Model Inventory

Fuel iX Model Inventory

Last Updated: Tue, 27 Oct 2026 17:50:34 GMT

This page lists the AI models available on the Fuel iX proxy. It does not necessarily reflect what your organization has access to, or what the Copilots product supports.

Hosting location reflects the provider cloud region; the region — not the city — is the contractual data-residency boundary.


Chat & Reasoning Models

TELUS AI Sovereign (SAIF)

ModelAliasModel IDCapabilitiesMarkingInput CostOutput Cost
Wasikan AI 80Bwasikan-ai-80b, wasikan-v2-2wasikan-ai-80bText onlyNot attested *FreeFree
Wasikan Qwen3 Next 80Bwasikan-qwen-3-next-80bqwen3-next-80bText onlyNot attested *FreeFree
Gemma 4 SAIF Kidcgemma-4-saif-kidcgemma-4-31b-it (FP8)Text onlyNot attested *FreeFree
Gemma 4 SAIFgemma-4-saifgemma-4-31b-it (FP8)Text onlyNot attested *FreeFree
Mistral Small 3.2 24Bmistral-small-3.2-24bmistral-small-3.2-24bText onlyNot attested *FreeFree
↳mistral-small-3.2-24b-prodmistral-small-3.2-24b--FreeFree
Hal 2.0 Previewhal-2.0-previewhal-2.0-previewText onlyNot attested *$2.75/M$13.75/M
Clarke 1.0clarke-1.0clarke-1.0Text onlyNot attested *$1.50/M$7.00/M
Hal 1.0hal-1.0hal-1.0Text onlyNot attested *$2.75/M$13.75/M
Tycho 1.0tycho-1.0tycho-1.0Text onlyNot attested *$0.50/M$2.25/M

Anthropic

ModelAliasRegionCapabilitiesMarkingInput CostOutput CostLong-Context InputLong-Context Output
Claude Sonnet 5.5claude-sonnet-5, cursor-c-sonnet-5, claude-sonnet-5-5, cursor-c-sonnet-5-5, claude-sonnet🌐 GlobalVision, PDF, Tools, ReasoningWatermark *$2.00/M$10.00/M$2.00/M (>200k)$10.00/M (>200k)
Claude Sonnet 5claude-sonnet-5-0, claude-sonnet-5-vertex🌐 GlobalVision, PDF, Tools, ReasoningWatermark$2.00/M$10.00/M$2.00/M (>200k)$10.00/M (>200k)
Claude Sonnet 4.6claude-sonnet-4-6, cursor-c-sonnet-4-6, claude-sonnet-4-6-vertex, claude-sonnet-4, claude-4-sonnet, cursor-c-4-sonnet🌐 GlobalVision, PDF, Tools, Reasoning, BatchWatermark$3.00/M$15.00/M$3.00/M (>200k)$15.00/M (>200k)
↳claude-sonnet-4-6-anthropic🇺🇸 US--Contact SalesContact Sales--
Claude Opus 5.5claude-opus-5, cursor-c-opus-5, claude-opus-5-5, cursor-c-opus-5-5, claude-opus🌐 GlobalVision, PDF, Tools, ReasoningWatermark$4.00/M$20.00/M$4.00/M (>200k)$20.00/M (>200k)
↳-🇺🇸 US--$4.00/M$20.00/M$4.00/M (>200k)$20.00/M (>200k)
Claude Opus 5claude-opus-5-0🌐 GlobalVision, PDF, Tools, ReasoningWatermark$5.00/M$25.00/M$5.00/M (>200k)$25.00/M (>200k)
Claude Opus 4.8claude-opus-4-8, cursor-c-opus-4-8, claude-opus-4, cursor-c-4-opus🌐 GlobalVision, PDF, Tools, ReasoningWatermark$5.00/M$25.00/M$5.00/M (>200k)$25.00/M (>200k)
Claude Opus 4.7claude-opus-4-7, cursor-c-opus-4-7🌐 GlobalVision, PDF, Tools, ReasoningWatermark$5.00/M$25.00/M$5.00/M (>200k)$25.00/M (>200k)
Claude Opus 4.6claude-opus-4-6-20260205, claude-opus-4-6, cursor-c-opus-4-6🌐 GlobalVision, PDF, Tools, Reasoning, BatchWatermark$5.00/M$25.00/M$5.00/M (>200k)$25.00/M (>200k)
↳claude-opus-4-6-anthropic🇺🇸 US--Contact SalesContact Sales--
Claude Haiku 5.5claude-haiku-5, claude-haiku-5-5, claude-haiku🌐 GlobalVision, PDF, Tools, ReasoningWatermark *$0.10/M$0.50/M$0.50/M (>100k)$2.50/M (>100k)
Claude Fable 5.1claude-fable-5, claude-fable-5-1, claude-fable🌐 GlobalVision, PDF, Tools, ReasoningWatermark *$10.00/M$50.00/M--
Claude Opus 4.5claude-opus-4-5-20251101, claude-opus-4-5, cursor-c-opus-4-5🌐 GlobalVision, PDF, Tools, ReasoningWatermark$5.00/M$25.00/M--
↳claude-opus-4-5-20251101, claude-opus-4-5🇺🇸 US--$5.00/M$25.00/M--
Claude Haiku 4.5claude-haiku-4-5-20251001, claude-haiku-4-5, c-haiku-4-5, claude-haiku-4🌐 GlobalVision, PDF, Tools, Reasoning, BatchWatermark$1.00/M$5.00/M--
↳claude-haiku-4-5-bedrock🇺🇸 US--$1.00/M$5.00/M--
↳claude-haiku-4-5-anthropic🇺🇸 US--Contact SalesContact Sales--
Claude Sonnet 4.5claude-sonnet-4-5-20250929, claude-sonnet-4-5, claude-sonnet-4-20250514🌐 GlobalVision, PDF, Tools, Reasoning, BatchWatermark$3.00/M$15.00/M$3.00/M (>200k)$15.00/M (>200k)
↳claude-sonnet-4-5-bedrock🇺🇸 US--$3.00/M$15.00/M$3.00/M (>200k)$15.00/M (>200k)
↳claude-sonnet-4-5-anthropic🇺🇸 US--Contact SalesContact Sales--
Claude Opus 4.1claude-opus-4-1-20250805, claude-opus-4-1, cursor-c-opus-4-1🇺🇸 USVision, PDF, Tools, ReasoningWatermark$15.00/M$75.00/M--
Claude Sonnet 4claude-sonnet-4-legacy🌐 GlobalVision, PDF, Tools, ReasoningWatermark$3.00/M$15.00/M$6.00/M (>200k)$22.50/M (>200k)
Claude Sonnet 3.7-🇺🇸 USVision, PDF, Tools, ReasoningWatermark$3.00/M$15.00/M--

OpenAI

ModelAliasRegionCapabilitiesMarkingInput CostOutput CostLong-Context InputLong-Context Output
GPT-6.1 Terragpt-6.1-terra-bedrock, gpt-6.1-terra, gpt-6.1-terra-2026-10-26, gpt-6-terra🇺🇸 USVision, Tools, ReasoningNot attested *$1.00/M$5.00/M$2.00/M (>272k)$7.50/M (>272k)
GPT-6.1 Sol-🇺🇸 USVision, Tools, ReasoningNot attested *$2.00/M$10.00/M--
↳gpt-6.1-sol-bedrock, gpt-6.1-sol, gpt-6.1-sol-2026-09-29, gpt-6-sol🇺🇸 US--$2.00/M$10.00/M--
GPT-6 Luna-🇺🇸 USVision, Tools, ReasoningNot attested *$0.10/M$0.50/M$0.20/M (>272k)$0.75/M (>272k)
↳gpt-6-luna-bedrock🇺🇸 US--$0.10/M$0.50/M$0.20/M (>272k)$0.75/M (>272k)
↳gpt-6-luna-2026-09-22, gpt-6-luna🇺🇸 US--$0.10/M$0.50/M$0.20/M (>272k)$0.75/M (>272k)
GPT-6 Solgpt-6-sol-2026-09-22, gpt-6.0-sol🇺🇸 USVision, Tools, ReasoningNot attested *$2.00/M$10.00/M$4.00/M (>272k)$15.00/M (>272k)
GPT-6 Astragpt-6-astra-2026-09-03, gpt-6-astra🇺🇸 USVision, Tools, ReasoningNot attested *$10.00/M$50.00/M$20.00/M (>272k)$75.00/M (>272k)
GPT-5.6 Lunagpt-5.6-luna-2026-07-09, gpt-5.6-luna🇺🇸 USVision, Tools, ReasoningNot attested *$0.20/M$1.20/M$0.40/M (>272k)$1.80/M (>272k)
↳gpt-5.6-luna-bedrock🇺🇸 US--$0.20/M$1.20/M$0.40/M (>272k)$1.80/M (>272k)
GPT-5.6 Solgpt-5.6-sol-2026-07-09, gpt-5.6-sol🇺🇸 USVision, Tools, ReasoningNot attested *$4.00/M$20.00/M$8.00/M (>272k)$30.00/M (>272k)
GPT-5.6 Terragpt-5.6-terra-2026-07-09, gpt-5.6-terra🇺🇸 USVision, Tools, ReasoningNot attested *$2.00/M$12.00/M$4.00/M (>272k)$18.00/M (>272k)
Chatgpt-5-chat-2025-08-07, gpt-5-chat🇺🇸 USVision, Tools, ReasoningNot attested *$1.25/M$10.00/M--
GPT-5.5gpt-5.5-2026-04-24, gpt-5.5🇺🇸 USVision, Tools, ReasoningNot attested *$5.00/M$30.00/M$10.00/M (>272k)$45.00/M (>272k)
GPT-5.4 Minigpt-5.4-mini-2026-03-17, gpt-5.4-mini🇺🇸 USText onlyNot attested *$0.75/M$4.50/M--
GPT-5.4 Nanogpt-5.4-nano-2026-03-17, gpt-5.4-nano🇺🇸 USText onlyNot attested *$0.20/M$1.25/M--
GPT-5.4gpt-5.4-2026-03-05, gpt-5.4🇺🇸 USText onlyNot attested *$2.50/M$15.00/M$5.00/M (>272k)$22.50/M (>272k)
GPT-5.3 Codexgpt-5.3-codex-2026-02-24, gpt-5.3-codex🇺🇸 USText onlyNot attested *$1.75/M$14.00/M--
GPT-5.2gpt-5.2-2025-12-11, gpt-5.2🇺🇸 USVision, Tools, ReasoningNot attested *$1.75/M$14.00/M--
GPT-5.2 Chatgpt-5.2-chat-2025-12-11, gpt-5.2-chat🇺🇸 USVision, Tools, ReasoningNot attested *$1.75/M$14.00/M--
GPT-5gpt-5-2025-08-07, gpt-5🇺🇸 USVision, Tools, ReasoningNot attested *$1.25/M$10.00/M--
GPT-5 Minigpt-5-mini-2025-08-07, gpt-5-mini🇺🇸 USVision, Tools, ReasoningNot attested *$0.25/M$2.00/M--
GPT-5 Nanogpt-5-nano-2025-08-07, gpt-5-nano🇺🇸 USVision, Tools, ReasoningNot attested *$0.05/M$0.40/M--
o3o3🇺🇸 USVision, Tools, ReasoningNot attested *$2.20/M$8.80/M--
o4-minio4-mini🇺🇸 USVision, PDF, Tools, ReasoningNot attested *$1.10/M$4.40/M--
GPT-4.1gpt-4.1-2025-04-14, gpt-4.1🇺🇸 USVision, Tools, WebNot attested *$2.00/M$8.00/M--
GPT-4.1 Minigpt-4.1-mini-2025-04-14, gpt-4.1-mini🇺🇸 USVision, Tools, WebNot attested *$1.00/M$4.00/M--
↳gpt-4.1-mini-canada, gpt-4.1-mini🇨🇦 Canada--$1.00/M$4.00/M--
GPT-4.1 Nanogpt-4.1-nano-2025-04-14, gpt-4.1-nano🇺🇸 USVision, ToolsNot attested *$0.50/M$2.00/M--
GPT-4ogpt-4o-2024-05-13, gpt-4o🇺🇸 USVision, ToolsNot attested *$2.50/M$10.00/M--
↳gpt-4o-2024-05-13, gpt-4o🇺🇸 US--$5.00/M$15.00/M--
↳gpt-4o-2024-08-06🇺🇸 US--$2.50/M$10.00/M--
↳gpt-4o-2024-11-20, gpt-4o🇺🇸 US--$2.50/M$10.00/M--
↳gpt-4o-2024-05-13🇺🇸 US--$5.00/M$15.00/M--
↳gpt-4o-transcribe-2025-03-20, gpt-4o-transcribe🇺🇸 US--$2.50/M$10.00/M--
↳gpt-4o-transcribe-diarize-2025-03-20, gpt-4o-transcribe-diarize🇺🇸 US--$2.50/M$10.00/M--
↳gpt-4o-ca-east-2024-05-13🇨🇦 Canada--$5.00/M$15.00/M--
↳gpt-4o-ca-east, gpt-4o-ca-east-2024-11-20🇨🇦 Canada--$2.50/M$10.00/M--
↳gpt-4o-2024-11-20, gpt-4o🇨🇦 Canada--$2.50/M$10.00/M--
o3-minio3-mini🇺🇸 USTools, ReasoningNot attested *$1.10/M$4.40/M--
GPT-4o Minigpt-4o-mini-2024-07-18, gpt-4o-mini🇺🇸 USVision, ToolsNot attested *$0.165/M$0.66/M--
↳-🇺🇸 US--$0.15/M$0.60/M--
↳gpt-4o-mini-ca-east🇨🇦 Canada--$0.165/M$0.66/M--
GPT-4o (Content Filter)gpt-4o-2024-05-13-content-filter🇺🇸 USVision, ToolsNot attested *$5.00/M$15.00/M--
GPT-OSS 120Bgpt-oss-120b🇺🇸 USText onlyNot attested *$6.00/M$18.00/M--
GPT-OSS 20Bgpt-oss-20b🇺🇸 USText onlyNot attested *$0.07/M$0.30/M--

Google

ModelAliasRegionCapabilitiesMarkingInput CostOutput CostLong-Context InputLong-Context Output
Gemini 4 Argongemini-4-argon🌐 GlobalVision, Audio, Video, Tools, Reasoning, WebSynthID *$2.00/M$10.00/M--
Gemini 3.8 Flashgemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3-flash🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.75/M$3.75/M--
Gemini 3.5 Flash Litegemini-3.5-flash-lite🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.30/M$2.50/M--
Gemini 3.5 Flashgemini-3.5-flash🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$1.50/M$9.00/M--
↳gemini-3.5-flash-ca👑 🇨🇦 Canada--$1.50/M$9.00/M--
Gemini 3.1 Pro (Preview)gemini-3.1-pro-preview, gemini-3.1-pro, gemini-3-pro-preview, gemini-3-pro🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$2.00/M$12.00/M$4.00/M (>200k)$18.00/M (>200k)
Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview, gemini-3.1-flash-lite🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.25/M$1.50/M--
Gemini 3 Flashgemini-3-flash-preview🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.50/M$3.00/M--
Gemini 2.5 Flash Litegemini-2.5-flash-lite🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.10/M$0.40/M--
Gemini 2.5 Flashgemini-2.5-flash🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$0.15/M$0.60/M--
↳gemini-2.5-flash-ca👑 🇨🇦 Canada--$0.15/M$0.60/M--
Gemini 2.5 Progemini-2.5-pro🌐 GlobalVision, Audio, PDF, Video, Tools, Reasoning, WebSynthID *$1.25/M$10.00/M$2.50/M (>200k)$15.00/M (>200k)
↳gemini-2.5-pro🇺🇸 US--$1.25/M$10.00/M$2.50/M (>200k)$15.00/M (>200k)
↳gemini-2.5-pro-ca👑 🇨🇦 Canada--$1.25/M$10.00/M$2.50/M (>200k)$15.00/M (>200k)

DeepSeek

ModelAliasRegionCapabilitiesMarkingInput CostOutput Cost
DeepSeek V4.1 Flashdeepseek-v4.1-flash-2026-09-10, deepseek-v4.1-flash🇺🇸 USToolsNot attested *$0.375/M$1.50/M

Mistral

ModelAliasRegionCapabilitiesMarkingInput CostOutput Cost
Mistral Largemistral-large-24.02, mistral-large🇺🇸 USToolsNot attested *$8.00/M$24.00/M
↳mistral-large-24.02, mistral-large🇨🇦 Canada--$8.00/M$24.00/M

Meta

ModelAliasRegionCapabilitiesMarkingInput CostOutput Cost
Llama 4 Scoutllama-4-scout-17b-16e🇺🇸 USVision, ToolsNot attested *$0.25/M$0.70/M
Llama 4 Maverickllama-4-maverick-17b-128e🇺🇸 USVision, ToolsNot attested *$0.35/M$1.15/M
Llama 8Bllama-guard-3-8b🇺🇸 USText onlyNot attested *FreeFree

Other

ModelAliasRegionCapabilitiesMarkingInput CostOutput Cost
gemma-4-31b-itgemma-4-31b-it, gemma-4-31b, gemma-4🇺🇸 USText onlyNot attested *FreeFree
↳gemma-4-31b-it-bedrock, gemma-4-31b-it, gemma-4-31b, gemma-4🇺🇸 US--$0.14/M$0.40/M
gemma-4-26b-a4b-itgemma-4-26b-a4b-it, gemma-4-26b🇺🇸 USText onlyNot attested *FreeFree
voxtral-minivoxtral-mini, voxtral-mini-3b-2507🇺🇸 USText onlyNot attested *FreeFree

Marking records how a model marks its generated output as AI-generated, as required by EU AI Act Article 50(2) from 2026-12-02. SynthID and Watermark are embedded in the output itself; C2PA is signed metadata on generated files. Not attested means the provider publishes no marking mechanism for that output type — it is not a statement that the output is unmarked. A * marks an attestation we have not independently verified.


Embedding Models

TELUS AI Sovereign (SAIF)

ModelAliasModel IDInput CostOutput Cost
KaLM Embedding Gemma3 12Bkalm-embedding-gemma3-12bkalm-embedding-gemma3-12bFreeFree

OpenAI

ModelAliasRegionInput CostOutput Cost
Text Embedding Ada-002text-embedding-ada-002🇺🇸 US$0.10/MFree
↳text-embedding-ada-002🇨🇦 Canada$0.10/MFree
Text Embedding 3 Smalltext-embedding-3-small🇺🇸 US$0.02/MFree
↳text-embedding-3-small-ca-east🇨🇦 Canada$0.02/MFree
↳text-embedding-3-small-ca-east-global, text-embedding-3-small🇨🇦 Canada$0.02/MFree
Text Embedding 3 Largetext-embedding-3-large🇺🇸 US$0.13/MFree
↳text-embedding-3-large🇨🇦 Canada$0.13/MFree

Google

ModelAliasRegionInput CostOutput Cost
Gemini Embedding (Preview)gemini-embedding-2-preview🇺🇸 US$0.20/MFree
Gemini Embeddinggemini-embedding-001, gemini-embedding-001-ca👑 🇨🇦 Canada$0.01/MFree

Image Generation Models

OpenAI

ModelAliasRegionMarkingInput CostOutput Cost
****gpt-image-2🇺🇸 USC2PA *-TBD

Google

ModelAliasRegionMarkingInput CostOutput Cost
Gemini 3.1 Flash Imagegemini-3.1-flash-image🌐 GlobalSynthID-$0.039/image
Gemini 2.5 Flash Imagegemini-2.5-flash-image, imagen-4, imagen-4-ultra🌐 GlobalSynthID-$0.039/image

Audio Models

OpenAI

ModelAliasRegionMarkingInput CostOutput Cost
Whisperwhisper-1🇺🇸 USNot attested *FreeFree
TTS-1 HDtts-1-hd🇺🇸 USNot attested *FreeFree
TTS-1tts-1🇺🇸 USNot attested *FreeFree

Batch Processing

These models accept asynchronous batch requests through the Message Batches API, billed at 50% of the standard rate. Batches are a property of the specific deployment, not of the model: send them to one of the aliases below. The same model served from another region or cloud does not accept batches.

ModelBatch aliasHosting
Claude Haiku 4.5claude-haiku-4-5-anthropic🇺🇸 US
Claude Opus 4.6claude-opus-4-6-anthropic🇺🇸 US
Claude Sonnet 4.5claude-sonnet-4-5-anthropic🇺🇸 US
Claude Sonnet 4.6claude-sonnet-4-6-anthropic🇺🇸 US

Prompt Cache Pricing

Models that support prompt caching have differentiated pricing for cache operations. Cache write tokens are charged when content is first cached; cache read tokens are charged on cache hits at a reduced rate.

Anthropic

ModelCache WriteCache ReadLong-Context Cache WriteLong-Context Cache ReadCache Write 1hrLong-Context Cache Write 1hr
Claude Haiku 5.5$0.125/M$0.01/M$0.625/M$0.05/M$0.20/M$1.00/M
Claude Haiku 4.5$1.25/M$0.10/M$1.25/M$0.10/M$2.00/M$2.00/M
Claude Opus 5.5$5.00/M$0.20/M$5.00/M$0.20/M$8.00/M$8.00/M
Claude Opus 5$6.25/M$0.50/M$6.25/M$0.50/M$10.00/M$10.00/M
Claude Opus 4.8$6.25/M$0.50/M$6.25/M$0.50/M$10.00/M$10.00/M
Claude Opus 4.7$6.25/M$0.50/M$6.25/M$0.50/M$10.00/M$10.00/M
Claude Opus 4.6$6.25/M$0.50/M$6.25/M$0.50/M$10.00/M$10.00/M
Claude Opus 4.5$6.25/M$0.50/M--$10.00/M-
Claude Opus 4.1$18.75/M$1.50/M--$30.00/M-
Claude Sonnet 5.5$2.50/M$0.20/M$2.50/M$0.20/M$4.00/M$4.00/M
Claude Sonnet 5$2.50/M$0.20/M$2.50/M$0.20/M$4.00/M$4.00/M
Claude Sonnet 4.6$3.75/M$0.30/M$3.75/M$0.30/M$6.00/M$6.00/M
Claude Sonnet 4.5$3.75/M$0.30/M$3.75/M$0.30/M$6.00/M$6.00/M
Claude Sonnet 4$3.75/M$0.30/M$7.50/M$0.60/M$6.00/M$12.00/M
Claude Sonnet 3.7$3.75/M$0.30/M--$6.00/M-
Claude Fable 5.1$12.50/M$0.25/M--$20.00/M-

OpenAI

ModelCache WriteCache ReadLong-Context Cache WriteLong-Context Cache Read
GPT-6.1 Sol-$0.10/M--
GPT-6.1 Terra$1.25/M$0.05/M-$0.10/M
GPT-6 Luna-$0.01/M-$0.02/M
GPT-6 Astra-$1.00/M-$2.00/M
GPT-6 Sol-$0.20/M-$0.40/M
GPT-5.6 Sol-$0.40/M-$0.80/M
GPT-5.6 Luna$0.25/M$0.02/M-$0.04/M
GPT-5.6 Terra-$0.20/M-$0.40/M
GPT-5.5-$0.50/M-$1.00/M
GPT-5.4-$0.25/M-$0.50/M
GPT-5.4 Mini-$0.075/M--
GPT-5.4 Nano-$0.02/M--
GPT-5.3 Codex-$0.175/M--
GPT-5.2-$0.175/M--
GPT-5.2 Chat-$0.175/M--
GPT-5-$0.125/M--
GPT-5 Mini-$0.025/M--
GPT-5 Nano-$0.005/M--
GPT-4.1-$0.50/M--
GPT-4.1 Mini-$0.10/M--
GPT-4.1 Nano-$0.025/M--
GPT-4o Mini-$0.075/M--
GPT-4o-$1.25/M--
o4-mini-$0.275/M--
o3-mini-$0.55/M--
o3-$0.55/M--
Chat-$0.125/M--

Google

ModelCache ReadLong-Context Cache Read
Gemini 4 Argon$0.10/M-
Gemini 3.8 Flash$0.075/M-
Gemini 3.5 Flash$0.15/M-
Gemini 3 Flash$0.05/M-
Gemini 2.5 Flash$0.03/M-
Gemini 3.5 Flash Lite$0.03/M-
Gemini 3.1 Flash Lite$0.025/M-
Gemini 2.5 Flash Lite$0.01/M-
Gemini 3.1 Pro (Preview)$0.20/M$0.40/M
Gemini 2.5 Pro$0.125/M$0.25/M
Gemini 2.5 Flash Image$0.03/M-

DeepSeek

ModelCache Read
DeepSeek V4.1 Flash$0.008/M

Model Lifecycle Updates

Retired Models

These models have been retired by their provider and are no longer available for new requests.

ModelRetiredReplacementNotes
Claude Haiku 3.52026-07-05claude-haiku-4-5Vertex AI retirement July 2026
Claude Sonnet 3.52026-03-01claude-sonnet-4-5Retired by Bedrock on March 1
Claude Sonnet 3.52026-03-01claude-sonnet-4-5Retired — all providers discontinued
Claude Sonnet 3.72026-05-11claude-sonnet-4-5Vertex AI retirement May 2026
DALL-E 32026-03-04gpt-image-1.5Retired by Azure on March 4
DALL-E 32026-05-12gpt-image-2Retired by OpenAI on 2026-05-12 (announced 2025-11-14). Recommended successors: gpt-image-2, gpt-image-1, or gpt-image-1-mini.
DeepSeek R12026-08-03-Azure AI Foundry serverless endpoint decommissioned; every request fails with 'Model service is unavailable'. Retirement date reflects detection (2026-08-03) — the actual endpoint delete predates that. Replacement pending product decision (see ATL-1163).
Gemini 2.0 Flash2026-06-01gemini-3.5-flashRetired by Google on 2026-06-01. Migrate to gemini-3.5-flash.
Gemini 3 Pro (Preview)2026-03-26gemini-3.1-pro-previewGoogle retired Gemini 3 Pro Preview on March 26, 2026
Imagen 32026-06-30imagen-4Vertex AI retirement June 2026
Imagen 3 Fast2026-06-30imagen-4Vertex AI retirement June 2026
Wasikan LLaMA 3.3 70B2026-03-18wasikan-ai-80bReplaced by Wasikan Qwen3-Next-80B-A3B-Instruct

Upcoming Retirements

These models have announced retirement dates. Plan migration to the recommended replacement.

ModelRetirement DateReplacementStatus
Claude Sonnet 4.52026-11-30claude-sonnet-5-5Deprecated
Claude Opus 42026-05-14claude-opus-4-6Deprecated
Claude Opus 4.12026-08-05claude-opus-4-6Sunset
Claude Fable 52026-09-01claude-fable-5-1Deprecated
Claude Sonnet 42026-05-14claude-sonnet-4-6Deprecated
Gemini 2.5 Flash2026-10-16gemini-3-flashDeprecated
Gemini 3.6 Flash2026-11-19gemini-3.8-flashDeprecated
Gemini 3.7 Flash2027-01-28gemini-3.8-flashSunset
Gemini 2.5 Flash Lite2026-10-16gemini-3.1-flash-liteSunset
Gemini 2.5 Pro2026-10-16gemini-3.1-pro-previewDeprecated
Gemini 2.5 Pro2026-10-16gemini-3.1-pro-previewDeprecated
Imagen 42026-06-30gemini-2.5-flash-imageDeprecated
Imagen 4 Ultra2026-06-30gemini-2.5-flash-imageDeprecated
o3-mini2026-08-02o4-miniSunset
Whisper2027-02-26gpt-transcribeSunset
GPT-4o Mini2027-04-14gpt-4.1-miniSunset
GPT-4o2026-09-30gpt-5.1Sunset
Claude Sonnet 4.52026-11-30claude-sonnet-5-5Deprecated
Claude Sonnet 4.52026-11-30claude-sonnet-5-5Deprecated
GPT-4o2026-06-01gpt-4o-transcribeDeprecated
Claude Sonnet 4.52026-11-30claude-sonnet-5-5Deprecated
Gemini 3.6 Flash2026-11-19gemini-3.8-flashDeprecated

For provider-specific deprecation schedules, see:
Azure OpenAI |
Anthropic |
Google Gemini |
AWS Bedrock


Pricing is subject to change. Costs shown are per million tokens (M) unless otherwise specified.

This page is automatically updated when new models are deployed to production.


Did this page help you?