Text models at $0.15 per million input tokens or less, several of which still run inside enclaves.
One ID for free inference. Automatically selects a healthy, eligible free model that fits your request, prioritizing model quality and using observed success rates to break ties. No paid fallback.
GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.
Free access to North Mini Code on limited shared capacity. Anonymous route; account opt-in required.
Free access to Dots3 Note Preview on limited shared capacity. Anonymous route; account opt-in required.
Free access to Gemma 4 26B A4B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Llama 3.1 8B Instruct on limited shared capacity. Anonymous route; account opt-in required.
Free access to Mistral Small 3.1 24B on limited shared capacity. Anonymous route; account opt-in required.
Free access to GPT OSS 120B on limited shared capacity. Anonymous route; account opt-in required.
Free access to GPT OSS 20B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Qwen3 30B A3B on limited shared capacity. Anonymous route; account opt-in required.
Free access to Beam on limited shared capacity. Anonymous route; account opt-in required.
Free access to GLM 4.5 Flash on limited shared capacity. Anonymous route; account opt-in required.
Meta Llama 3.1 8B Instruct Turbo is a faster serving variant of Llama 3.1 8B Instruct, Meta's small multilingual instruction-tuned text model. The model has a 128K-token context window, officially supports eight languages and supports tool use.
12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Voxtral Mini 3B is a text model.
L3 8B Lunaris v1 Turbo is a faster serving variant of Lunaris v1, Sao10K's 8B generalist and roleplay model. Lunaris is a merge of four Llama 3 8B fine-tunes on Meta Llama 3 8B Instruct, aimed at better creativity and logic than Sao10K's Stheno v3.2.
GPT-5 Nano is the fastest, lowest-cost version of OpenAI's GPT-5 reasoning model, suited to summarization and classification tasks. It takes text and image input and produces text output, with a 400K-token context window and up to 128K output tokens.
Mercury 2.5 is a diffusion-based reasoning model from Inception with fast parallel token generation, tunable reasoning, tool calling, and structured output support.
Gemma 3 12B Instruct is the 12-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Gemma 3 4B Instruct is the 4-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.
Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.
Granite 4.2 8B is IBM's 8B-parameter dense reasoning model in the open-weight Granite 4.2 family, for reasoning, code generation, tool calling and agentic workflows. It takes text input and produces text output with a 128K-token native context, and offers full thinking, non-thinking and low-effort thinking modes per request.
Ling 3.0 Flash is inclusionAI's hybrid reasoning model, a hybrid-linear Mixture-of-Experts with 124B total and 5.1B active parameters built for efficient agentic workflows such as coding and deep research. It takes text input and output with a 256K-token context window, and its thinking mode can be turned off per request.
Ling 3.0 Flash VL is inclusionAI's multimodal version of Ling 3.0 Flash, a Mixture-of-Experts model with 124B total and 5.5B active parameters. It takes text, image and video input and produces text with a context of up to 256K tokens, and is built for document and chart understanding, GUI agents and long-video question answering.
NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.
NVIDIA Nemotron Nano 9B v2 is an open 9B-parameter reasoning and chat model from NVIDIA, built on a hybrid Mamba-2 and Transformer architecture with only four attention layers. It was produced by pruning and aligning the 12B Nemotron Nano v2 base model. It handles text input and output with up to 128K tokens of context and supports tool calling. Reasoning is on by default and can be switched off, and an optional thinking budget caps reasoning tokens.
Phi-4 is Microsoft's 14B-parameter dense decoder-only language model, trained on a blend of synthetic data, filtered public web content and academic books and Q&A data with a focus on reasoning. It takes text input and produces text output with a 16K-token context window and is intended primarily for English.
gpt-oss-safeguard-20b is the smaller open-weight safety reasoning model from OpenAI, fine-tuned from gpt-oss-20b, with about 21B total parameters and 3.6B active. It reads a developer-written safety policy at inference time and classifies content against it with a visible chain of thought, for lower-latency trust and safety tasks such as input and output filtering and content labeling. It supports low, medium and high reasoning effort and is released under Apache 2.0.
GLM 4.7 Flash is a text model.
NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
DeepSeek V4 Flash (Preview) is the April 2026 preview release of DeepSeek's efficiency-focused Mixture-of-Experts model, with 284B total and 13B active parameters and a 1M-token context window. It offers a non-thinking mode and two thinking levels (high and max) for fast reasoning and coding workloads.
Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
Seed 2.0 Mini is the throughput-optimized model in ByteDance Seed's Seed 2.0 family, built for low-latency, high-concurrency and batch workloads. It supports multimodal understanding, tool calling and four thinking levels from minimal to high, with a 256K-token context window.
Gemini 2.5 Flash-Lite is Google's cost-efficient multimodal model in the Gemini 2.5 family, built for high-frequency, lightweight tasks such as high-volume classification and simple data extraction. It takes text, image, video, audio and PDF input and produces text output, with a 1M-token context window and thinking support.
Mercury 3 is Inception's most capable diffusion-based reasoning model, generating over 1,000 tokens per second with a 1M-token context window, tunable reasoning, tool calling, and structured output support.
GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.
Mistral Small 3.2 is a 24B open-weight model from Mistral AI that accepts text and image input, released in June 2025 as a minor update to Mistral Small 3.1. It improves instruction following, produces fewer repetitive or infinite generations, and has a more robust function-calling template.
Llama 3.3 70B Instruct is Meta's 70B-parameter multilingual instruction-tuned model, tuned for assistant-style dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai. It takes text input and produces text and code with a 128K-token context window. This Turbo variant is a faster serving variant of Llama 3.3 70B Instruct.
Llama 4 Scout is Meta's natively multimodal Mixture-of-Experts model with 17B active parameters, 16 experts and 109B total parameters. It takes text and image input and produces text and code with a context window of up to 10M tokens, and is built for assistant chat and visual reasoning such as captioning and image question answering.
Ministral 3 3B Instruct is the instruction-tuned 3B model in Mistral AI's Ministral 3 family of small dense open-weight models, combining a 3.4B language model with a 0.4B vision encoder. It takes text and image input and produces text output, with native function calling and JSON output, and support for 11 languages. It is built for edge and local deployment, and for tasks such as image captioning, classification, translation and data extraction.
Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.
Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.
Kolibri 1 is a text model.
Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Qwen3 14B is a dense 14.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
Qwen3 30B A3B is a Mixture-of-Experts model in the Qwen3 family with 30.5B total and 3.3B active parameters from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
GLM 5.3 Flash Uncensored is a text model.
Qwen 3.8 Flash is an efficient multimodal model from Alibaba's Qwen team, built on the open-weight Qwen3.8 Flash Next Mixture-of-Experts model with 125B total and 6B active parameters. It accepts text, image and video input with a 1M-token context window, supports function calling and structured output, and has a thinking mode that can be turned off.
Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
