The model library
52 text and code models, every one behind the same API key, balance, and rate-limit envelope. Newest first, with the date each went live here. Prices are exact and shown before you call.
- Models
- 52
- Providers
- 14
- Input from
- $0.04per 1M tokens, Decider 27B
- Latest
- GPT-6.2 Astraadded 18 Nov 2026
Text & Code48
Frontier and open-weights chat models behind the OpenAI-compatible endpoint.
- GPT-6.2 AstraOpenAI's frontier GPT for the hardest professional work, 20% below GPT-6 Astra at $8 / $40 per 1M tokens.1.05M$8.00$40.0018 Nov 2026
- GPT-6.2 SolOpenAI's everyday GPT for coding and agents, smarter than GPT-6.1 Sol at the same $2 / $10 per 1M tokens.1.05M$2.00$10.0018 Nov 2026
- Qwen4-MaxAlibaba's next-generation flagship Qwen: multimodal input, deep reasoning and tool calling across a 1M-token window, at $1.50 / $4.50 per 1M tokens.1M$1.50$4.5016 Nov 2026
- Gemini 4 CarbonGoogle DeepMind's strongest reasoning model, built for sustained agentic coding, multimodal knowledge work, scientific reasoning and cybersecurity defense. Introductory price until 30 November.1.05M$2.00$10.0012 Nov 2026
- Gemini 4 HydrogenGoogle DeepMind's fast, efficient Gemini 4 model for everyday coding and agentic work: four thinking levels and a 1M-token window at one flat price.1.05M$1.50$7.5012 Nov 2026
- Claude Fable 5.2Anthropic's most capable generally available Claude, for demanding reasoning and long-horizon agentic work, at 20% below Fable 5.1.1M$8.00$40.009 Nov 2026
- Kimi K3.1 ProMoonshot's 3T-class open-weight flagship with a 1M context window, built for coding, 3D and financial agents.1.05M$2.00$10.0026 Oct 2026
- Kimi K3.1 Pro HighspeedK3.1 Pro at 2-3x the speed for responsive interactive agents, at twice the price.1.05M$4.00$20.0026 Oct 2026
- MiMo-V2.6-FlashXiaomi's low-cost, full-modality reasoning model for high-frequency calls and large-scale professional workloads.1.05M$0.14$0.2821 Oct 2026
- MiMo-V2.6-Pro-UltraspeedMiMo-V2.6-Pro's flagship quality with output up to 20x faster, for real-time and latency-sensitive work.1.05M$4.35$8.7021 Oct 2026
- Gemini 4 ArgonGoogle DeepMind's frontier model for long-horizon coding, legal, finance and science work, #1 on the Vals Index at launch. Introductory price until 30 November.1.05M$2.00$10.0013 Oct 2026
- GLM-LegalComing soonZ.ai's legal model, built on GLM-5.3-Flash, for contract review, evidence analysis and compliance. API access by application for now.—TBAAnnounced 12 Oct
- Muse WonderMeta's first frontier model family, built for long-running personal and professional agent work, served by Meta directly.1.05M$4.00$20.0012 Oct 2026
- Claude Haiku 5.5Anthropic's cheapest and fastest Claude: a big step up from Haiku 4.5 in coding, computer use and knowledge work, at $0.10 / $0.50 per 1M tokens for prompts up to 100K.1M$0.10$0.507 Oct 2026
- Mistral Large 4PreviewMistral's 1-trillion-parameter open-weight flagship (52B active), text and image in, trained in Europe: the best open-weight model for coding, strong at defensive cybersecurity, with low, medium and high reasoning modes. Weights released; still a public preview on the API.524K$0.70$2.106 Oct 2026
- Claude Sonnet 5.5The fast Claude 5.5: near-Opus coding and knowledge work, 30%+ faster than Sonnet 5, at half Opus 5.5's price.1M$2.00$10.0028 Sep 2026
- GPT-4.1 miniOpenAI's April 2025 small model with a million-token window, still running inside a lot of production agents. Keep it as your baseline and test newer models against it on the same key.1.05M$0.40$1.6027 Sep 2026
- GLM-5.3Z.ai's flagship coding and agent model, GLM-5.2's base post-trained further, at the same price.1M$1.40$4.4023 Sep 2026
- Muse Spark 1.3Meta Superintelligence Labs' frontier model, fourth on the Artificial Analysis index, served by Meta directly.1.05M$1.25$4.2523 Sep 2026
- Claude Opus 5.5First of the Claude 5.5 generation: Fable-class agentic coding and computer use at 20% below Opus 5.1M$4.00$20.0022 Sep 2026
- GPT-6 LunaGPT-6's high-volume tier: the cheapest frontier-family model in the catalog, with a million-token window.1.05M$0.10$0.5022 Sep 2026
- GPT-6 SolGPT-6 for complex coding and agent work at a fifth of Astra's price, with the same million-token window.1.05M$2.00$10.0022 Sep 2026
- MiMo-V2.6-ProXiaomi's trillion-parameter flagship: frontier-class agentic coding on the price/intelligence Pareto line.1.05M$0.435$0.8716 Sep 2026
- Gemini 3.1 Flash-LiteGoogle's cheapest text model here, for high-volume classification and extraction.—$0.25$1.5011 Sep 2026
- Gemini 3.5 Flash-LiteCost-efficient Gemini for high-volume agentic work, translation and simple data processing.—$0.30$2.5011 Sep 2026
- Gemini 3.6 FlashThe previous-generation Flash, balancing speed and multimodal work across everyday agentic tasks.—$0.75$3.7511 Sep 2026
- Gemini 3.8 FlashGoogle's most capable Flash model, built for long-horizon software engineering and autonomous agents.—$0.75$3.7511 Sep 2026
- DeepSeek V4.1 FlashDeepSeek's cheapest current model, a million-token window at flash rates.1M$0.30$1.2010 Sep 2026
- GLM-5.3-FlashNative multimodal coding model at the lowest rate in the catalog.1M$0.15$0.5010 Sep 2026
- GPT-6 AstraOpenAI's GPT-6 flagship, a million-token window one key away.1.05M$10.00$50.003 Sep 2026
- Claude Fable 5.1Anthropic's top generally available model, tied for first on the Artificial Analysis Intelligence Index.1M$10.00$50.001 Sep 2026
- Gemini 3 Flash (preview)PreviewThe Gemini 3 Flash preview line.1.05M$0.50$3.0030 Aug 2026
- Gemini 3.1 Pro (preview)PreviewGoogle's newest Pro tier, shipped as a preview.1.05M$2.00$12.0030 Aug 2026
- Gemini 3.7 FlashGoogle's current fast model, million-token context.1.05M$0.75$3.7530 Aug 2026
- Grok 4.3Million-token context at roughly half the flagship rate.1M$1.25$2.5030 Aug 2026
- Grok 4.5The previous flagship, same rate card.500K$2.00$6.0030 Aug 2026
- Grok 4.6xAI's flagship, half-million-token context.500K$2.00$6.0030 Aug 2026
- Claude Fable 5Anthropic's first Mythos-class model, the new flagship tier above Opus, tuned for the hardest reasoning and agentic work.200K$10.00$50.005 Aug 2026
- Claude Opus 5The Claude 5 generation's deep-work model, maximum-capability reasoning for research, architecture, and hard agentic tasks.200K$5.00$25.005 Aug 2026
- GLM-5.2Z.ai's open-weight frontier challenger, strong coding and reasoning with one of the best free tiers in class.128K$1.40$4.401 Aug 2026
- DeepSeek V4 ProRetired by DeepSeek on 14 Sep 2026. Requests are served by V4.1 Flash from then, and billed at Flash's rate.1.05M$1.32$3.9615 Jul 2026
- Kimi K2.6Moonshot's value tier, K3-style agentic tool-calling at half the price, a favorite for high-volume agent loops.256K$0.95$4.0020 Jun 2026
- Claude Haiku 4.5Fast, cheap frontier-family model for high-volume tasks.200K$1.00$5.001 Jun 2026
- Claude Opus 4.6The frontier tier for the hardest reasoning and agentic work.200K$5.00$25.001 Jun 2026
- Claude Sonnet 4.5RetiringFrontier-quality text and reasoning through one OpenAI-compatible endpoint.200K$3.00$15.001 Jun 2026
- GPT-5.5OpenAI's flagship, one key away.256K$5.00$30.001 Jun 2026
- Kimi K3Agentic coding model with strong multi-step tool use.256K$3.00$15.001 Jun 2026
- Mistral Medium 3.5Mistral's flagship 128B dense model, chat, reasoning and coding merged into one, served from the EU.262K$1.50$7.5028 Apr 2026
Jev Decisions4
System One models: state plus typed questions in, calibrated probabilities out, no generated text. POST /v1/decisions.
- Gemini Decision 1Google's decision model: typed answers with calibrated probabilities over text, images, audio, video and PDFs, $0.10 per million input tokens and free output.262K$0.10Free11 Nov 2026
- Microsoft-Decision-1Microsoft's decision model: typed answers with calibrated probabilities, first on accuracy and the fastest measured in Microsoft's 36-benchmark comparison.33K$0.042Free9 Oct 2026
- Decider 27BPerplexity's decision model: typed answers with probabilities, text or image state, $0.04 per million input tokens and free output.—$0.04Free1 Oct 2026
- JevTyped decisions with calibrated probabilities in about 100 ms. No generated text, so nothing to parse and nothing to hallucinate.32K$0.042Free15 Sep 2026
By provider
Each provider's full lineup, on one page.
One key. Every model. Exact prices.
Every model on this page is live behind api.companyfabric.com. Free starter credits included, no subscription required.