$1.40 / Mtok in 202,800 ctx open-weights

Context Indexed

GLM 5.2

Accounts

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$1.40 / Mtok in 1,048,575 ctx open-weights

Context Indexed

GPT OSS 120B

Accounts

Kimi coding model for software agents, refactors, and repository reasoning

$1.90 / Mtok in 262,000 ctx open-weights

Context Indexed

Jamba Large 1.7

Ai21

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer a

$2.00 / Mtok in 256,000 ctx open-weights

Context Indexed

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

$5.00 / Mtok in 1,000,000 ctx closed

Coding

Claude Opus 4.6

Anthropic

Claude Opus Latest

Anthropic

This model always redirects to the latest model in the Claude Opus family.

$5.00 / Mtok in 1,000,000 ctx closed

Vision Indexed

Claude-Sonnet-3.5-June

Anthropic

Legacy model retained for compatibility with older integrations

$2.60 / Mtok in 189,096 ctx closed

Vision Indexed

Anthropic

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c

$3.00 / Mtok in 1,000,000 ctx closed

Vision Indexed

Baichuan

Baidu

Multimodal reasoning model for visual analysis, planning, and tool use

$0.840 / Mtok in 128,000 ctx closed

Context Indexed

Kimi K2 0711 Instruct FP4

Baseten

Kimi model for long-context chat, coding, and agentic reasoning

$0.100 / Mtok in 128,000 ctx closed

Vision Indexed

FLUX.2 Klein 4B

Black Forest Labs

Image model for prompt-driven generation, editing, and visual design workflows

$1.00 / Mtok in 128,000 ctx open-weights

Vision Indexed

Seed 1.6

Bytedance

Multimodal reasoning model for visual analysis, planning, and tool use

$0.250 / Mtok in 256,000 ctx closed

Context Indexed

Bytedance Seed

Tool-capable chat model for instruction following and agentic application workflows

$0.210 / Mtok in 262,000 ctx closed

Vision Indexed

UI-TARS 7B

Open Llama multimodal model for image understanding and text reasoning

$0.049 / Mtok in 128,000 ctx open-weights

Vision Indexed

Llama 4 Scout 17B 16E Instruct

Cf

Open Llama with long-context vision for efficient multimodal agents

$0.270 / Mtok in 131,000 ctx open-weights

Context Indexed

Llama Guard 3 8B

Cf

Safety model for policy screening, moderation, and risk-aware routing workflows

$0.484 / Mtok in 131,072 ctx open-weights

Context Indexed

Mistral Small 3.1 24B Instruct

Cf

Efficient Mistral model for fast chat, extraction, and production assistants

$0.351 / Mtok in 128,000 ctx open-weights

Vision Indexed

Kimi K2.6

Cf

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

$0.950 / Mtok in 262,144 ctx open-weights

Vision Indexed

Kimi K2.7 Code

Cf

Chutesai

Efficient Mistral model for fast chat, extraction, and production assistants

$0.200 / Mtok in 128,000 ctx closed

Context Indexed

C

Uncensored

Cognitivecomputations

Cohere

Deepcogito

DeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designe

$0.435 / Mtok in 1,048,576 ctx open-weights

Vision Indexed

E

ElevenLabs-v2.5-Turbo

Elevenlabs

Speech generation model for controllable voice, narration, and audio delivery

$0 / Mtok in 128,000 ctx closed

Vision Indexed

E

ElevenLabs-v3

Elevenlabs

Speech generation model for controllable voice, narration, and audio delivery

$0 / Mtok in 128,000 ctx closed

Vision Indexed

DeepSeek-V4-Pro-EL

Empiriolabs

Flagship DeepSeek model for coding, reasoning, and agentic work

$1.67 / Mtok in 1,000,000 ctx open-weights

Vision Indexed

DeepSeek-V4-Flash-EL

Empiriolabs

Fast DeepSeek model for efficient chat, coding help, and agent loops

$0.140 / Mtok in 1,000,000 ctx open-weights

Context Indexed

E

RNJ-1 Instruct 8B

Essentialai

Gemini 2.5 Flash

Google

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinki

$0.300 / Mtok in 1,048,576 ctx closed

Best for: High-throughput multimodal and extraction jobs

Vision Indexed

Gemini 2.5 Pro Preview 05-06

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

$1.25 / Mtok in 1,048,576 ctx closed

Vision Indexed

Gemini 2.5 Pro Preview 06-05

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

$1.25 / Mtok in 1,048,576 ctx closed

Reason

Gemini 2.5 Pro

Google

Grok 4.3

Grok

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

$1.25 / Mtok in 1,000,000 ctx closed

Context Indexed

G

Compound Mini

Groq

Qwen3.6 27B

Hf Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

$0.450 / Mtok in 262,144 ctx open-weights

Context Indexed

Kilo Auto

Automatic model router for matching prompts to suitable backends and budgets

$0.050 / Mtok in 400,000 ctx closed

Vision Indexed

Meituan

Meta

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active

$0.200 / Mtok in 1,048,576 ctx open-weights

Best for: Teams that want open-weight flexibility with hosted convenience

Vision Indexed

Llama 4 Scout 17B 16E

Meta

Open multimodal Llama model for long-context analysis and efficient agents

$0.110 / Mtok in 131,072 ctx open-weights

Cheap

Llama 4 Scout

Meta

DeepSeek V3.1 Nex N1

Nex Agi

DeepSeek chat model for instruction following, coding, and analysis

$0.280 / Mtok in 128,000 ctx closed

Vision Indexed

N

Nex-N2-Mini

Nex Agi

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool

$0.025 / Mtok in 262,144 ctx open-weights

Vision Indexed

N

Nex-N2-Pro

Nex Agi

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and

$0.250 / Mtok in 262,144 ctx open-weights

Context Indexed

DeepHermes-3 Mistral 24B (Preview)

Nousresearch

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates so

$2.00 / Mtok in 128,000 ctx closed

Vision Indexed

Sonar Pro

Perplexity

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona

$3.00 / Mtok in 200,000 ctx closed

Vision Indexed

Poolside

Free provider route for experiments, demos, and cost-sensitive chat workloads

$0 / Mtok in 262,144 ctx open-weights

Context Indexed

P

Prime Intellect: INTELLECT-3

Prime Intellect

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

$0.200 / Mtok in 131,072 ctx open-weights

Context Indexed

Pro/deepseek-ai/DeepSeek-R1

Pro

Vision Indexed

Qwen3 VL 8B Thinking

Qwen

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, an

$0.117 / Mtok in 256,000 ctx open-weights

Context Indexed

R

Relace Apply 3

Relace

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your fil

$0.850 / Mtok in 256,000 ctx closed

Context Indexed

R

Relace Search

Relace

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search pe

$1.00 / Mtok in 256,000 ctx closed

Vision Indexed

S

Fugu Ultra

Sakana

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model t

$5.00 / Mtok in 1,000,000 ctx closed

Context Indexed

Llama-xLAM-2 70B fc-r

Salesforce

Open Llama instruction model for multilingual chat, reasoning, and coding

$2.50 / Mtok in 128,000 ctx closed

Context Indexed

Step 3.5 Flash 2603

Stepfun Ai

StepFun flash model for efficient multimodal reasoning, coding, and tool use

$0.100 / Mtok in 256,000 ctx closed

Context Indexed

stepfun-ai/Step-3.5-Flash

Stepfun Ai

Tee

Multimodal reasoning model for visual analysis, planning, and tool use

$0.300 / Mtok in 131,072 ctx closed

Context Indexed

Hunyuan A13B Instruct

Tencent

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thou

$0.140 / Mtok in 131,072 ctx open-weights

Context Indexed

Hy3 (free)

Tencent

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It

$0 / Mtok in 262,144 ctx open-weights

Context Indexed

Hy3 preview

Tencent

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled,

$0.063 / Mtok in 262,144 ctx open-weights

Context Indexed

Hy3

Tencent

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It

$0.200 / Mtok in 262,144 ctx open-weights

Context Indexed

T

Anubis 70B v1.1

Thedrummer

General-purpose chat model for instruction following, writing, and analysis

$0.310 / Mtok in 131,072 ctx closed

Context Indexed

T

Cydonia 24B V4.1

Thedrummer

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

$0.300 / Mtok in 131,072 ctx open-weights

Vision Indexed

T

TheDrummer Skyfall 31B v4.2

Thedrummer

Multimodal model for analyzing text, images, documents, and rich media

$0.550 / Mtok in 131,072 ctx closed

Vision Indexed

T

Inkling

Thinkingmachines

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning

$1.00 / Mtok in 1,048,576 ctx open-weights

Context Indexed

GLM 4 32B 0414

Thudm

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$0.200 / Mtok in 128,000 ctx closed

Context Indexed

GLM Z1 32B 0414

Thudm

solar-10.7b-instruct

Upstage

Open-weight instruction model for adaptable chat and self-hosted production workloads

$0 / Mtok in 128,000 ctx open-weights

Vision Indexed

Doubao-Seed-1.8

Volcengine

Volcengine

Xiaomimimo

Zhipuai

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$0 / Mtok in 131,072 ctx open-weights

Context Indexed

GLM-4.6

Zhipuai

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

$0 / Mtok in 202,752 ctx open-weights