# Heaven API 模型广场 / Model plaza Verified: 2026-10-18 Canonical: https://ai.heaven.help/model-plaza 仅作价格参考。实际扣费以账户及分组规则为准;可用模型以分组权限和模型列表为准。 Models: 126. Units vary by model; each rate has its own label. Standard paid tier only. Retired models have historical prices, not availability guarantees. ## GPT-6 Astra Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-6-astra Input: $10 (USD per 1M tokens). Cache read: $1 (USD per 1M tokens). Output: $50 (USD per 1M tokens). Cache write: $12.5 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-6.1 Sol Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-6.1-sol Input: $2 (USD per 1M tokens). Cache read: $0.1 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Cache write: $2.5 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-6 Luna Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-6-luna Input: $0.1 (USD per 1M tokens). Cache read: $0.01 (USD per 1M tokens). Output: $0.5 (USD per 1M tokens). Cache write: $0.125 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-6 Sol Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-6-sol Input: $2 (USD per 1M tokens). Cache read: $0.2 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Cache write: $2.5 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.6 Sol Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.6-sol Input: $4 (USD per 1M tokens). Cache read: $0.4 (USD per 1M tokens). Output: $20 (USD per 1M tokens). Cache write: $5 / 1M tokens. Promotional rate guaranteed at least through 2026-11-21; check the official source afterward. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.6 Terra Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.6-terra Input: $2 (USD per 1M tokens). Cache read: $0.2 (USD per 1M tokens). Output: $12 (USD per 1M tokens). Cache write: $2.5 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.6 Luna Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.6-luna Input: $0.2 (USD per 1M tokens). Cache read: $0.02 (USD per 1M tokens). Output: $1.2 (USD per 1M tokens). Cache write: $0.25 / 1M tokens. Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.5 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.5 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $30 (USD per 1M tokens). Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.5 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.5-pro Input: $30 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $180 (USD per 1M tokens). Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.4 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.4 Input: $2.5 (USD per 1M tokens). Cache read: $0.25 (USD per 1M tokens). Output: $15 (USD per 1M tokens). Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.4 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.4-pro Input: $30 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $180 (USD per 1M tokens). Up to 272K input tokens Over 272K: input and cache ×2, output ×1.5 for the entire request. Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.4 Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.4-mini Input: $0.75 (USD per 1M tokens). Cache read: $0.075 (USD per 1M tokens). Output: $4.5 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.4 Nano Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.4-nano Input: $0.2 (USD per 1M tokens). Cache read: $0.02 (USD per 1M tokens). Output: $1.25 (USD per 1M tokens). Provider shutdown: 2027-04-01. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.3 Codex Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5.3-codex Input: $1.75 (USD per 1M tokens). Cache read: $0.175 (USD per 1M tokens). Output: $14 (USD per 1M tokens). Provider shutdown: 2027-04-01. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.2 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.2 Input: $1.75 (USD per 1M tokens). Cache read: $0.175 (USD per 1M tokens). Output: $14 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.2 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.2-pro Input: $21 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $168 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5.1 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5.1 Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Provider shutdown: 2027-04-01. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5 Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5 Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5-mini Input: $0.25 (USD per 1M tokens). Cache read: $0.025 (USD per 1M tokens). Output: $2 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5 Nano Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5-nano Input: $0.05 (USD per 1M tokens). Cache read: $0.005 (USD per 1M tokens). Output: $0.4 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-5 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-5-pro Input: $15 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $120 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4.1 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4.1 Input: $2 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $8 (USD per 1M tokens). Provider shutdown: 2027-01-14. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4.1 Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4.1-mini Input: $0.4 (USD per 1M tokens). Cache read: $0.1 (USD per 1M tokens). Output: $1.6 (USD per 1M tokens). Provider shutdown: 2027-01-14. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4.1 Nano Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4.1-nano Input: $0.1 (USD per 1M tokens). Cache read: $0.025 (USD per 1M tokens). Output: $0.4 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4o Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4o Input: $2.5 (USD per 1M tokens). Cache read: $1.25 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Provider shutdown: 2027-01-14. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4o Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4o-mini Input: $0.15 (USD per 1M tokens). Cache read: $0.075 (USD per 1M tokens). Output: $0.6 (USD per 1M tokens). Provider shutdown: 2027-01-14. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o3 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o3 Input: $2 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $8 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o3 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o3-pro Input: $20 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $80 (USD per 1M tokens). Provider shutdown: 2026-12-11. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o3 Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o3-mini Input: $1.1 (USD per 1M tokens). Cache read: $0.55 (USD per 1M tokens). Output: $4.4 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o4 Mini Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o4-mini Input: $1.1 (USD per 1M tokens). Cache read: $0.275 (USD per 1M tokens). Output: $4.4 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o1 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o1 Input: $15 (USD per 1M tokens). Cache read: $7.5 (USD per 1M tokens). Output: $60 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## o1 Pro Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): o1-pro Input: $150 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $600 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## Chat Latest Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): chat-latest Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $30 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4 Turbo Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4-turbo Input: $10 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $30 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4 Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-4 Input: $30 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $60 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-3.5 Turbo Provider: OpenAI Category: Text and reasoning Reference ID (not a gateway availability guarantee): gpt-3.5-turbo Input: $0.5 (USD per 1M tokens). Cache read: — (USD per 1M tokens). Output: $1.5 (USD per 1M tokens). Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## Claude Fable 5.1 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-fable-5-1 Input: $10 (USD per 1M tokens). Cache read: $0.25 (USD per 1M tokens). Output: $50 (USD per 1M tokens). Cache write: $12.5 (5 minutes); $20 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 5.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-5-5 Input: $4 (USD per 1M tokens). Cache read: $0.2 (USD per 1M tokens). Output: $20 (USD per 1M tokens). Cache write: $5 (5 minutes); $8 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Sonnet 5.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-sonnet-5-5 Input: $2 (USD per 1M tokens). Cache read: $0.1 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Cache write: $2.5 (5 minutes); $4 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Haiku 5.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-haiku-5-5 Input: $0.1 (USD per 1M tokens). Cache read: $0.01 (USD per 1M tokens). Output: $0.5 (USD per 1M tokens). Cache write: $0.125 (5 minutes); $0.2 (1 hour) / 1M tokens. Up to 100K input tokens. Above 100K, all listed token rates ×5. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Fable 5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-fable-5 Input: $10 (USD per 1M tokens). Cache read: $1 (USD per 1M tokens). Output: $50 (USD per 1M tokens). Cache write: $12.5 (5 minutes); $20 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Mythos 5.1 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-mythos-5-1 Input: $10 (USD per 1M tokens). Cache read: $0.25 (USD per 1M tokens). Output: $50 (USD per 1M tokens). Cache write: $12.5 (5 minutes); $20 (1 hour) / 1M tokens. Restricted access; provider approval may be required. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Mythos 5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-mythos-5 Input: $10 (USD per 1M tokens). Cache read: $1 (USD per 1M tokens). Output: $50 (USD per 1M tokens). Cache write: $12.5 (5 minutes); $20 (1 hour) / 1M tokens. Restricted access; provider approval may be required. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-5 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $25 (USD per 1M tokens). Cache write: $6.25 (5 minutes); $10 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 4.8 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4-8 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $25 (USD per 1M tokens). Cache write: $6.25 (5 minutes); $10 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 4.7 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4-7 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $25 (USD per 1M tokens). Cache write: $6.25 (5 minutes); $10 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 4.6 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4-6 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $25 (USD per 1M tokens). Cache write: $6.25 (5 minutes); $10 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 4.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4-5 Related IDs: claude-opus-4-5-20251101 Input: $5 (USD per 1M tokens). Cache read: $0.5 (USD per 1M tokens). Output: $25 (USD per 1M tokens). Cache write: $6.25 (5 minutes); $10 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Sonnet 5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-sonnet-5 Input: $2 (USD per 1M tokens). Cache read: $0.2 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Cache write: $2.5 (5 minutes); $4 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Sonnet 4.6 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-sonnet-4-6 Input: $3 (USD per 1M tokens). Cache read: $0.3 (USD per 1M tokens). Output: $15 (USD per 1M tokens). Cache write: $3.75 (5 minutes); $6 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Sonnet 4.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-sonnet-4-5 Related IDs: claude-sonnet-4-5-20250929 Input: $3 (USD per 1M tokens). Cache read: $0.3 (USD per 1M tokens). Output: $15 (USD per 1M tokens). Cache write: $3.75 (5 minutes); $6 (1 hour) / 1M tokens. Legacy long-context requests may have separate pricing; see the official source. Provider shutdown: 2026-11-30. Status as of 2026-10-18: Deprecated. Source: https://platform.claude.com/docs/en/about-claude/model-deprecations Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Haiku 4.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-haiku-4-5 Related IDs: claude-haiku-4-5-20251001 Input: $1 (USD per 1M tokens). Cache read: $0.1 (USD per 1M tokens). Output: $5 (USD per 1M tokens). Cache write: $1.25 (5 minutes); $2 (1 hour) / 1M tokens. Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Gemini 4 Argon Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-4-argon Input: $2 (USD per 1M tokens). Cache read: $0.1 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Gemini text output includes thinking tokens. Implicit caching only; no explicit cache writes. Price valid through 2026-11-30; from 2026-12-01: input $4, cache read $0.2, output $20 / 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.8 Flash Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3.8-flash Input: $0.75 (USD per 1M tokens). Cache read: $0.075 (USD per 1M tokens). Output: $3.75 (USD per 1M tokens). Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Price valid through 2026-12-31; from 2027-01-01: input $1.5, cache read $0.15, output $7.5 / 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.6 Flash Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3.6-flash Input: $0.75 (USD per 1M tokens). Cache read: $0.075 (USD per 1M tokens). Output: $3.75 (USD per 1M tokens). Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Price valid through 2026-12-31; from 2027-01-01: input $1.5, cache read $0.15, output $7.5 / 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.5 Flash-Lite Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3.5-flash-lite Input: $0.3 (USD per 1M tokens). Cache read: $0.03 (USD per 1M tokens). Output: $2.5 (USD per 1M tokens). Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Flash-Lite Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3.1-flash-lite Input: $0.25 (USD per 1M tokens). Cache read: $0.025 (USD per 1M tokens). Output: $1.5 (USD per 1M tokens). Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Audio input: $0.5; audio cache read: $0.05 / 1M tokens. Provider shutdown: 2027-05-07. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Pro Preview Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3.1-pro-preview Related IDs: gemini-3.1-pro-preview-customtools Input: $2 (USD per 1M tokens). Cache read: $0.2 (USD per 1M tokens). Output: $12 (USD per 1M tokens). Up to 200K input tokens; above 200K, input and cache ×2, output ×1.5. Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3 Flash Preview Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-3-flash-preview Input: $0.5 (USD per 1M tokens). Cache read: $0.05 (USD per 1M tokens). Output: $3 (USD per 1M tokens). Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Audio input: $1; audio cache read: $0.1 / 1M tokens. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Pro Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-2.5-pro Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Gemini 2.5 access is limited to projects with prior usage. Up to 200K input tokens; above 200K, input and cache ×2, output ×1.5. Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Flash Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-2.5-flash Input: $0.3 (USD per 1M tokens). Cache read: $0.03 (USD per 1M tokens). Output: $2.5 (USD per 1M tokens). Gemini 2.5 access is limited to projects with prior usage. Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Audio input: $1; audio cache read: $0.1 / 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Flash-Lite Provider: Google Category: Text and reasoning Reference ID (not a gateway availability guarantee): gemini-2.5-flash-lite Input: $0.1 (USD per 1M tokens). Cache read: $0.01 (USD per 1M tokens). Output: $0.4 (USD per 1M tokens). Gemini 2.5 access is limited to projects with prior usage. Gemini text output includes thinking tokens. Cache storage is billed separately; see the official source. Audio input: $0.3; audio cache read: $0.03 / 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## GPT Image 2.5 Sunburst Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-2.5-sunburst Text input: $5 (USD per 1M tokens). Text cache read: $1.25 (USD per 1M tokens). Image input: $8 (USD per 1M tokens). Image cache read: $2 (USD per 1M tokens). Image output: $30 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Official price source: https://developers.openai.com/api/docs/pricing ## GPT Image 2.5 Flare Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-2.5-flare Text input: $5 (USD per 1M tokens). Text cache read: $1.25 (USD per 1M tokens). Image input: $8 (USD per 1M tokens). Image cache read: $2 (USD per 1M tokens). Image output: $30 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Official price source: https://developers.openai.com/api/docs/pricing ## GPT Image 2 Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-2 Use the official calculator for this model; no single per-image rate is quoted here. Official price source: https://developers.openai.com/api/docs/models/gpt-image-2 ## GPT Image 1.5 Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-1.5 Text input: $5 (USD per 1M tokens). Text cache read: $1.25 (USD per 1M tokens). Text output: $10 (USD per 1M tokens). Image input: $8 (USD per 1M tokens). Image cache read: $2 (USD per 1M tokens). Image output: $32 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Provider shutdown: 2026-12-01. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-image-1.5 ## GPT Image 1 Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-1 Text input: $5 (USD per 1M tokens). Text cache read: $1.25 (USD per 1M tokens). Image input: $10 (USD per 1M tokens). Image cache read: $2.5 (USD per 1M tokens). Image output: $40 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Provider shutdown: 2026-10-23. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-image-1 ## GPT Image 1 Mini Provider: OpenAI Category: Image generation Reference ID (not a gateway availability guarantee): gpt-image-1-mini Text input: $2 (USD per 1M tokens). Text cache read: $0.2 (USD per 1M tokens). Image input: $2.5 (USD per 1M tokens). Image cache read: $0.25 (USD per 1M tokens). Image output: $8 (USD per 1M tokens). Provider shutdown: 2026-12-01. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-image-1-mini ## Nano Banana 2.1 Provider: Google Category: Image generation Reference ID (not a gateway availability guarantee): gemini-nano-banana-2.1 Input: $1.5 (USD per 1M tokens). Text output: $7.5 (USD per 1M tokens). Image output: $30 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Flash Image · Nano Banana 2 Provider: Google Category: Image generation Reference ID (not a gateway availability guarantee): gemini-3.1-flash-image Input: $0.5 (USD per 1M tokens). Text output: $3 (USD per 1M tokens). Image output: $60 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Flash Lite Image · Nano Banana 2 Lite Provider: Google Category: Image generation Reference ID (not a gateway availability guarantee): gemini-3.1-flash-lite-image Input: $0.25 (USD per 1M tokens). Text output: $1.5 (USD per 1M tokens). Image output: $30 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3 Pro Image · Nano Banana Pro Provider: Google Category: Image generation Reference ID (not a gateway availability guarantee): gemini-3-pro-image Input: $2 (USD per 1M tokens). Text output: $12 (USD per 1M tokens). Image output: $120 (USD per 1M tokens). Image cost depends on size, quality and input tokens; use the official calculator. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## GPT Realtime 2.1 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-2.1 Audio input: $32 (USD per 1M tokens). Audio cache read: $0.4 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $4 (USD per 1M tokens). Text cache read: $0.4 (USD per 1M tokens). Text output: $24 (USD per 1M tokens). Image input: $5 (USD per 1M tokens). Image cache read: $0.5 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime 2.1 Mini Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-2.1-mini Audio input: $10 (USD per 1M tokens). Audio cache read: $0.3 (USD per 1M tokens). Audio output: $20 (USD per 1M tokens). Text input: $0.6 (USD per 1M tokens). Text cache read: $0.06 (USD per 1M tokens). Text output: $2.4 (USD per 1M tokens). Image input: $0.8 (USD per 1M tokens). Image cache read: $0.08 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime 2 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-2 Audio input: $32 (USD per 1M tokens). Audio cache read: $0.4 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $4 (USD per 1M tokens). Text cache read: $0.4 (USD per 1M tokens). Text output: $24 (USD per 1M tokens). Image input: $5 (USD per 1M tokens). Image cache read: $0.5 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime 1.5 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-1.5 Audio input: $32 (USD per 1M tokens). Audio cache read: $0.4 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $4 (USD per 1M tokens). Text cache read: $0.4 (USD per 1M tokens). Text output: $16 (USD per 1M tokens). Image input: $5 (USD per 1M tokens). Image cache read: $0.5 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime Audio input: $32 (USD per 1M tokens). Audio cache read: $0.4 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $4 (USD per 1M tokens). Text cache read: $0.4 (USD per 1M tokens). Text output: $16 (USD per 1M tokens). Provider shutdown: 2027-01-20. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime Mini Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-mini Audio input: $10 (USD per 1M tokens). Audio cache read: $0.3 (USD per 1M tokens). Audio output: $20 (USD per 1M tokens). Text input: $0.6 (USD per 1M tokens). Text cache read: $0.06 (USD per 1M tokens). Text output: $2.4 (USD per 1M tokens). Provider shutdown: 2027-01-20. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT Audio 1.5 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-audio-1.5 Audio input: $32 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $2.5 (USD per 1M tokens). Text output: $10 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Audio Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-audio Audio input: $32 (USD per 1M tokens). Audio output: $64 (USD per 1M tokens). Text input: $2.5 (USD per 1M tokens). Text output: $10 (USD per 1M tokens). Provider shutdown: 2027-01-20. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT Audio Mini Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-audio-mini Audio input: $10 (USD per 1M tokens). Audio output: $20 (USD per 1M tokens). Text input: $0.6 (USD per 1M tokens). Text output: $2.4 (USD per 1M tokens). Provider shutdown: 2027-01-20. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4o Mini TTS Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-4o-mini-tts Text input: $0.6 (USD per 1M tokens). Audio output: $12 (USD per 1M tokens). Provider shutdown: 2027-01-06. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## TTS-1 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): tts-1 Text input: $15 (USD per 1M characters). Provider shutdown: 2027-01-06. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## TTS-1 HD Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): tts-1-hd Text input: $30 (USD per 1M characters). Provider shutdown: 2027-01-06. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT Transcribe Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-transcribe Transcription: $0.0045 (USD per minute). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Live Transcribe Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-live-transcribe Transcription: $0.017 (USD per minute). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime Whisper Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-whisper Transcription: $0.017 (USD per minute). Official price source: https://developers.openai.com/api/docs/pricing ## GPT Realtime Translate Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-realtime-translate Audio and speech: $0.034 (USD per minute). Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4o Transcribe Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-4o-transcribe Input: $2.5 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Estimated cost: $0.006 (USD per minute). Provider shutdown: 2027-02-26. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## GPT-4o Mini Transcribe Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-4o-mini-transcribe Input: $1.25 (USD per 1M tokens). Output: $5 (USD per 1M tokens). Estimated cost: $0.003 (USD per minute). Provider shutdown: 2027-02-26. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/pricing ## Whisper-1 Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): whisper-1 Transcription: $0.006 (USD per minute). Provider shutdown: 2027-02-26. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/whisper-1 ## GPT-4o Transcribe Diarize Provider: OpenAI Category: Audio and speech Reference ID (not a gateway availability guarantee): gpt-4o-transcribe-diarize Audio input: $2.5 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Provider shutdown: 2027-02-26. Status as of 2026-10-18: Deprecated. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-4o-transcribe-diarize ## Gemini 3.8 Live Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.8-live Text input: $0.75 (USD per 1M tokens). Text output: $4.5 (USD per 1M tokens). Audio input: $3 (USD per 1M tokens). Audio output: $12 (USD per 1M tokens). Image / video input: $1 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.8 Live Extended Thinking Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.8-live-extended-thinking Text input: $0.75 (USD per 1M tokens). Text output: $4.5 (USD per 1M tokens). Audio input: $3 (USD per 1M tokens). Audio output: $12 (USD per 1M tokens). Image / video input: $1 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Flash Live Preview Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.1-flash-live-preview Text input: $0.75 (USD per 1M tokens). Text output: $4.5 (USD per 1M tokens). Audio input: $3 (USD per 1M tokens). Audio output: $12 (USD per 1M tokens). Image / video input: $1 (USD per 1M tokens). Provider shutdown: 2026-11-17. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.5 Live Translate Preview Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.5-live-translate-preview Audio input: $3.5 (USD per 1M tokens). Audio output: $21 (USD per 1M tokens). Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.5 Transcribe Live Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.5-transcribe-live Audio input: $3.5 (USD per 1M tokens). Text output: $21 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.5 Transcribe Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.5-transcribe Audio input: $2 (USD per 1M tokens). Text output: $12 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.8 Flash TTS Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.8-flash-tts Text input: $0.5 (USD per 1M tokens). Audio output: $9 (USD per 1M tokens). Through 2026-12-31; from 2027-01-01, text input $1 and audio output $18 per 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.8 Flash-Lite TTS Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.8-flash-lite-tts Text input: $0.5 (USD per 1M tokens). Audio output: $6 (USD per 1M tokens). Through 2026-12-31; from 2027-01-01, text input $1 and audio output $12 per 1M tokens. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 3.1 Flash TTS Preview Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-3.1-flash-tts-preview Text input: $1 (USD per 1M tokens). Audio output: $20 (USD per 1M tokens). Provider shutdown: 2026-11-17. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Flash Native Audio Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-2.5-flash-native-audio-preview-12-2025 Text input: $0.5 (USD per 1M tokens). Text output: $2 (USD per 1M tokens). Audio / video input: $3 (USD per 1M tokens). Audio output: $12 (USD per 1M tokens). Provider shutdown: 2026-11-17. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Flash Preview TTS Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-2.5-flash-preview-tts Text input: $0.5 (USD per 1M tokens). Audio output: $10 (USD per 1M tokens). Provider shutdown: 2026-11-17. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini 2.5 Pro Preview TTS Provider: Google Category: Audio and speech Reference ID (not a gateway availability guarantee): gemini-2.5-pro-preview-tts Text input: $1 (USD per 1M tokens). Audio output: $20 (USD per 1M tokens). Provider shutdown: 2026-11-17. Status as of 2026-10-18: Deprecated. Source: https://ai.google.dev/gemini-api/docs/deprecations Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Veo 3.1 Provider: Google Category: Video generation Reference ID (not a gateway availability guarantee): veo-3.1-generate-preview 720p / 1080p: $0.4 (USD per second). 4K: $0.6 (USD per second). Video prices include audio. Only successful generations are charged by Google. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Veo 3.1 Fast Provider: Google Category: Video generation Reference ID (not a gateway availability guarantee): veo-3.1-fast-generate-preview 720p: $0.1 (USD per second). 1080p: $0.12 (USD per second). 4K: $0.3 (USD per second). Video prices include audio. Only successful generations are charged by Google. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Veo 3.1 Lite Provider: Google Category: Video generation Reference ID (not a gateway availability guarantee): veo-3.1-lite-generate-preview 720p: $0.05 (USD per second). 1080p: $0.08 (USD per second). Video prices include audio. Only successful generations are charged by Google. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini Omni Flash Provider: Google Category: Video generation Reference ID (not a gateway availability guarantee): gemini-omni-1.1-flash Input: $1.5 (USD per 1M tokens). Text output: $9 (USD per 1M tokens). Video output: $17.5 (USD per 1M tokens). Video output is token-billed; approximately $0.10 per second at 720p, plus input and text output. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Gemini Omni Flash Preview Provider: Google Category: Video generation Reference ID (not a gateway availability guarantee): gemini-omni-flash-preview Input: $1.5 (USD per 1M tokens). Text output: $9 (USD per 1M tokens). Video output: $17.5 (USD per 1M tokens). Video output is token-billed; approximately $0.10 per second at 720p, plus input and text output. Preview model. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Text Embedding 3 Small Provider: OpenAI Category: Embeddings Reference ID (not a gateway availability guarantee): text-embedding-3-small Text input: $0.02 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/models/text-embedding-3-small ## Text Embedding 3 Large Provider: OpenAI Category: Embeddings Reference ID (not a gateway availability guarantee): text-embedding-3-large Text input: $0.13 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/models/text-embedding-3-large ## Text Embedding Ada 002 Provider: OpenAI Category: Embeddings Reference ID (not a gateway availability guarantee): text-embedding-ada-002 Text input: $0.1 (USD per 1M tokens). Official price source: https://developers.openai.com/api/docs/models/text-embedding-ada-002 ## Gemini Embedding 2 Provider: Google Category: Embeddings Reference ID (not a gateway availability guarantee): gemini-embedding-2 Text input: $0.2 (USD per 1M tokens). Image input: $0.45 (USD per 1M tokens). Audio input: $6.5 (USD per 1M tokens). Video input: $12 (USD per 1M tokens). Official price source: https://ai.google.dev/gemini-api/docs/pricing ## GPT-5.2 Codex Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5.2-codex Input: $1.75 (USD per 1M tokens). Cache read: $0.175 (USD per 1M tokens). Output: $14 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-07-23. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-5.2-codex ## GPT-5.1 Codex Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5.1-codex Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-07-23. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-5.1-codex ## GPT-5.1 Codex Max Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5.1-codex-max Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-07-23. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-5.1-codex-max ## GPT-5.1 Codex Mini Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5.1-codex-mini Input: $0.25 (USD per 1M tokens). Cache read: $0.025 (USD per 1M tokens). Output: $2 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-07-23. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini ## GPT-5 Codex Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): gpt-5-codex Input: $1.25 (USD per 1M tokens). Cache read: $0.125 (USD per 1M tokens). Output: $10 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-07-23. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/gpt-5-codex ## Codex Mini Latest Provider: OpenAI Category: Coding Reference ID (not a gateway availability guarantee): codex-mini-latest Input: $1.5 (USD per 1M tokens). Cache read: $0.375 (USD per 1M tokens). Output: $6 (USD per 1M tokens). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-02-12. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/codex-mini-latest ## Claude Opus 4.1 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4-1 Input: $15 (USD per 1M tokens). Cache read: $1.5 (USD per 1M tokens). Output: $75 (USD per 1M tokens). Cache write: $18.75 (5 minutes); $30 (1 hour) / 1M tokens. Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-08-05. Status as of 2026-10-18: Retired. Source: https://platform.claude.com/docs/en/about-claude/model-deprecations Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Opus 4 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-opus-4 Input: $15 (USD per 1M tokens). Cache read: $1.5 (USD per 1M tokens). Output: $75 (USD per 1M tokens). Cache write: $18.75 (5 minutes); $30 (1 hour) / 1M tokens. Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-06-15. Status as of 2026-10-18: Retired. Source: https://platform.claude.com/docs/en/about-claude/model-deprecations Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Sonnet 4 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-sonnet-4 Input: $3 (USD per 1M tokens). Cache read: $0.3 (USD per 1M tokens). Output: $15 (USD per 1M tokens). Cache write: $3.75 (5 minutes); $6 (1 hour) / 1M tokens. Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-06-15. Status as of 2026-10-18: Retired. Source: https://platform.claude.com/docs/en/about-claude/model-deprecations Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Claude Haiku 3.5 Provider: Anthropic Category: Text and reasoning Reference ID (not a gateway availability guarantee): claude-3-5-haiku Input: $0.8 (USD per 1M tokens). Cache read: $0.08 (USD per 1M tokens). Output: $4 (USD per 1M tokens). Cache write: $1 (5 minutes); $1.6 (1 hour) / 1M tokens. Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-02-19. Status as of 2026-10-18: Retired. Source: https://platform.claude.com/docs/en/about-claude/model-deprecations Official price source: https://platform.claude.com/docs/en/about-claude/pricing ## Gemini 2.5 Flash Image · Nano Banana Provider: Google Category: Image generation Reference ID (not a gateway availability guarantee): gemini-2.5-flash-image Input: $0.3 (USD per 1M tokens). Image output: $0.039 (USD per image). Official pricing and deprecation pages show conflicting retirement dates; confirm with Google before use. Official price source: https://ai.google.dev/gemini-api/docs/pricing ## Sora 2 Provider: OpenAI Category: Video generation Reference ID (not a gateway availability guarantee): sora-2 720p: $0.1 (USD per second). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-09-24. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/sora-2 ## Sora 2 Pro Provider: OpenAI Category: Video generation Reference ID (not a gateway availability guarantee): sora-2-pro 720p: $0.3 (USD per second). 1792 × 1024: $0.5 (USD per second). 1080p: $0.7 (USD per second). Historical prices only; this model has been retired by the provider. Provider shutdown: 2026-09-24. Status as of 2026-10-18: Retired. Source: https://developers.openai.com/api/docs/deprecations Official price source: https://developers.openai.com/api/docs/models/sora-2-pro ## 这里的价格就是我的实际扣费吗? 不是。这里展示厂商官方 API 参考价。你的账户与分组扣费规则继续生效,实际用量和扣费请在控制台核对。 ## 这里列出的模型都能直接调用吗? 这是参考目录,不是实时可用清单。先确认分组权限和模型列表,再按接入教程选择模型 ID、协议与地址。 ## 这些价格包含哪些费用? 请按卡片单位比较:文本/图像/音频/视频 Token、字符、张、分钟或秒。展示标准付费 API 价格,不含 Batch、Flex、Fast、区域附加费、税费及工具费用。已停用模型仅保留历史参考,以官方来源为准。