OpenAI GPT-6 Astra API Pricing and Speed
OpenAI GPT-6 Astra API pricing: $10.00 per 1M tokens for input and $50.00 per 1M tokens for output, from the official API price list of OpenAI. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $10.00 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · no price change seen since 16 Oct 2026.
Quality on your task: not measured by Measured Lab yet. On our data, GPT-6 Astra fits 6 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $212.50 for 5,000 customer messages a month
- Calculated Pull data from invoices and documents with strict JSON and page images: $80.00 for 2,000 documents a month
- Calculated Summarize documents and meetings: $98.00 for 1,000 documents or meetings a month
- Calculated Translate content: $165.00 for 3,000 pages a month
- Calculated Chat assistant on your website: $2,085.00 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $587.50 for 500 coding tasks a month
What our data confirms
- Published Strict JSON output, in OpenAI documentation, read 17 Oct 2026
- Published Calls your tools, in OpenAI documentation, read 17 Oct 2026
- Published Reads images; OpenRouter listing, 9 Nov 2026
Example to try
“Read this invoice and return the supplier, invoice number, date, total and tax as JSON; leave a field empty if it is not on the page.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 3.9 s, 120 tokens/s (median of 115 test requests on 23 dates, short request)
- Observed Hidden reasoning: 142 tokens on that request, billed as output
Before you choose
- Published Training on your data, per OpenAI API data controls: no — API data is not used for training unless you explicitly opt in to share it, read 9 Nov 2026
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $10.00Input per 1M tokens, from OpenAI Published
- $50.00Output per 1M tokens, from OpenAI Published
- $1.00Cached input per 1M tokens, from OpenAI Published
All prices by channel
| Price per 1M tokens | OpenAI direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $10.00 Published | $10.00 Published | — |
| Output | $50.00 Published | $50.00 Published | — |
| Cached input · read | $1.00 Published | $1.00 Published | — |
| Cache write | $12.50 Published | $12.50 Published | — |
| Above the long-request threshold · input | $20.00 Published | — | — |
| Above the long-request threshold · output | $75.00 Published | — | — |
| Above the long-request threshold · cached input | $2.00 Published | — | — |
| Batch · input / output | — | $5.00 / $25.00 Published | — |
Input price from OpenAI, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$10.00 throughout9 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$10.00 throughout9 Nov 2026
Context window1,050,000tokens Published
Max output128,000tokens Published
Long-request price above272,000tokens Published
OpenRouter providers who serves this model through OpenRouter, at what price
OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.
Pinned min: $5.00 / $25.00 · OpenAI (openai/flex)
Unpinned range: input $5.00–$60.00, output $25.00–$300.00 across 8 endpoints of 3 providers (listing shows $10.00 / $50.00).
Models with the widest provider price spread on OpenRouter
Request fragment that pins OpenAI (openai/flex):
{"provider": {"order": ["openai/flex"], "allow_fallbacks": false}}With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).
All endpoints (8), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
| OpenAI | openai/flex | Not stated | $5.00 | $25.00 | 1,050,000 |
| Amazon Bedrock | amazon-bedrock/global | Not stated | $10.00 | $50.00 | 1,050,000 |
| Azure | azure | Not stated | $10.00 | $50.00 | 1,050,000 |
| OpenAI | openai | Not stated | $10.00 | $50.00 | 1,050,000 |
| Amazon Bedrock | amazon-bedrock/us-west-2 | Not stated | $11.00 | $55.00 | 1,050,000 |
| Azure | azure/us | Not stated | $11.00 | $55.00 | 1,050,000 |
| OpenAI | openai/fast | Not stated | $20.00 | $100.00 | 1,050,000 |
| OpenAI | openai/ultrafast | Not stated | $60.00 | $300.00 | 1,050,000 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: low115 answers on 23 dates · 100 % answered | 3.93 srange 1.54–9.12 s · slow 10 %: 5.42 s Observed | 120 tokens/srange 38.4–214 · slowest 10 %: 71.4 tokens/s | $0.0146range $0.008–$0.021 Calculated | 142for 76 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: low105 answers on 21 dates · 100 % answered | 4.04 srange 2.50–9.32 s · slow 10 %: 5.92 s Observed | 120 tokens/srange 46.3–215 · slowest 10 %: 64.5 tokens/s | $0.0144range $0.00748–$0.0219 Calculated | 143for 74 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: low105 answers on 21 dates · 100 % answered | 3.93 srange 2.53–9.74 s · slow 10 %: 5.18 s Observed | 120 tokens/srange 36.6–233 · slowest 10 %: 67.9 tokens/s | $0.0144range $0.00807–$0.0183 Calculated | 142for 76 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: low105 answers on 21 dates · 100 % answered | 3.89 srange 2.09–8.79 s · slow 10 %: 5.98 s Observed | 125 tokens/srange 40.5–213 · slowest 10 %: 78.0 tokens/s | $0.0143range $0.00823–$0.0199 Calculated | 140for 76 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: low105 answers on 21 dates · 100 % answered | 4.69 srange 1.54–17.88 s · slow 10 %: 7.25 s Observed | 119 tokens/srange 40.9–203 · slowest 10 %: 64.0 tokens/s | $0.0146range $0.00824–$0.0197 Calculated | 144for 76 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
Figures the provider publishes (1)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| HealthBench Professional | 64.7 Stated by the provider | Results table in GPT-6 Astra System Card - OpenAI Deployment Safety Hubread 17 Oct 2026 |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
What typical tasks cost with this model
| Task | At OpenAI's price ($10.00 / $50.00) | Through OpenRouter ($10.00 / $50.00) |
|---|---|---|
| 1,000 chat replies | $25.00 | $25.00 |
| Summarizing 100 documents | $6.10 | $6.10 |
| A day of coding assistant use | $20.00 | $20.00 |
Calculated Prices per 1M tokens (input / output) in brackets; token counts and what is not included: our assumptions and the same tasks on other models.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 16 Oct 2026
- Shown in: the United States
- Checks so far: 25 checks since 16 Oct 2026
- What changed: no price change since 16 Oct 2026
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| Above how many request tokens does GPT-6 Astra switch to its long-request price directly from OpenAI (official API price)? | 272 thousand tokens | Published | |
| How much does GPT-6 Astra cost per 1M cache-read tokens (cache hits) directly from OpenAI (official API price)? | $1.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M cache-read tokens (cache hits) when a request is above the long-request threshold, directly from OpenAI (official API price)? | $2.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M cache-write tokens directly from OpenAI (official API price)? | $12.50 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M cache-write tokens when a request is above the long-request threshold, directly from OpenAI (official API price)? | $25.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M input tokens directly from OpenAI (official API price)? | $10.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M output tokens directly from OpenAI (official API price)? | $50.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M request tokens when a request is above the long-request threshold, directly from OpenAI (official API price)? | $20.00 per 1M tokens | Published | |
| How much does GPT-6 Astra cost per 1M response tokens when a request is above the long-request threshold, directly from OpenAI (official API price)? | $75.00 per 1M tokens | Published | |
| How much does OpenAI GPT-6 Astra cost per 1M cache-read tokens (cache hits) on OpenRouter? | $1.00 per 1M tokens | Published | |
| How much does OpenAI GPT-6 Astra cost per 1M cache-write tokens on OpenRouter? | $12.50 per 1M tokens | Published | |
| How much does OpenAI GPT-6 Astra cost per 1M output tokens on OpenRouter? | $50.00 per 1M tokens | Published | |
| What is the context window of OpenAI GPT-6 Astra on OpenRouter, in tokens? | 1,050,000 tokens | Published | |
| What is the maximum output length of OpenAI GPT-6 Astra on OpenRouter, in tokens? | 128,000 tokens | Published |
History
Same price in all 25 checks since 16 Oct 2026.
- — First check: $10.00 per 1M tokens
- Short-lived or unconfirmed moves are not shown as changes.
The source record lists $0.00001 per token ($10.00 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.00001"
Latest briefings each price change recalculated as a task cost
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Record history — 343 records for 15 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $10.00 per 1M tokens | Published |
| 8 Nov 2026 | $10.00 per 1M tokens | Published |
| 7 Nov 2026 | $10.00 per 1M tokens | Published |
| 6 Nov 2026 | $10.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 272 thousand tokens | Published |
| 8 Nov 2026 | 272 thousand tokens | Published |
| 7 Nov 2026 | 272 thousand tokens | Published |
| 6 Nov 2026 | 272 thousand tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $1.00 per 1M tokens | Published |
| 8 Nov 2026 | $1.00 per 1M tokens | Published |
| 7 Nov 2026 | $1.00 per 1M tokens | Published |
| 6 Nov 2026 | $1.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $2.00 per 1M tokens | Published |
| 8 Nov 2026 | $2.00 per 1M tokens | Published |
| 7 Nov 2026 | $2.00 per 1M tokens | Published |
| 6 Nov 2026 | $2.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $12.50 per 1M tokens | Published |
| 8 Nov 2026 | $12.50 per 1M tokens | Published |
| 7 Nov 2026 | $12.50 per 1M tokens | Published |
| 6 Nov 2026 | $12.50 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $25.00 per 1M tokens | Published |
| 8 Nov 2026 | $25.00 per 1M tokens | Published |
| 7 Nov 2026 | $25.00 per 1M tokens | Published |
| 6 Nov 2026 | $25.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $10.00 per 1M tokens | Published |
| 8 Nov 2026 | $10.00 per 1M tokens | Published |
| 7 Nov 2026 | $10.00 per 1M tokens | Published |
| 6 Nov 2026 | $10.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $50.00 per 1M tokens | Published |
| 8 Nov 2026 | $50.00 per 1M tokens | Published |
| 7 Nov 2026 | $50.00 per 1M tokens | Published |
| 6 Nov 2026 | $50.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $20.00 per 1M tokens | Published |
| 8 Nov 2026 | $20.00 per 1M tokens | Published |
| 7 Nov 2026 | $20.00 per 1M tokens | Published |
| 6 Nov 2026 | $20.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $75.00 per 1M tokens | Published |
| 8 Nov 2026 | $75.00 per 1M tokens | Published |
| 7 Nov 2026 | $75.00 per 1M tokens | Published |
| 6 Nov 2026 | $75.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $1.00 per 1M tokens | Published |
| 8 Nov 2026 | $1.00 per 1M tokens | Published |
| 7 Nov 2026 | $1.00 per 1M tokens | Published |
| 6 Nov 2026 | $1.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $12.50 per 1M tokens | Published |
| 8 Nov 2026 | $12.50 per 1M tokens | Published |
| 7 Nov 2026 | $12.50 per 1M tokens | Published |
| 6 Nov 2026 | $12.50 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $50.00 per 1M tokens | Published |
| 8 Nov 2026 | $50.00 per 1M tokens | Published |
| 7 Nov 2026 | $50.00 per 1M tokens | Published |
| 6 Nov 2026 | $50.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 1,050,000 tokens | Published |
| 8 Nov 2026 | 1,050,000 tokens | Published |
| 7 Nov 2026 | 1,050,000 tokens | Published |
| 6 Nov 2026 | 1,050,000 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 128,000 tokens | Published |
| 8 Nov 2026 | 128,000 tokens | Published |
| 7 Nov 2026 | 128,000 tokens | Published |
| 6 Nov 2026 | 128,000 tokens | Published |
Showing the latest 60 of 343 records; the full history is in data.json and data.csv.