.2 Cache Write 30m: $30 Cache Write 12h: $60 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. Ultrafast promotion applies until March 1, 2027 at 00:00 Pacific time. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Fast / long context Input $32USD / 1M tokensOutput $120USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Fast / long contextInput: $32 Output: $120 Cache Read: $1.6 Cache Write 30m: $40 Cache Write 12h: $80 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗Ultrafast / long context Tariff not listedInput $48USD / 1M tokensOutput $180USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenAI · Ultrafast / long contextInput: $48 Output: $180 Cache Read: $2.4 Cache Write 30m: $60 Cache Write 12h: $120 Short context: up to 272,000 input tokens; long context: over 272,000. Endpoint eligibility follows the official model documentation. Ultrafast promotion applies until March 1, 2027 at 00:00 Pacific time. These are text token rates. Checked 2026-11-22T15:43:15.988Z Price source ↗ | gpt-6.2-astra | Catalog-listedConditionsSource-listed tariff. The live engine supplies prices and observation timestamps. Compare explicit Batch and prompt-length tiers; missing prices are unknown. | Not supplied | Official source ↗2026-11-19 | |
Batch / Router catalog Input $4USD / 1M tokensOutput $20USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenRouter · Batch / Router catalogInput: $4 Output: $20 Cache Read: $0.2 Cache Write: $5 Web Search: $0.01 Batch processing tariff; not a synchronous Standard request. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-11-22T15:43:15.988Z Price source ↗Batch / Router catalog / >272000 prompt tokens Input $8USD / 1M tokensOutput $30USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenRouter · Batch / Router catalog / >272000 prompt tokensInput: $8 Output: $30 Cache Read: $0.4 Cache Write: $10 Web Search: $0.01 Conditional prompt-length pricing from OpenRouter. All prompt tokens count toward the strictly-greater threshold; omitted price keys inherit earlier matching overrides or the base. Batch processing tariff; not a synchronous Standard request. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-11-22T15:43:15.988Z Price source ↗Router catalog Input $8USD / 1M tokensOutput $40USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenRouter · Router catalogInput: $8 Output: $40 Cache Read: $0.4 Cache Write: $10 Web Search: $0.01 OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-11-22T15:43:15.988Z Price source ↗Router catalog / >272000 prompt tokens Tariff not listedInput $16USD / 1M tokensOutput $60USD / 1M tokens Updated 2026-11-22 · 15:43 UTCOpenRouter · Router catalog / >272000 prompt tokensInput: $16 Output: $60 Cache Read: $0.8 Cache Write: $20 Web Search: $0.01 Conditional prompt-length pricing from OpenRouter. All prompt tokens count toward the strictly-greater threshold; omitted price keys inherit earlier matching overrides or the base. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-11-22T15:43:15.988Z Price source ↗ | openai/gpt-6.2-astra | Catalog-listedConditionsSource-listed tariff. The live engine supplies prices and observation timestamps. Compare explicit Batch and prompt-length tiers; missing prices are unknown. | Not supplied | Official source ↗2026-11-19 |
GPT-6.2 Astra is a OpenAI AI model listed in the OpenRouter catalog. This page separates provider pricing, context limits and independent evaluation results. Source information was checked on November 19, 2026.
GPT-6.2 Astra specifications
OpenRouter lists a context window of 1,050,000 tokens and a maximum completion of 128,000 tokens for its route. These are route limits; the original provider and other deployments can impose different limits. The exact OpenRouter identifier is openai/gpt-6.2-astra.
Pricing and tariff conditions
The provider table shows collected prices with their source and observation time. Compare input and output from the same tariff. Batch processing, prompt length, caching, tools and regional processing can change charges. A Batch price does not describe an ordinary synchronous request.
Prompt-length tiers retain their thresholds. Check the published source before estimating a bill for a large prompt. Missing prices mean unknown, and a retained historical quote is not an active service guarantee.
Benchmark and model comparison
The Artificial Analysis Intelligence Index score is 62 for the published configuration GPT-6.2 Astra Max. This is a dated evaluation result checked on November 19, 2026. Rank on xpu live is among verified models in this curated catalog. Other reasoning settings can produce different results and costs.
Sources and availability
Original provider pricing reference · OpenRouter model catalog. Availability depends on the chosen route, account and region. Review the exact provider model identifier and tariff conditions before integrating.
Specifications
- Catalog model ID
- openai/gpt-6.2-astra
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- file, image, text
- Output modalities
- text
- Context / input token limit
- 1,050,000
- Maximum output tokens
- 128,000
- Tool calling
- Not verified in cited sources
- Structured output
- Not verified in cited sources
- API parameters (source-specific)
- Not verified in cited sources
- Weight access
- Proprietary / hosted API
- Weight license / access terms
- Not verified in cited sources
- Total parameters (billions)
- Not publicly disclosed
- Active parameters (billions)
- Not publicly disclosed
- Download size (GB)
- Not applicable — no public weights
- Release date
- Not verified in cited sources
- Notes
- Provider route limits and eligibility can differ. Compare the exact tariff, context tier and billing mode.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.