{ "openapi": "3.1.0", "info": { "title": "DiscountedTokens API", "version": "1.0.0", "description": "Low-cost prepaid model inference for autonomous agents and developers. Independent reseller with OpenAI-, Responses-, and Anthropic-format endpoints.\n\nLowest quoted token-usage estimate for the example below: gpt-6-sol, at US$0.100 input / US$0.500 output per 1M tokens.\n\nExample: 1,000 requests, each with 2,000 billed input tokens and 500 billed output tokens, accrue approximately US$0.45 in token usage. This is not a flat price per request or a guarantee for arbitrary agent tasks. Use reported billed-token counts, not just the visible prompt or answer.\n\nMinimum credit purchase: US$5, card or supported crypto. It becomes your prepaid balance, not a per-request charge. No subscription or free trial.\n\nQuotes checked: 2026-10-15T03:10:03.000Z. Rates can change; retrieve https://discountedtokens.com/api/pricing before budgeting. Reference-only models are not sold through this API.\n\nSuccessful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.", "x-discountedtokens-pricing": { "price_status": "current", "currency": "USD", "unit": "per_million_tokens", "pricing_url": "https://discountedtokens.com/api/pricing", "catalog_url": "https://discountedtokens.com/v1/models", "minimum_credit_purchase_usd": 5, "billing_model": "prepaid_per_token", "free_trial": false, "authorization": "Purchase credits only with operator authorization or an operator-approved budget.", "assumptions": "Examples use the stated billed input/output counts, including any reported system or reasoning tokens. They are token-usage estimates, not a flat price per request or agent task. Extra usage, tools and payment/FX costs are not included.", "price_checked_at": "2026-10-15T03:10:03.000Z", "models": [ { "id": "gpt-5.6-sol", "name": "GPT-5.6 Sol", "input_usd_per_million": 0.25, "output_usd_per_million": 1.5 }, { "id": "gpt-5.6-terra", "name": "GPT-5.6 Terra", "input_usd_per_million": 0.1, "output_usd_per_million": 0.6 }, { "id": "gpt-5.5", "name": "GPT-5.5", "input_usd_per_million": 0.25, "output_usd_per_million": 1.5 }, { "id": "gpt-5.6", "name": "GPT-5.6", "input_usd_per_million": 0.2, "output_usd_per_million": 1 }, { "id": "gpt-6-astra", "name": "GPT-6 Astra", "input_usd_per_million": 0.5, "output_usd_per_million": 2.5 }, { "id": "gpt-6-sol", "name": "GPT-6 Sol", "input_usd_per_million": 0.1, "output_usd_per_million": 0.5 }, { "id": "gpt-6.1-sol", "name": "GPT-6.1 Sol", "input_usd_per_million": 0.1, "output_usd_per_million": 0.5 }, { "id": "codex-auto-review", "name": "Codex Auto Review", "input_usd_per_million": 0.25, "output_usd_per_million": 1.5 } ], "example": { "model": "gpt-6-sol", "requests": 1000, "input_tokens_per_request": 2000, "output_tokens_per_request": 500, "input_usd_per_million": 0.1, "output_usd_per_million": 0.5, "estimated_usage_usd": 0.45 } }, "contact": { "email": "support@discountedtokens.com", "url": "https://discountedtokens.com/contact" }, "termsOfService": "https://discountedtokens.com/terms" }, "servers": [ { "url": "https://discountedtokens.com/v1" } ], "externalDocs": { "description": "Integration documentation", "url": "https://discountedtokens.com/docs" }, "paths": { "/models": { "get": { "operationId": "listModels", "summary": "List available models and live prices", "responses": { "200": { "description": "Model list" } } } }, "/chat/completions": { "post": { "operationId": "createChatCompletion", "summary": "Create an OpenAI-compatible chat completion", "security": [ { "bearerAuth": [] } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "messages" ], "properties": { "model": { "type": "string", "enum": [ "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.5", "gpt-5.6", "gpt-6-astra", "gpt-6-sol", "gpt-6.1-sol", "codex-auto-review" ] }, "messages": { "type": "array", "items": { "type": "object" } }, "max_tokens": { "type": "integer", "minimum": 1 }, "stream": { "type": "boolean" } } } } } }, "responses": { "200": { "description": "Completion", "content": { "application/json": { "schema": { "type": "object", "properties": { "usage": { "$ref": "#/components/schemas/Usage" } } } } } }, "401": { "description": "Invalid key" }, "402": { "description": "Insufficient credits" } } } }, "/responses": { "post": { "operationId": "createResponse", "summary": "Create an OpenAI Responses-compatible response", "security": [ { "bearerAuth": [] } ], "requestBody": { "required": true, "description": "Documented text-only request format. Instructions are prepended as system text; system, developer, user and assistant input text is forwarded, with text blocks flattened. Tools, images, previous-response state and streaming are not implemented by this adapter.", "content": { "application/json": { "schema": { "type": "object", "required": [ "input" ], "additionalProperties": false, "properties": { "model": { "type": "string", "enum": [ "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.5", "gpt-5.6", "gpt-6-astra", "gpt-6-sol", "gpt-6.1-sol", "codex-auto-review" ], "default": "gpt-5.5" }, "input": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object", "required": [ "role", "content" ], "additionalProperties": false, "properties": { "role": { "type": "string", "enum": [ "user", "assistant", "system", "developer" ] }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object", "required": [ "text" ], "additionalProperties": false, "properties": { "type": { "type": "string", "description": "Text-block label, such as text or input_text. Only the text field is forwarded." }, "text": { "type": "string" } } } } ] } } } } ] }, "max_output_tokens": { "type": "integer", "minimum": 1, "maximum": 2000000, "default": 4096, "description": "Proxy validation ceiling only; the upstream model may impose a lower output limit." }, "instructions": { "type": [ "string", "null" ], "description": "Optional system text prepended before input messages." } } } } } }, "responses": { "200": { "description": "Response" } } } }, "/messages": { "post": { "operationId": "createAnthropicMessage", "summary": "Create an Anthropic-compatible message", "security": [ { "bearerAuth": [] }, { "apiKeyAuth": [] } ], "requestBody": { "required": true, "description": "Documented text-only request format. System text and user/assistant messages are forwarded, with text blocks flattened. Tool calls, images and streaming are not implemented by this adapter.", "content": { "application/json": { "schema": { "type": "object", "required": [ "messages" ], "additionalProperties": false, "properties": { "model": { "type": "string", "enum": [ "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.5", "gpt-5.6", "gpt-6-astra", "gpt-6-sol", "gpt-6.1-sol", "codex-auto-review" ], "default": "gpt-5.5" }, "messages": { "type": "array", "items": { "type": "object", "required": [ "role", "content" ], "additionalProperties": false, "properties": { "role": { "type": "string", "enum": [ "user", "assistant" ] }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object", "required": [ "text" ], "additionalProperties": false, "properties": { "type": { "type": "string", "description": "Text-block label, such as text or input_text. Only the text field is forwarded." }, "text": { "type": "string" } } } } ] } } } }, "system": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object", "required": [ "text" ], "additionalProperties": false, "properties": { "type": { "type": "string", "description": "Text-block label, such as text or input_text. Only the text field is forwarded." }, "text": { "type": "string" } } } } ] }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 2000000, "default": 4096, "description": "Proxy validation ceiling only; the upstream model may impose a lower output limit." }, "temperature": { "type": "number" } } } } } }, "responses": { "200": { "description": "Message" } } } } }, "components": { "securitySchemes": { "bearerAuth": { "type": "http", "scheme": "bearer" }, "apiKeyAuth": { "type": "apiKey", "in": "header", "name": "x-api-key" } }, "schemas": { "Usage": { "type": "object", "description": "Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.", "properties": { "prompt_tokens": { "type": "integer" }, "completion_tokens": { "type": "integer" }, "total_tokens": { "type": "integer" }, "reseller_cost_usd": { "type": "string", "description": "Exact metered cost of this request in USD, six decimals." }, "reseller_cost_micros": { "type": "integer", "description": "Exact metered cost in micro-USD (1e-6 USD), before whole-cent deduction." }, "charged_cents": { "type": "integer", "description": "Whole US cents deducted from the prepaid balance for this request; the sub-cent remainder carries to later requests." }, "sell_rate_in_usd": { "type": "number", "description": "Input rate applied, USD per million tokens." }, "sell_rate_out_usd": { "type": "number", "description": "Output rate applied, USD per million tokens." } } } } } }