Compare prices for the same model
USD per 1 million uncached text tokens. Each cell lists input / output. Short-context Standard rates; cache, tools, regional fees, taxes and funding fees are excluded.
| Exact model | Official provider | OpenRouter | API429 |
|---|---|---|---|
GPT 5.5gpt-5.5 | $5 / $30Standard; input ≤272,000 tokensSource | $5 / $30Base tier; context overrides applySource | $1.5 / $9Base rate; full conditions below |
GPT 5.6 Lunagpt-5.6-luna | $0.2 / $1.2Standard; input ≤272,000 tokensSource | $0.2 / $1.2Base tier; context overrides applySource | $0.3 / $1.8$0.3 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 5.6 Solgpt-5.6-sol | $4 / $20Cyber models table; input ≤272,000 tokensSource | $2 / $10Base tier; context overrides applySource | $1.5 / $9$1.5 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 5.6 Terragpt-5.6-terra | $2 / $12Standard; input ≤272,000 tokensSource | $2 / $12Base tier; context overrides applySource | $0.75 / $4.5$0.75 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 6 Astragpt-6-astra | $10 / $50Standard; input ≤272,000 tokensSource | $10 / $50Base tier; context overrides applySource | $3 / $15$3 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 6 Lunagpt-6-luna | $0.1 / $0.5Standard; input ≤272,000 tokensSource | $0.1 / $0.5Base tier; context overrides applySource | $0.03 / $0.15$0.03 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 6 Solgpt-6-sol | $2 / $10Standard; input ≤272,000 tokensSource | $2 / $10Base tier; context overrides applySource | $0.6 / $3$0.6 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
GPT 6.1 Solgpt-6.1-sol | $2 / $10Standard; input ≤272,000 tokensSource | $2 / $10Base tier; context overrides applySource | $0.6 / $3$0.6 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive |
OpenRouter amounts are model-list rates, excluding its separately listed platform fees. A missing quote means it was not verified for this comparison; it does not establish that the provider has no such model. Unverified reference figures are not filled with older or inferred prices.
The same workload, three budgets
Example: gpt-6.1-sol, 10 million input and 2 million output tokens across many short-context requests. No cache, tools or extra operations; this is not one 10-million-token prompt.
A changed token mix or context tier changes the result. For actual budgets, add billable reasoning, cache writes and tool use from your usage records.
API pricing and ChatGPT subscriptions
A ChatGPT subscription is not an API budget. Direct API calls use an OpenAI Platform key; gateway calls use a separate key and balance. Compare the same model and token workload rather than a monthly subscription with the price of one response.
Why long context changes the bill
The main table uses short-context rates. For the listed GPT models, prompts above 272,000 input tokens use a separate rate for the entire request: input and cache double, output increases by 1.5×. Full API429 rates appear below. Do not price the first part of a long request at the short-context rate.
Cached input, cache writes, reasoning and hosted tools can change the total. OpenRouter rates are recorded independently: differences from OpenAI remain visible rather than being replaced with the official rate.
When direct access or a gateway fits better
Direct OpenAI access fits teams that need its projects, management features and direct contract. API429 fits a multi-model integration using one key and a unified balance. Matching model IDs do not establish identical support for every tool; check the gateway request contract.
All published OpenAI / GPT rates in API429
These rows come from the live public API429 catalog, including conditional rates. Publication is separate from access under your key. GET /v1/models confirms your permitted models.
| Model | Rate and condition |
|---|---|
GPT 5.5gpt-5.5 | $1.5 / 1,000,000 cache-write input tokens $1.5 / 1,000,000 cached input tokens $1.5 / 1,000,000 input tokens $9 / 1,000,000 output tokens |
GPT 5.6 Lunagpt-5.6-luna | $0.375 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $0.75 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.03 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.06 / 1,000,000 cached input tokens · Context over 272,000 tokens $0.3 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $0.6 / 1,000,000 input tokens · Context over 272,000 tokens $1.8 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $2.7 / 1,000,000 output tokens · Context over 272,000 tokens $3 / 1,000 web-search calls |
GPT 5.6 Solgpt-5.6-sol | $1.875 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $3.75 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.15 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.3 / 1,000,000 cached input tokens · Context over 272,000 tokens $1.5 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $3 / 1,000,000 input tokens · Context over 272,000 tokens $9 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $13.5 / 1,000,000 output tokens · Context over 272,000 tokens $3 / 1,000 web-search calls |
GPT 5.6 Terragpt-5.6-terra | $0.9375 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $1.875 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.075 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.15 / 1,000,000 cached input tokens · Context over 272,000 tokens $0.75 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $1.5 / 1,000,000 input tokens · Context over 272,000 tokens $4.5 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $6.75 / 1,000,000 output tokens · Context over 272,000 tokens $3 / 1,000 web-search calls |
GPT 6 Astragpt-6-astra | $3.75 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $7.5 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.3 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.6 / 1,000,000 cached input tokens · Context over 272,000 tokens $3 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $6 / 1,000,000 input tokens · Context over 272,000 tokens $15 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $22.5 / 1,000,000 output tokens · Context over 272,000 tokens |
GPT 6 Lunagpt-6-luna | $0.0375 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $0.075 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.003 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.006 / 1,000,000 cached input tokens · Context over 272,000 tokens $0.03 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $0.06 / 1,000,000 input tokens · Context over 272,000 tokens $0.15 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $0.225 / 1,000,000 output tokens · Context over 272,000 tokens |
GPT 6 Solgpt-6-sol | $0.75 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $1.5 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.06 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.12 / 1,000,000 cached input tokens · Context over 272,000 tokens $0.6 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $1.2 / 1,000,000 input tokens · Context over 272,000 tokens $3 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $4.5 / 1,000,000 output tokens · Context over 272,000 tokens |
GPT 6.1 Solgpt-6.1-sol | $0.75 / 1,000,000 cache-write input tokens · Context up to 272,000 tokens inclusive $1.5 / 1,000,000 cache-write input tokens · Context over 272,000 tokens $0.03 / 1,000,000 cached input tokens · Context up to 272,000 tokens inclusive $0.06 / 1,000,000 cached input tokens · Context over 272,000 tokens $0.6 / 1,000,000 input tokens · Context up to 272,000 tokens inclusive $1.2 / 1,000,000 input tokens · Context over 272,000 tokens $3 / 1,000,000 output tokens · Context up to 272,000 tokens inclusive $4.5 / 1,000,000 output tokens · Context over 272,000 tokens |
API429 catalog generated: . Public source.
Connect the model and check the result
Create an API429 key and check the permitted model IDs before migrating a workload. Keep the key on your server. Review the request contract and inspect actual usage and charges on a small representative job before increasing volume.
Sources and comparison method
Reference rates checked October 2, 2026. Recheck after a model release, promotion or pricing change. Reference figures are hidden after their review deadline; current API429 prices load from the public catalog. Neither individual contracts nor discounts are inferred.