WORKLOAD INPUT
Request assumptions.
Direct token charges only. Tool calls, storage, regional pricing and non-Standard tiers are excluded.
MODEL ECONOMICS / PRIMARY-SOURCE VERIFIED 2026-11-10
AI Model Pricing & API Cost Comparison
One source-backed view of Standard API pricing and core limits across frontier and specialist models. Native billing units remain explicit; incompatible units are never forced into a single rate.
PRICING DATABASE
Compare the published baseline.
Rates below reflect the catalog's verified Standard period in each model's native billing basis. Model-specific long-context or scheduled-rate changes are called out in the model row.
| Model | Provider | Context | Max output | Primary rate | Cached rate | Output rate | Source |
|---|---|---|---|---|---|---|---|
| GPT-6 Astra gpt-6-astra Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× output | OpenAI | 1,050,000tokens | 128,000tokens | $10.00 | $1.00 | $50.00 | Official ↗ |
| GPT-6 Sol gpt-6-sol Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× output | OpenAI | 1,050,000tokens | 128,000tokens | $2.00 | $0.20 | $10.00 | Official ↗ |
| GPT-6 Luna gpt-6-luna Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× output | OpenAI | 1,050,000tokens | 128,000tokens | $0.10 | $0.01 | $0.50 | Official ↗ |
| GPT-5.6 Sol gpt-5.6-sol Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× outputCurrent $4/$20 Standard rates are promotional through November 30, 2026 (provider notice checked November 10, 2026). | OpenAI | 1,050,000tokens | 128,000tokens | $4.00 | $0.40 | $20.00 | Official ↗ |
| GPT-5.6 Terra gpt-5.6-terra Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× output | OpenAI | 1,050,000tokens | 128,000tokens | $2.00 | $0.20 | $12.00 | Official ↗ |
| GPT-5.6 Luna gpt-5.6-luna Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× output | OpenAI | 1,050,000tokens | 128,000tokens | $0.20 | $0.02 | $1.20 | Official ↗ |
| Claude Fable 5.1 claude-fable-5-1 Pricing basis: per 1 million tokens | Anthropic | 1,000,000tokens | 128,000tokens | $10.00 | $0.25 | $50.00 | Official ↗ |
| Claude Opus 5.5 claude-opus-5-5 Pricing basis: per 1 million tokens | Anthropic | 1,000,000tokens | 128,000tokens | $4.00 | $0.20 | $20.00 | Official ↗ |
| Claude Sonnet 5 claude-sonnet-5 Pricing basis: per 1 million tokens | Anthropic | 1,000,000tokens | 128,000tokens | $2.00 | $0.20 | $10.00 | Official ↗ |
| Claude Haiku 4.5 claude-haiku-4-5-20251001 Pricing basis: per 1 million tokens | Anthropic | 200,000tokens | 64,000tokens | $1.00 | $0.10 | $5.00 | Official ↗ |
| Gemini 3.8 Flash gemini-3.8-flash Pricing basis: per 1 million tokensScheduled Standard pricing change from 2027-01-01; see the model record for native billing dimensions.Introductory Standard pricing applies through December 31, 2026; higher Standard pricing starts January 1, 2027. | 1,048,576tokens | 65,536tokens | $0.75 | $0.075 | $3.75 | Official ↗ | |
| Grok 4.7 grok-4.7 Pricing basis: per 1 million tokensLong context > 200,000: 2× input/cache · 2× outputxAI documents no separate text output limit for Grok 4.7. | xAI | 500,000tokens | No separate limit | $2.00 | $0.50 | $6.00 | Official ↗ |
| Grok 4.6 grok-4.6 Pricing basis: per 1 million tokensLong context > 200,000: 2× input/cache · 2× outputxAI documents no separate text output limit for Grok 4.6. | xAI | 500,000tokens | No separate limit | $2.00 | $0.50 | $6.00 | Official ↗ |
| Grok 4.3 grok-4.3 Pricing basis: per 1 million tokensLong context > 200,000: 2× input/cache · 2× outputxAI does not publish a separate text output cap on the cited model page. | xAI | 1,000,000tokens | Not published | $1.25 | $0.20 | $2.50 | Official ↗ |
| Gemini 3.7 Flash gemini-3.7-flash Pricing basis: per 1 million tokensScheduled Standard pricing change from 2027-01-01; see the model record for native billing dimensions.Gemini 3.7 Flash is a stable, generally available model and remains fully supported, while Gemini 3.8 Flash is the newer Flash generation. | 1,048,576tokens | 65,536tokens | $0.75 | $0.075 | $3.75 | Official ↗ | |
| Llama 4 Scout llama-4-scout Pricing status: not-publishedPricing basis: per 1 million tokensMeta publishes model specifications and open-weight access, but no directly comparable provider Standard paid token rate is stored in this catalog. | Meta | 10,000,000tokens | Not published | Not published | — | — | Official ↗ |
| Llama 4 Maverick llama-4-maverick Pricing status: not-publishedPricing basis: per 1 million tokensMeta publishes model specifications and open-weight access, but no directly comparable provider Standard paid token rate is stored in this catalog. | Meta | 1,000,000tokens | Not published | Not published | — | — | Official ↗ |
| DeepSeek V4.1 Flash deepseek-flash Pricing status: official-paidPricing basis: per 1 million tokensDeepSeek publishes time-variable peak and off-peak USD token rates rather than one fixed Standard rate. | DeepSeek | 1,048,576tokens | 393,216tokens | Not published | — | — | Official ↗ |
| Mistral Small 4 mistral-small-2603 Pricing basis: per 1 million tokensMistral publishes the context window as 256k tokens; SXF stores this as 256,000 for normalized numeric filtering. | Mistral AI | 256,000tokens | Not published | $0.15 | $0.015 | $0.60 | Official ↗ |
| Mistral Medium 3.5 mistral-medium-3-5 Pricing basis: per 1 million tokensMistral publishes the context window as 256k tokens; SXF stores this as 256,000 for normalized numeric filtering. | Mistral AI | 256,000tokens | Not published | $1.50 | $0.15 | $7.50 | Official ↗ |
| Qwen3.8 Max qwen3.8-max Pricing basis: per 1 million tokensSXF stores the Global list price; Alibaba Cloud publishes separate pricing for some regional scopes. | Alibaba Cloud | 1,000,000tokens | 131,072tokens | $1.65 | $0.206 | $4.951 | Official ↗ |
| Command A+ command-a-plus-05-2026 Pricing status: free-previewPricing basis: per 1 million tokensCohere documents Command A+ as free through standard API rate limits for both trial and production keys. | Cohere | 128,000tokens | 64,000tokens | Not published | — | — | Official ↗ |
| Amazon Nova 2 Lite amazon.nova-2-lite-v1:0 Pricing basis: per 1 million tokensAmazon Bedrock documents Standard pay-per-token access, but pricing can vary by routing and region. | Amazon | 1,000,000tokens | 64,000tokens | $0.30 | — | $2.50 | Official ↗ |
| OCR 4.1 mistral-ocr-4-1 Pricing basis: per pageMistral documents OCR 4.1 as GA Premier and the latest OCR service in its Document AI stack. | Mistral AI | Not published | Not published | $0.004 per page | — | — | Official ↗ |
| Voxtral Mini Transcribe 2 voxtral-mini-2602 Pricing basis: per minuteMistral documents the model as GA Premier v26.02 and optimized for transcription purposes only. | Mistral AI | Not published | Not published | $0.003 per minute | — | — | Official ↗ |
| Rerank 4 Pro rerank-v4.0-pro Pricing status: not-publishedPricing basis: per search unitCohere lists rerank-v4.0-pro as a latest Rerank model and recommends it for state-of-the-art quality and complex use cases. | Cohere | 32,768tokens | Not published | Not published · per search unit | — | — | Official ↗ |
| Codestral codestral-2508 Pricing basis: per 1 million tokensCodestral v25.08 is the current GA Premier code-completion model; the older v25.01 model is retired. | Mistral AI | 128,000tokens | Not published | $0.30 | $0.03 | $0.90 | Official ↗ |
| Codestral Embed codestral-embed-2505 Pricing basis: per 1 million tokensCodestral Embed is GA Premier v25.05 with an 8k context window and an embeddings API endpoint. | Mistral AI | 8,000tokens | Not published | $0.15 | $0.015 | — | Official ↗ |
| GPT-Live 1 gpt-live-1 Pricing basis: per minuteVoice sessions are billed per second at the published per-minute rate; backend model and tool usage is billed separately. | OpenAI | Not published | Not published | $0.05 per minute | — | — | Official ↗ |
| GPT-Live-Transcribe gpt-live-transcribe Pricing basis: per minute | OpenAI | Not published | Not published | $0.017 per minute | — | — | Official ↗ |
| GPT-Transcribe gpt-transcribe Pricing basis: per minute | OpenAI | Not published | Not published | $0.0045 per minute | — | — | Official ↗ |
| Mistral Large 3 mistral-large-2512 Pricing basis: per 1 million tokens | Mistral AI | 256,000tokens | Not published | $0.50 | $0.05 | $1.50 | Official ↗ |
| Ministral 3 14B ministral-14b-2512 Pricing basis: per 1 million tokens | Mistral AI | 256,000tokens | Not published | $0.20 | $0.02 | $0.20 | Official ↗ |
| Ministral 3 8B ministral-8b-2512 Pricing basis: per 1 million tokens | Mistral AI | 256,000tokens | Not published | $0.15 | $0.015 | $0.15 | Official ↗ |
| Ministral 3 3B ministral-3b-2512 Pricing basis: per 1 million tokens | Mistral AI | 256,000tokens | Not published | $0.10 | $0.01 | $0.10 | Official ↗ |
| Claude Sonnet 5.5 claude-sonnet-5-5 Pricing basis: per 1 million tokens | Anthropic | 1,000,000tokens | 128,000tokens | $2.00 | $0.10 | $10.00 | Official ↗ |
| Gemini 3.8 Flash TTS gemini-3.8-flash-tts Pricing basis: per 1 million tokensScheduled Standard pricing change from 2027-01-01; see the model record for native billing dimensions.Google lists Gemini 3.8 Flash TTS as generally available as of September 22, 2026. | 8,192tokens | 16,384tokens | $0.50 | $0.125 | $9.00 | Official ↗ | |
| Gemini 3.8 Flash-Lite TTS gemini-3.8-flash-lite-tts Pricing basis: per 1 million tokensScheduled Standard pricing change from 2027-01-01; see the model record for native billing dimensions.Google lists Gemini 3.8 Flash-Lite TTS as generally available as of September 22, 2026 and as the production replacement for gemini-3.1-flash-tts-preview. | 8,192tokens | 16,384tokens | $0.50 | $0.125 | $6.00 | Official ↗ | |
| Embed v4.0 embed-v4.0 Pricing status: not-publishedPricing basis: per 1 million tokensCohere continues to list embed-v4.0 in the current model catalog with text, image and mixed text/image (PDF) inputs and a 128K context length. | Cohere | 128,000tokens | Not published | Not published | — | — | Official ↗ |
| Command A Reasoning command-a-reasoning-08-2025 Pricing status: free-previewPricing basis: per 1 million tokensCohere currently lists command-a-reasoning-08-2025 as Live with a 256K context window and 32K maximum output. | Cohere | 256,000tokens | 32,000tokens | Not published | — | — | Official ↗ |
| DeepSeek V4 Pro deepseek-v4-pro Pricing status: official-paidPricing basis: per 1 million tokensDeepSeek currently continues API service for DeepSeek V4 Pro; current official documentation supersedes the earlier September 2026 phase-out notice. | DeepSeek | 1,048,576tokens | 393,216tokens | Not published | — | — | Official ↗ |
| Gemini 3.5 Transcribe gemini-3.5-transcribe Pricing basis: per 1 million tokensGoogle announced Gemini 3.5 Transcribe as generally available on August 26, 2026, with no shutdown date currently announced. | Not published | Not published | $2.00 | — | $12.00 | Official ↗ | |
| Embed 5 Pro embed-v5.0-pro Pricing status: not-publishedPricing basis: per 1 million tokensCohere released Embed 5 Pro on September 30, 2026 and currently lists it as available through the Embed API. | Cohere | 128,000tokens | Not published | Not published | — | — | Official ↗ |
| Embed 5 Fast embed-v5.0-fast Pricing status: not-publishedPricing basis: per 1 million tokensCohere released Embed 5 Fast on September 30, 2026 and currently lists it as available through the Embed API. | Cohere | 128,000tokens | Not published | Not published | — | — | Official ↗ |
| GPT-5.6 Cyber gpt-5.6-cyber Pricing basis: per 1 million tokensGPT-5.6 Cyber requires separate Daybreak Red approval and project provisioning; general API access is not implied. | OpenAI | 400,000tokens | 128,000tokens | $12.50 | $1.25 | $75.00 | Official ↗ |
| Gemini 3.6 Flash gemini-3.6-flash Pricing basis: per 1 million tokensScheduled Standard pricing change from 2027-01-01; see the model record for native billing dimensions.Google lists gemini-3.6-flash as a stable model with no shutdown date announced. | 1,048,576tokens | 65,536tokens | $0.75 | $0.075 | $3.75 | Official ↗ | |
| Gemini 3.5 Flash-Lite gemini-3.5-flash-lite Pricing basis: per 1 million tokensGoogle lists gemini-3.5-flash-lite as stable with no shutdown date announced. | 1,048,576tokens | 65,536tokens | $0.30 | $0.03 | $2.50 | Official ↗ | |
| Gemini Embedding 001 gemini-embedding-001 Pricing basis: per 1 million tokensGoogle explicitly states gemini-embedding-001 remains available for text-only embedding use cases alongside the newer multimodal Gemini Embedding 2. | 2,048tokens | Not published | $0.15 | — | — | Official ↗ | |
| Voxtral Mini Transcribe Realtime voxtral-mini-transcribe-realtime-2602 Pricing basis: per minuteMistral lists Voxtral Mini Transcribe Realtime as GA v26.02 and optimized for live transcription only. | Mistral AI | Not published | Not published | $0.006 per minute | — | — | Official ↗ |
| Mistral Embed mistral-embed-2312 Pricing basis: per 1 million tokensMistral lists Mistral Embed as a current GA Premier embedding model with an 8k context window. | Mistral AI | 8,000tokens | Not published | $0.10 | — | — | Official ↗ |
| GPT-6.1 Sol gpt-6.1-sol Pricing basis: per 1 million tokensLong context > 272,000: 2× input/cache · 1.5× outputReleased September 29, 2026 as the newer Sol model, positioned near GPT-6 Astra for complex work at one-fifth of Astra's standard input/output token prices. | OpenAI | 1,050,000tokens | 128,000tokens | $2.00 | $0.10 | $10.00 | Official ↗ |
| GPT-Realtime-Translate gpt-realtime-translate Pricing basis: per minuteReleased May 7, 2026. | OpenAI | 16,000tokens | 2,000tokens | $0.034 per minute | — | — | Official ↗ |
| GPT-Realtime-Whisper gpt-realtime-whisper Pricing basis: per minuteReleased May 7, 2026. | OpenAI | 16,000tokens | 2,000tokens | $0.017 per minute | — | — | Official ↗ |
| Claude Mythos 5.1 claude-mythos-5-1 Pricing basis: per 1 million tokensActive invite-only model released September 1, 2026; retirement not sooner than September 1, 2027. | Anthropic | 1,000,000tokens | 128,000tokens | $10.00 | $0.25 | $50.00 | Official ↗ |
| Mistral Large 4 mistral-large-4 Pricing basis: per 1 million tokensReleased October 6, 2026 in Public Preview. | Mistral AI | 1,000,000tokens | Not published | $1.36 | $0.14 | $4.18 | Official ↗ |
| Shieldstral 1.0 shieldstral-1.0 Pricing status: not-publishedPricing basis: per 1 million tokensPublic Preview model released August 4, 2026 under Apache 2.0. | Mistral AI | 32,768tokens | Not published | Not published | — | — | Official ↗ |
| Parse 5 parse-v5.0 Pricing status: not-publishedPricing basis: per pageReleased August 27, 2026. | Cohere | 8,192tokens | Not published | Not published · per page | — | — | Official ↗ |
| North Mini Code north-mini-code-1-0 Pricing status: free-previewPricing basis: per 1 million tokensAvailable through Chat V2 API and as Apache 2.0 open weights. | Cohere | 256,000tokens | 64,000tokens | Not published | — | — | Official ↗ |
| North Small Translate north-small-translate-1-0 Pricing status: free-previewPricing basis: per 1 million tokensReleased September 9, 2026. | Cohere | 16,000tokens | 16,000tokens | Not published | — | — | Official ↗ |
| Rerank 4 Fast rerank-v4.0-fast Pricing status: not-publishedPricing basis: per search unitCohere lists rerank-v4.0-fast as a latest Rerank model with 32,768-token context. | Cohere | 32,768tokens | Not published | Not published · per search unit | — | — | Official ↗ |
| Kimi K3 kimi-k3 Pricing status: official-paidPricing basis: per 1 million tokensOfficial API rates are verified but no historical effective-from date is inferred for the canonical schedule. | Moonshot AI | 1,048,576tokens | Not published | Not published | — | — | Official ↗ |
| Gemma 4 31B IT gemma-4-31b-it Pricing status: free-previewPricing basis: per 1 million tokensGemini Developer API provides hosted access to gemma-4-31b-it. | 262,144tokens | Not published | Not published | — | — | Official ↗ | |
| GLM-5.3 glm-5.3 Pricing status: not-publishedPricing basis: per 1 million tokensThe official release documents low, high and max reasoning effort with thinking always enabled. | Z.ai | Not published | Not published | Not published | — | — | Official ↗ |
| MiniMax M3 MiniMax-M3 Pricing status: official-paidPricing basis: per 1 million tokensMiniMax publishes separate PAYG bands for input up to 512K and 512K–1M. | MiniMax | 1,000,000tokens | Not published | Not published | — | — | Official ↗ |
| Qwen3-Coder-Next qwen3-coder-next Pricing status: official-paidPricing basis: per 1 million tokensAlibaba Cloud publishes three input-length pricing bands for EU and international endpoints. | Alibaba Cloud | 262,144tokens | 65,536tokens | Not published | — | — | Official ↗ |
| Gemini 3.8 Flash Cyber gemini-3.8-flash-cyber Pricing basis: per 1 million tokensGenerally available behind an allowlist; access requires Google team or Fairwind approval. | 1,048,576tokens | 65,536tokens | $1.50 | $0.15 | $7.50 | Official ↗ | |
| GPT-Rosalind Research gpt-rosalind-research Pricing basis: per 1 million tokensAPI access is limited to eligible organizations and approved internal research through OpenAI's trusted-access program. | OpenAI | Not published | Not published | $5.00 | $0.50 | $25.00 | Official ↗ |
| Grok Voice Think Fast 2.0 grok-voice-think-fast-2.0 Pricing basis: per minuteThe versioned model is billed at $0.08 per minute of audio and is excluded from the token calculator. | xAI | Not published | Not published | $0.08 per minute | — | — | Official ↗ |
| gpt-oss-120b gpt-oss-120b Pricing status: self-hostedPricing basis: per 1 million tokensOpenAI explicitly states that gpt-oss models are not served through the OpenAI API and have no OpenAI API pricing. | OpenAI | 131,072tokens | 131,072tokens | Not published | — | — | Official ↗ |
| Qwen3.5-397B-A17B qwen3.5-397b-a17b Pricing basis: per 1 million tokensGlobal (Frankfurt/Virginia): ≤128K input/request $0.172 input / $1.032 output; >128K–256K $0.43 input / $2.58 output per MTok. International (Singapore): $0.60 / $3.60. Tiered rates; no single flat comparison applies.Alibaba Cloud publishes Global list prices in Frankfurt and Virginia in two request-input-length tiers: up to 128K and above 128K to 256K tokens. The per-token rate for a request follows its input-size tier. | Alibaba Cloud | 262,144tokens | 65,536tokens | From $0.172 | — | From $1.032 | Official ↗ |
| GPT-Image-2.5 Sunburst gpt-image-2.5-sunburst Pricing basis: per 1 million IMAGE tokens (text input billed separately)This model generates image output, not text. Official Standard image-token rates are $8.00 input, $2.00 cached image input and $30.00 output per 1M image tokens. | OpenAI | Not published | Not published | $8.00 | $2.00 | $30.00 | Official ↗ |
| GPT-Realtime-2.1 gpt-realtime-2.1 Pricing basis: per 1 million TEXT tokens (audio/image separate)Displayed Standard token rates are TEXT ONLY: $4.00 input, $0.40 cached, and $24.00 output per 1M text tokens. | OpenAI | 128,000tokens | 32,000tokens | $4.00 | $0.40 | $24.00 | Official ↗ |
| GPT-Realtime-2.1 Mini gpt-realtime-2.1-mini Pricing basis: per 1 million TEXT tokens (audio/image separate)Displayed Standard prices are TEXT ONLY: $0.60 input, $0.06 cached and $2.40 output per 1M text tokens. | OpenAI | 128,000tokens | 32,000tokens | $0.60 | $0.06 | $2.40 | Official ↗ |
| Gemini 3.8 Live gemini-3.8-live Pricing basis: per 1 million TEXT tokens (audio/video separate)Shown Standard prices cover TEXT tokens only: $0.75 input and $4.50 output per 1M text tokens. | 131,072tokens | 65,536tokens | $0.75 | — | $4.50 | Official ↗ | |
| Gemini Embedding 2 gemini-embedding-2 Pricing basis: per 1 million TEXT input tokens (other media separate)Displayed Standard price ($0.20 per 1M tokens) applies to TEXT embedding inputs only. Embeddings have no generative output-token charge. | 8,192tokens | Not published | $0.20 | — | — | Official ↗ | |
| Nano Banana 2.1 gemini-nano-banana-2.1 Pricing basis: per 1 million tokens (IMAGE output; text output billed separately)Standard paid API input: $1.50 per 1M text/image/video input tokens; generated IMAGE output: $30.00 per 1M IMAGE output tokens. Text and thinking output is separately priced at $7.50 per 1M text tokens; do not apply the image rate to text. | 131,072tokens | 32,768tokens | $1.50 | — | $30.00 | Official ↗ | |
| Nano Banana Pro gemini-3-pro-image Pricing basis: per 1 million tokens (IMAGE output; text output billed separately)Stable provider-native model ID is gemini-3-pro-image; Nano Banana Pro is its consumer-facing name. | 65,536tokens | 32,768tokens | $2.00 | — | $120.00 | Official ↗ | |
| Kling VIDEO 3.0 kling-3.0 Pricing status: not-publishedPricing basis: per generation task (official credits vary by second, resolution and audio)The official developer API provides /text-to-video/kling-3.0 and supports both 720p/1080p/4K video settings; product and developer-plan access or pricing may differ. | Kling AI | Not published | Not published | Not published · per generation task (official credits vary by second, resolution and audio) | — | — | Official ↗ |
| Seedance 2.0 dreamina-seedance-2-0-260128 Pricing basis: per 1M metered service tokens (no video input, 480p/720p only)BytePlus ModelArk native ID is dreamina-seedance-2-0-260128. This is distinct from Seedance 2.0 Fast or Mini; account activation, region and service availability must be checked in BytePlus. | ByteDance | Not published | Not published | $7.00 | — | — | Official ↗ |
| GPT-Image-2.5 Flare gpt-image-2.5-flare Pricing basis: per 1 million IMAGE tokens (text input separately billed)Standard paid image-token rates are $8.00 input, $2.00 cached image input and $30.00 output per 1 million IMAGE tokens. Text input is billed separately: $5.00 input and $1.25 cached per 1 million TEXT tokens. | OpenAI | Not published | Not published | $8.00 | $2.00 | $30.00 | Official ↗ |
| Gemini Omni Flash 1.1 gemini-omni-1.1-flash Pricing basis: per 1 million input / VIDEO output tokens (text output separate)Standard paid Gemini API input rate is $1.50 per 1 million input tokens across text/image/video/audio. Generated VIDEO output is $17.50 per 1 million VIDEO tokens; text output, when applicable, is $9.00 per 1 million text tokens. | 1,048,576tokens | Not published | $1.50 | — | $17.50 | Official ↗ | |
| Lyria 3.5 lyria-3.5 Pricing basis: per generated full song (Standard paid API)Google Gemini API publishes $0.08 per generated full song, billed per request (Standard paid tier); no free API tier. This is NOT a token or per-second price. | 131,072tokens | Not published | $0.08 per generated full song (Standard paid API) | — | — | Official ↗ | |
| FLUX.2 Max flux-2-max Pricing basis: per first output megapixel; additional/reference megapixels extraOfficial base price is $0.07 for the FIRST output megapixel (MP, 1024×1024). Each ADDITIONAL output MP is +$0.03, and image reference input is $0.03 per input MP. The displayed $0.07 is therefore a STARTING price, not a universal image cost. | Black Forest Labs | Not published | Not published | $0.07 per first output megapixel; additional/reference megapixels extra | — | — | Official ↗ |
| Eleven v4 eleven_v4 Pricing status: not-publishedPricing basis: per input character; credit cost and USD vary by planProvider-native ID eleven_v4 is available through the Text to Dialogue API; supports 90+ languages, including Arabic, and multiple speakers. | ElevenLabs | Not published | Not published | Not published · per input character; credit cost and USD vary by plan | — | — | Official ↗ |
| Eleven v4 Turbo eleven_v4_turbo Pricing status: not-publishedPricing basis: per input character; credit cost and USD vary by planProvider-native ID eleven_v4_turbo is supported by ElevenLabs Text to Dialogue WebSocket and its realtime/agent ecosystem; 90+ languages including Arabic. | ElevenLabs | Not published | Not published | Not published · per input character; credit cost and USD vary by plan | — | — | Official ↗ |
| GPT-Image-2 gpt-image-2 Pricing basis: per 1 million IMAGE tokens (text input separate)OpenAI Standard image-token rates are $4.00 input, $1.00 cached image input, $15.00 generated IMAGE output per 1M tokens; TEXT prompt input is separately billed $2.50 and $0.625 cached per 1M TEXT tokens. | OpenAI | Not published | Not published | $4.00 | $1.00 | $15.00 | Official ↗ |
| Ideogram 4.0 ideogram-v4 Pricing basis: per image, Turbo generation only (Default/Quality higher)Ideogram API lists $0.03 per image for Ideogram 4.0 Turbo generation. DEFAULT is $0.06 and QUALITY $0.10 per image. This catalog rate is TURBO ONLY; changing speed or editing endpoints changes price. | Ideogram | Not published | Not published | $0.03 per image, Turbo generation only (Default/Quality higher) | — | — | Official ↗ |
| Ideogram 3.0 ideogram-v3 Pricing basis: per image, Turbo generation only (Default/Quality higher)Ideogram 3.0 API TURBO output costs $0.03 per image. DEFAULT $0.06, QUALITY $0.09. Prices vary further for character reference and editing endpoints. | Ideogram | Not published | Not published | $0.03 per image, Turbo generation only (Default/Quality higher) | — | — | Official ↗ |
| Runway Gen-4.5 gen4.5 Pricing basis: per generated minute (equivalent to $0.12/second; 12 credits/second)Official Runway Dev API model ID is gen4.5, usable for both text-to-video and image-to-video requests. | Runway | Not published | Not published | $7.20 per generated minute (equivalent to $0.12/second; 12 credits/second) | — | — | Official ↗ |
| Deepgram Nova-3 nova-3 Pricing basis: per pre-recorded MONOLINGUAL audio minute (streaming/multilingual differ)Official Pay-As-You-Go pre-recorded monolingual Nova-3 rate is $0.0043 per audio minute; multilingual pre-recorded is $0.0052/minute. | Deepgram | Not published | Not published | $0.0043 per pre-recorded MONOLINGUAL audio minute (streaming/multilingual differ) | — | — | Official ↗ |
| Deepgram Flux flux-general-en Pricing basis: per streaming ENGLISH audio minute (promotional Pay As You Go)Official Pay-As-You-Go Flux English STREAMING rate is currently $0.0065/audio minute (limited-time promotional, regular $0.0077). Multilingual Flux variant is $0.0078/minute and is NOT represented by this model ID. | Deepgram | Not published | Not published | $0.0065 per streaming ENGLISH audio minute (promotional Pay As You Go) | — | — | Official ↗ |
| ElevenLabs Scribe v2 scribe_v2 Pricing basis: per 60 audio minutes (hourly API rate; add-ons extra)ElevenLabs official Speech to Text API model ID is scribe_v2, used at POST /v1/speech-to-text. | ElevenLabs | Not published | Not published | $0.22 per 60 audio minutes (hourly API rate; add-ons extra) | — | — | Official ↗ |
| ElevenLabs Scribe v2 Realtime scribe_v2_realtime Pricing basis: per 60 audio minutes (realtime WebSocket hourly API rate)Official WebSocket model_id is scribe_v2_realtime at wss://api.elevenlabs.io/v1/speech-to-text/realtime. | ElevenLabs | Not published | Not published | $0.39 per 60 audio minutes (realtime WebSocket hourly API rate) | — | — | Official ↗ |
| FLUX.2 Klein 9B flux-2-klein-9b Pricing basis: per first output MP (additional/reference MP extra)Official BFL API endpoint is POST /v1/flux-2-klein-9b. The model's weights are available with license terms; open weights do NOT imply unrestricted commercial usage. | Black Forest Labs | Not published | Not published | $0.015 per first output MP (additional/reference MP extra) | — | — | Official ↗ |
| FLUX.2 Pro flux-2-pro Pricing basis: per first output MP (additional/reference MP extra)Official BFL API endpoint is POST /v1/flux-2-pro. Proprietary hosted model; access through BFL API. | Black Forest Labs | Not published | Not published | $0.03 per first output MP (additional/reference MP extra) | — | — | Official ↗ |
| Claude Haiku 5.5 claude-haiku-5-5 Pricing basis: per million tokens, <=100K or >100K prompt tierGlobal (Frankfurt/Virginia): ≤128K input/request $0.10 input / $0.50 output; >128K–256K $0.50 input / $2.50 output per MTok. International (Singapore): $0.60 / $3.60. Tiered rates; no single flat comparison applies.Prompt-length tiered Standard API prices: <=100,000 input prompt tokens $0.10 input/$0.50 output per million; >100,000 prompt tokens $0.50 input/$2.50 output per million. | Anthropic | 1,000,000tokens | 128,000tokens | From $0.10 | — | From $0.50 | Official ↗ |
| Gemini 3.1 Pro Preview gemini-3.1-pro-preview Pricing basis: per million tokens, <=200K or >200K prompt tierGlobal (Frankfurt/Virginia): ≤128K input/request $2.00 input / $12.00 output; >128K–256K $4.00 input / $18.00 output per MTok. International (Singapore): $0.60 / $3.60. Tiered rates; no single flat comparison applies.Official API ID gemini-3.1-pro-preview; preview availability may change. | 1,048,576tokens | 65,536tokens | From $2.00 | — | From $12.00 | Official ↗ | |
| Nano Banana 2 (Gemini 3.1 Flash Image) gemini-3.1-flash-image Pricing basis: per million tokens: IMAGE output only, text output separateNative API ID gemini-3.1-flash-image is different from gemini-nano-banana-2.1 already in the catalog. | 131,072tokens | 32,768tokens | $0.50 | — | $60.00 | Official ↗ | |
| Gemini 3.8 Live Extended Thinking gemini-3.8-live-extended-thinking Pricing basis: per million TEXT tokens; audio/video priced separatelyOfficial API ID gemini-3.8-live-extended-thinking is distinct from gemini-3.8-live. | 131,072tokens | 65,536tokens | $0.75 | — | $4.50 | Official ↗ | |
| Stable Image Ultra stable-image-ultra Pricing basis: per successful Ultra image, 8 creditsOfficial service endpoint POST /v2beta/stable-image/generate/ultra. This is a hosted API service, not an independent open-weight model. | Stability AI | Not published | Not published | $0.08 per successful Ultra image, 8 credits | — | — | Official ↗ |
No models match this filter.
Catalog verified 2026-11-10. Promotional or scheduled rates can change; the official vendor documentation remains the final billing authority.
Current dataset ↗ · Append-only change ledger ↗
TOKEN COST CALCULATOR
Estimate one workload.
Enter uncached input, cached input and output tokens. The calculator selects the Standard pricing period by date and applies stored long-context rules automatically.
ESTIMATED DIRECT TOKEN COST
Standard API estimate.
Calculated from the same public catalog used to render the table above.
ESTIMATED TOTAL—
Uncached input—
Cached input—
Output—
Loading pricing dataset…
METHODOLOGY
Comparable first. Caveats visible.
SXF separates directly comparable Standard token rates from service tiers and add-ons that can change the bill but are not equivalent across providers.
One unit.
Headline token rates are normalized to USD per one million tokens. Cached input stays separate from ordinary input.
Request shape matters.
Stored long-context rules and dated pricing schedules are applied from the canonical dataset instead of being retyped into the calculator.
Do not mix tiers.
Batch, Flex, Fast, Priority, tools, grounding, storage, regional uplifts and negotiated pricing remain outside the headline calculator.
PRICING FAQ
How to read the database.
What pricing does the SXF model database use?
The table normalizes vendor-listed Standard API token pricing in USD per one million tokens. It does not mix Batch, Flex, Fast, Priority, regional, enterprise, or negotiated pricing into the headline rates.
Does the calculator include tool or grounding charges?
No. The calculator estimates direct text-token charges only. Search, grounding, code execution, tools, cache storage, regional uplifts, and other add-on charges are excluded unless they are explicitly represented as token rates.
How does long-context pricing work for OpenAI models in this database?
For cataloged OpenAI models with a long-context rule, requests above 272,000 total input tokens use the published higher input, cache, and output rates for the full request. The calculator applies that rule automatically.
Why does Gemini 3.8 Flash show a future price change?
Google published introductory Standard pricing through December 31, 2026 and higher Standard pricing beginning January 1, 2027. The calculator selects the stored pricing period from the billing date.