GoogleGoogle 4.6TrustPilotTrustPilot 4.9

Every model, unlimited possibilities

Frontier and open models, pre-warmed and ready. Route to any of them from a single Claws endpoint, swap providers without rewriting a line. Here’s what’s powering agents this week.

479 models online69 providers312ms median P95
All models
Ranked by live usage across every hosted agent this week. Filter by capability, every model routes through the same single endpoint.
OpenAI: GPT-6.2 Astra Pro
OpenAI
NEW
gpt-6.2-astra-pro
1 Credit = 1,250 Tokens
Long ContextVision

GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mod…

Anthropic: Claude Fable 5.2
Anthropic
NEW
claude-fable-5.2
1 Credit = 1,250 Tokens
Long ContextVision

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning,…

OpenAI: GPT Astra Latest
Community
gpt-astra-latest
1 Credit = 1,250 Tokens
Long ContextVision

This model always redirects to the latest model in the GPT Astra family.

Google: Gemini 4 Neon
Google
NEW
gemini-4-neon
1 Credit = 3,333 Tokens
Long ContextVision

Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.

Meta: Muse Wonder
Meta
muse-wonder
1 Credit = 2,500 Tokens
Long ContextVision

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks.

Sakana: Fugu Ultra v2
Community
fugu-ultra-v2
1 Credit = 2,000 Tokens
Long ContextVision

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.

Xiaomi: MiMo-V2.6-Pro-UltraSpeed
Xiaomi
mimo-v2.6-pro-ultraspeed
1 Credit = 2,299 Tokens
Long ContextVision

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.

Qwen: Qwen4 Max
Alibaba
NEW
qwen4-max
1 Credit = 7,018 Tokens
Long ContextReasoning

Qwen4 Max is the flagship model in Alibaba's Qwen4 series.

Baidu: ERNIE-Light-DT-1.0
Community
NEW
ernie-light-dt-1.0-intl
1 Credit = 8,850 Tokens
Long Context

ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model.

Pareto 26.9
Community
pareto-26.9
1 Credit = 4,000 Tokens
Long ContextVision

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

Fireworks: Ember-1
Community
ember-1
1 Credit = 3,333 Tokens
Long ContextVision

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).

AionLabs: Aion 3.5
Community
aion-3.5
1 Credit = 3,333 Tokens
Long Context

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Tencent: Hy4 flash
Tencent
NEW
hy4-flash
1 Credit = 285,714 Tokens
Long ContextVision

Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flag…

Anthropic: Claude Fable Latest
Community
claude-fable-latest
1 Credit = 1,250 Tokens
Long ContextVision

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

Thinking Machines: Inkling 2 Small
Community
NEW
inkling-2-small
1 Credit = 33,333 Tokens
Long ContextReasoning

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters ou…

inclusionAI: Ling 3.2 Flash (free)
Community
NEW
ling-3.2-flash:free
Pricing on request
Long ContextVision

Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 2…

Nex AGI: Nex-N2.6
Community
NEW
nex-n2.6
1 Credit = 83,333 Tokens
Long ContextVision

Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B pa…

Z.ai: GLM 5.3 FlashX Legal
Z.ai
NEW
glm-5.3-flashx-legal
1 Credit = 27,027 Tokens
Long ContextVision

GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, an…

KT: Mi:dm K 3.0 Pro
Community
NEW
midm-k-3.0-pro
1 Credit = 50,000 Tokens
Long Context

Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters.

Motif Technologies: Motif 3
Community
NEW
motif-3
1 Credit = 33,333 Tokens
Long Context

Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters.

LiquidAI: LFM3-1.7B
Community
NEW
lfm-3-1.7b
1 Credit = 125,000 Tokens
Long Context

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs.

Ricursive: Ripple 65B Preview
Community
NEW
ripple-65b-preview
1 Credit = 100,000 Tokens
Long Context

Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

SpaceXAI: Grok 4.7
xAI
grok-4.7
1 Credit = 5,000 Tokens
Long ContextReasoning

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

MoonshotAI: Kimi K3.1 Pro (batch)
Community
NEW
kimi-k3.1-pro:batch
1 Credit = 26,882 Tokens
Long ContextVision

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token c…

Pareto Latest
Community
pareto-latest
1 Credit = 12,500 Tokens
Long ContextVision

This model always redirects to the latest model in the Pareto family.

Particle AI: Particle-1
Community
NEW
particle-1
1 Credit = 166,667 Tokens
Long ContextVision

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.

Elorian: Glimpse
Community
glimpse
1 Credit = 16,667 Tokens
Long ContextVision

Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical…

StepFun: Step 5 Preview
Community
step-5-preview
1 Credit = 10,000 Tokens
Long ContextVision

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total p…

MiniMax: MiniMax M3.1 Flash
Community
minimax-m3.1-flash
1 Credit = 66,667 Tokens
Long ContextVision

MiniMax-M3.1-Flash is a multimodal model from MiniMax.

Recursive: Flint (free)
Community
NEW
flint-v1.0:free
Pricing on request
Long Context

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's…

Moondream: Moondream 3 Preview
Community
moondream3-preview
1 Credit = 33,333 Tokens
Mid ContextVision

Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts).

Reflection: Beam 1.0 501B A23B
Community
beam-1.0-501b-a23b
1 Credit = 40,000 Tokens
Long Context

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

Mistral: Mistral Large 4
Mistral
mistral-large-4-0
1 Credit = 14,286 Tokens
Long ContextVision

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

DeepSeek: DeepSeek V4.1 Flash 1017
DeepSeek
deepseek-v4.1-flash-1017
1 Credit = 66,667 Tokens
Long ContextVision

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model…

NVIDIA: Nemotron 3.5 Super VL
Community
nemotron-3.5-super-vl
1 Credit = 66,667 Tokens
Long ContextVision

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

PrismML: Ternary Bonsai 2 9B
Community
ternary-bonsai-2-9b
1 Credit = 125,000 Tokens
Long ContextVision

Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use.

ScaleDown: Summarize
Community
summarize
1 Credit = 250,000 Tokens
Long ContextVision

Summarize is an abstractive summarization model from ScaleDown.

Cohere: Command A+
Cohere
command-a-plus
1 Credit = 33,333 Tokens
Mid ContextVision

Command A+ is Cohere's flagship model for enterprise agentic workflows.

Perceptron: Perceptron Mk1.5
Community
perceptron-mk1.5
1 Credit = 66,667 Tokens
Mid ContextVision

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents.

Upstage: Solar Mini 4
Community
solar-mini4
1 Credit = 200,000 Tokens
Long Context

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K…

DeepSeek: DeepSeek Pro Latest
Community
deepseek-pro-latest
1 Credit = 100,100 Tokens
Long Context

This model always redirects to the latest model in the DeepSeek Pro family.

Inference.net: Schematron V2 Small
Community
schematron-v2-small
1 Credit = 200,000 Tokens
Mid Context

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

IBM: Granite 4.2 8B
Community
granite-4.2-8b
1 Credit = 166,667 Tokens
Mid Context

Granite 4.2 8B is a dense reasoning model from IBM.

Z.ai: GLM Flash Latest
Community
glm-flash-latest
1 Credit = 250,627 Tokens
Long ContextVision

This model always redirects to the latest model in the GLM Flash family.

ByteDance Seed: Seed 2.1 Turbo
Community
seed-2-1-turbo
1 Credit = 20,000 Tokens
Long ContextVision

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows.

xAI: Grok Latest
Community
grok-latest
1 Credit = 5,000 Tokens
Long ContextVision

This model always redirects to the latest Grok model from xAI.

Dots Studio: Dots3-Note Preview (free)
Community
dots-3-note-preview:free
Pricing on request
Long ContextVision

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.

Meituan: LongCat 2.0
Community
longcat-2.0
1 Credit = 33,333 Tokens
Long Context

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.

Google: Gemini Pro Latest
Community
gemini-pro-latest
1 Credit = 5,000 Tokens
Long ContextReasoning

This model always redirects to the latest model in the Gemini Pro family.

MoonshotAI: Kimi Latest
Community
kimi-latest
1 Credit = 54,825 Tokens
Long ContextVision

This model always redirects to the latest model in the Kimi family.

Reka Edge
Community
reka-edge
1 Credit = 100,000 Tokens
Vision

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.

Writer: Palmyra X5
Community
palmyra-x5
1 Credit = 16,667 Tokens
Long Context

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise.

Free Models Router
Community
free
Pricing on request
Long ContextVision

The simplest way to get free inference.

Perplexity: Sonar Pro Search
Perplexity
sonar-pro-search
1 Credit = 3,333 Tokens
Long ContextVision

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system.

Amazon: Nova Premier 1.0
Community
nova-premier-v1
1 Credit = 4,000 Tokens
Long ContextVision

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for dis…

Magnum v4 72B
Community
magnum-v4-72b
1 Credit = 4,000 Tokens
Mid Context

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anth…

Relace: Relace Search
Community
relace-search
1 Credit = 10,000 Tokens
Long Context

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 re…

Nous: Hermes 4 405B
Community
hermes-4-405b
1 Credit = 10,000 Tokens
Mid Context

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.

Morph: Morph V3 Large
Community
morph-v3-large
1 Credit = 11,111 Tokens
Long Context

Morph's high-accuracy apply model for complex code edits.

Sao10K: Llama 3.1 Euryale 70B v2.2
Community
l3.1-euryale-70b
1 Credit = 11,765 Tokens
Mid ContextReasoning

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k).

Meta: Llama 3.1 70B Instruct
Meta
llama-3.1-70b-instruct
1 Credit = 13,889 Tokens
Mid Context

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.

TheDrummer: Skyfall 36B V2
Community
skyfall-36b-v2
1 Credit = 18,182 Tokens
Mid Context

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-pla…

Mancer: Weaver (alpha)
Community
weaver
1 Credit = 33,333 Tokens
Mid Context

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory.

ReMM SLERP 13B
Community
remm-slerp-l2-13b
1 Credit = 33,333 Tokens
Mid Context

A recreation trial of the original MythoMax-L2-B13 but with updated models.

Venice: Uncensored
Community
dolphin-mistral-24b-venice-edition
1 Credit = 50,000 Tokens
Mid Context

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in…

ByteDance: UI-TARS 7B
Community
ui-tars-1.5-7b
1 Credit = 100,000 Tokens
Mid ContextVision

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobil…

MythoMax 13B
Community
mythomax-l2-13b
1 Credit = 125,000 Tokens
Mid Context

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.

Microsoft: Phi 4
Microsoft
phi-4
1 Credit = 142,857 Tokens
Mid Context

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations w…

TypeSafe: Jev Router
Community
jev-router
Pricing on request
Long ContextVision

Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.

OpenAI: GPT-6.2 Astra
OpenAI
NEW
gpt-6.2-astra
1 Credit = 1,250 Tokens
Long ContextVision

GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.

Anthropic: Claude Fable 5.1
Anthropic
claude-fable-5.1
1 Credit = 1,000 Tokens
Long ContextVision

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…

OpenAI: GPT Sol Latest
Community
gpt-sol-latest
1 Credit = 5,000 Tokens
Long ContextVision

This model always redirects to the latest model in the GPT Sol family.

Google: Gemini 4 Carbon
Google
NEW
gemini-4-carbon
1 Credit = 5,000 Tokens
Long ContextVision

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.

Meta: Muse Ember
Meta
NEW
muse-ember
1 Credit = 100,000 Tokens
Long ContextVision

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat…

Sakana: Fugu Max
Community
fugu-max
1 Credit = 5,000 Tokens
Long ContextVision

Fugu Max is the cost-performance model in Sakana AI's Fugu family.

Xiaomi: MiMo-V2.6-Pro
Xiaomi
mimo-v2.6-pro
1 Credit = 22,989 Tokens
Long ContextVision

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.

Qwen: Qwen3.8 Max Prime
Alibaba
qwen3.8-max-prime
1 Credit = 2,500 Tokens
Long ContextReasoning

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point.

Baidu: ERNIE-5.5-Flash-Preview (free)
Community
NEW
ernie-5.5-flash-preview:free
Pricing on request
Long Context

ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabiliti…

Pareto 26.10
Community
pareto-26.10
1 Credit = 12,500 Tokens
Long ContextVision

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

AionLabs: Aion 3.5 Mini
Community
aion-3.5-mini
1 Credit = 14,286 Tokens
Long Context

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Tencent: Hy4
Tencent
NEW
hy4
1 Credit = 23,981 Tokens
Long ContextVision

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agent…

Anthropic: Claude Opus Latest
Community
claude-opus-latest
1 Credit = 2,500 Tokens
Long ContextReasoning

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

Thinking Machines: Inkling Small
Community
inkling-small
1 Credit = 22,222 Tokens
Long ContextReasoning

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…

inclusionAI: Ling 3.1 Flash
Community
ling-3.1-flash
1 Credit = 222,222 Tokens
Long Context

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Nex AGI: Nex-N2.5-Pro
Community
nex-n2.5-pro
1 Credit = 133,333 Tokens
Long ContextVision

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes.

Z.ai: GLM 5.3 Prime
Z.ai
glm-5.3-prime
1 Credit = 5,952 Tokens
Long Context

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput…

LiquidAI: LFM3-1.7B (free)
Community
NEW
lfm-3-1.7b:free
Pricing on request
Long Context

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs.

SpaceXAI: Grok 4.7 (batch)
xAI
grok-4.7:batch
1 Credit = 6,250 Tokens
Long ContextReasoning

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

MoonshotAI: Kimi K3.1 Pro
Community
NEW
kimi-k3.1-pro
1 Credit = 39,526 Tokens
Long ContextVision

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token c…

Particle AI: Particle-1 (free)
Community
NEW
particle-1:free
Pricing on request
Long ContextVision

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.

StepFun: Step 3.7 Flash
Community
step-3.7-flash
1 Credit = 50,000 Tokens
Long ContextVision

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.

MiniMax: MiniMax M3
Community
minimax-m3
1 Credit = 33,333 Tokens
Long ContextVision

MiniMax-M3 is a multimodal foundation model from MiniMax.

Moondream: Moondream 3.1
Community
moondream3.1-9b-a2b
1 Credit = 33,333 Tokens
Mid ContextVision

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mi…

Mistral: Mistral Medium 3.5
Mistral
mistral-medium-3-5
1 Credit = 6,667 Tokens
Long ContextVision

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

DeepSeek: DeepSeek V4.1 Flash 1017 (batch)
DeepSeek
deepseek-v4.1-flash-1017:batch
1 Credit = 277,778 Tokens
Long ContextVision

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model…

NVIDIA: Nemotron 3.5 Super VL (free)
Community
nemotron-3.5-super-vl:free
Pricing on request
Long ContextVision

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

PrismML: Ternary Bonsai 2 27B
Community
ternary-bonsai-2-27b
1 Credit = 133,333 Tokens
Long ContextVision

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B.

ScaleDown: Extract
Community
extract
1 Credit = 250,000 Tokens
Long ContextVision

Extract is a description-driven entity extraction model from ScaleDown.

Cohere: North Mini Code (free)
Cohere
north-mini-code:free
Pricing on request
Long ContextCode

North Mini Code is Cohere's first agentic coding model and the debut of its North family.

Perceptron: Perceptron Mk1
Community
perceptron-mk1
1 Credit = 66,667 Tokens
Mid ContextVision

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and…

Upstage: Solar Pro 4
Community
solar-pro4
1 Credit = 66,667 Tokens
Long ContextReasoning

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window.

DeepSeek: DeepSeek Flash Latest
Community
deepseek-flash-latest
1 Credit = 285,714 Tokens
Long ContextVision

This model always redirects to the latest model in the DeepSeek Flash family.

Inference.net: Schematron V2 Turbo
Community
schematron-v2-turbo
1 Credit = 333,333 Tokens
Mid Context

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

Z.ai: GLM Latest
Community
glm-latest
1 Credit = 143,062 Tokens
Long Context

This model always redirects to the latest GLM model from Z.ai.

ByteDance Seed: Seed-2.0-Lite
Community
seed-2.0-lite
1 Credit = 40,000 Tokens
Long ContextVision

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering n…

Google: Gemini Flash Latest
Community
gemini-flash-latest
1 Credit = 6,667 Tokens
Long ContextVision

This model always redirects to the latest model in the Gemini Flash family.

Reka Flash 3
Community
reka-flash-3
1 Credit = 100,000 Tokens
Mid Context

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.

Auto Router
Community
NEW
auto
Pricing on request
Long ContextVision

Auto is OpenRouter’s flagship model router, built for general-purpose usage.

Perplexity: Sonar Pro
Perplexity
sonar-pro
1 Credit = 3,333 Tokens
Long ContextVision

Note: Sonar Pro pricing includes Perplexity search pricing.

Amazon: Nova 2 Lite
Community
nova-2-lite-v1
1 Credit = 33,333 Tokens
Long ContextVision

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.

Relace: Relace Apply 3
Community
relace-apply-3
1 Credit = 11,765 Tokens
Long Context

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files.

Morph: Morph V3 Fast
Community
morph-v3-fast
1 Credit = 12,500 Tokens
Long Context

Morph's fastest apply model for code edits.

Sao10K: Llama 3 8B Lunaris
Community
l3-lunaris-8b
1 Credit = 250,000 Tokens
Reasoning

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3.

Meta: Llama 3.3 70B Instruct
Meta
llama-3.3-70b-instruct
1 Credit = 14,085 Tokens
Mid Context

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

TheDrummer: UnslopNemo 12B
Community
unslopnemo-12b
1 Credit = 25,000 Tokens
Long Context

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

OpenAI: GPT-6 Astra
OpenAI
gpt-6-astra
1 Credit = 1,000 Tokens
Long ContextVision

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.

Anthropic: Claude Fable 5.2 (batch)
Anthropic
NEW
claude-fable-5.2:batch
1 Credit = 2,500 Tokens
Long ContextVision

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning,…

OpenAI: GPT Terra Latest
Community
gpt-terra-latest
1 Credit = 10,000 Tokens
Long ContextVision

This model always redirects to the latest model in the GPT Terra family.

Google: Gemini 4 Neon (batch)
Google
NEW
gemini-4-neon:batch
1 Credit = 6,667 Tokens
Long ContextVision

Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.

Meta: Muse Spark Open
Meta
muse-spark-open
1 Credit = 8,000 Tokens
Long ContextVision

Muse Spark Open is a coding-optimized open-weight model.

Sakana: Fugu Ultra
Community
fugu-ultra
1 Credit = 2,000 Tokens
Long ContextVision

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family.

Xiaomi: MiMo-V2.6-Flash
Xiaomi
mimo-v2.6-flash
1 Credit = 71,429 Tokens
Long ContextVision

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

Qwen: Qwen3.8 Max (0902)
Alibaba
qwen3.8-max-0902
1 Credit = 5,000 Tokens
Long ContextReasoning

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

Pareto 26.10 Preview
Community
pareto-26.10-preview
1 Credit = 12,500 Tokens
Long ContextVision

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

AionLabs: Aion-3.0
Community
aion-3.0
1 Credit = 3,333 Tokens
Mid Context

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Tencent: Hy4 preview
Tencent
hy4-preview
1 Credit = 11,990 Tokens
Long Context

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

Anthropic: Claude Sonnet Latest
Community
claude-sonnet-latest
1 Credit = 5,000 Tokens
Long ContextReasoning

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

Thinking Machines: Inkling Small (batch)
Community
inkling-small:batch
1 Credit = 27,778 Tokens
Long ContextReasoning

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…

inclusionAI: Ling 3.0 Flash VL
Community
ling-3.0-flash-vl
1 Credit = 166,667 Tokens
Mid ContextVision

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabiliti…

Nex AGI: Nex-N2.5-Mini
Community
nex-n2.5-mini
1 Credit = 400,000 Tokens
Long ContextVision

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes.

Z.ai: GLM 5.3 FlashX
Z.ai
glm-5.3-flashx
1 Credit = 27,027 Tokens
Long ContextVision

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 toke…

LiquidAI: LFM2.5-24B-A2B
Community
lfm-2.5-24b-a2b
1 Credit = 200,000 Tokens
Mid Context

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters.

SpaceXAI: Grok 4.6
xAI
grok-4.6
1 Credit = 5,000 Tokens
Long ContextReasoning

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

MoonshotAI: Kimi K3 (batch)
Community
kimi-k3:batch
1 Credit = 4,386 Tokens
Long ContextVision

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

MiniMax: MiniMax M3 (batch)
Community
minimax-m3:batch
1 Credit = 44,643 Tokens
Long ContextVision

MiniMax-M3 is a multimodal foundation model from MiniMax.

Mistral: Mistral Medium 3.5 (batch)
Mistral
mistral-medium-3-5:batch
1 Credit = 13,333 Tokens
Long ContextVision

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

DeepSeek: DeepSeek V4.1 Flash (batch)
DeepSeek
deepseek-v4.1-flash:batch
1 Credit = 89,286 Tokens
Long ContextVision

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)…

NVIDIA: Nemotron 3.5 Lightning
Community
nemotron-3.5-lightning
1 Credit = 142,857 Tokens
Long Context

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

Cohere: Command A
Cohere
command-a
1 Credit = 4,000 Tokens
Long ContextCode

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, mult…

DeepSeek: DeepSeek V4 Flash Latest
Community
deepseek-v4-flash-latest
1 Credit = 214,408 Tokens
Long Context

This model always redirects to the latest model in the DeepSeek V4 Flash family.

ByteDance Seed: Seed-2.0-Mini
Community
seed-2.0-mini
1 Credit = 100,000 Tokens
Long ContextVision

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference…

Auto Code
Community
NEW
auto-code
Pricing on request
Long ContextVision

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses.

Perplexity: Sonar Reasoning Pro
Perplexity
sonar-reasoning-pro
1 Credit = 5,000 Tokens
Mid ContextReasoning

Note: Sonar Pro pricing includes Perplexity search pricing.

Amazon: Nova Pro 1.0
Community
nova-pro-v1
1 Credit = 12,500 Tokens
Long ContextVision

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide…

Morph: Morph V3 Large (batch)
Community
morph-v3-large:batch
1 Credit = 22,222 Tokens
Long Context

Morph's high-accuracy apply model for complex code edits.

Meta: Llama 4 Maverick
Meta
llama-4-maverick
1 Credit = 28,571 Tokens
Long ContextVision

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architec…

TheDrummer: Cydonia 24B V4.1
Community
cydonia-24b-v4.1
1 Credit = 33,333 Tokens
Mid Context

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

OpenAI: GPT-6 Astra Pro
OpenAI
gpt-6-astra-pro
1 Credit = 1,000 Tokens
Long ContextVision

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…

Anthropic: Claude Fable 5
Anthropic
claude-fable-5
1 Credit = 1,000 Tokens
Long ContextVision

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.

OpenAI: GPT Luna Latest
Community
gpt-luna-latest
1 Credit = 100,000 Tokens
Long ContextVision

This model always redirects to the latest model in the GPT Luna family.

Google: Gemini 4 Hydrogen
Google
NEW
gemini-4-hydrogen
1 Credit = 6,667 Tokens
Long ContextVision

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows,…

Meta: Muse Spark 1.3
Meta
muse-spark-1.3
1 Credit = 8,000 Tokens
Long ContextVision

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.

Sakana: Sakana Namazu
Community
sakana-namazu
1 Credit = 10,526 Tokens
Long ContextVision

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language…

Xiaomi: MiMo-V2.5-Pro
Xiaomi
mimo-v2.5-pro
1 Credit = 20,833 Tokens
Long Context

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, an…

Qwen: Qwen3.8 Max (0902) (batch)
Alibaba
qwen3.8-max-0902:batch
1 Credit = 8,696 Tokens
Long ContextReasoning

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

AionLabs: Aion-3.0-Mini
Community
aion-3.0-mini
1 Credit = 14,286 Tokens
Mid Context

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.

Tencent: Hy-MT2-30B-A3B
Tencent
hy-mt2-30b-a3b
1 Credit = 135,135 Tokens
Mid Context

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.

Anthropic: Claude Haiku Latest
Community
claude-haiku-latest
1 Credit = 100,000 Tokens
Long ContextVision

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

Thinking Machines: Inkling
Community
inkling
1 Credit = 10,000 Tokens
Long ContextReasoning

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

inclusionAI: Ling 3.0 Tiny
Community
ling-3.0-tiny
1 Credit = 666,667 Tokens
Long Context

Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total.

Z.ai: GLM 5.3 Flash
Z.ai
glm-5.3-flash
1 Credit = 66,667 Tokens
Long ContextVision

GLM-5.3-Flash is a native multimodal model from Z.ai.

SpaceXAI: Grok 4.6 (batch)
xAI
grok-4.6:batch
1 Credit = 6,250 Tokens
Long ContextReasoning

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

MoonshotAI: Kimi K3
Community
kimi-k3
1 Credit = 52,083 Tokens
Long ContextVision

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

MiniMax: MiniMax M2.7
Community
minimax-m2.7
1 Credit = 47,619 Tokens
Mid Context

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.

Mistral: Mistral Small 4
Mistral
mistral-small-2603
1 Credit = 66,667 Tokens
Long ContextVision

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into…

DeepSeek: DeepSeek V4.1 Flash
DeepSeek
deepseek-v4.1-flash
1 Credit = 197,239 Tokens
Long ContextVision

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)…

NVIDIA: Nemotron 3.5 Lightning (free)
Community
nemotron-3.5-lightning:free
Pricing on request
Long Context

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

Cohere: Command R+ (08-2024)
Cohere
command-r-plus-08-2024
1 Credit = 4,000 Tokens
Mid ContextCode

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower l…

Auto Router (Beta)
Community
auto-beta
Pricing on request
Long ContextVision

The experimental version of our Auto Router where we test new improvements.

Perplexity: Sonar Deep Research
Perplexity
sonar-deep-research
1 Credit = 5,000 Tokens
Mid Context

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.

Amazon: Nova Lite 1.0
Community
nova-lite-v1
1 Credit = 166,667 Tokens
Long ContextVision

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to…

Morph: Morph V3 Fast (batch)
Community
morph-v3-fast:batch
1 Credit = 25,000 Tokens
Mid Context

Morph's fastest apply model for code edits.

Meta: Llama Guard 4 12B
Meta
llama-guard-4-12b
1 Credit = 55,556 Tokens
Mid ContextVision

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.

OpenAI: GPT-5.5 Pro
OpenAI
gpt-5.5-pro
1 Credit = 333 Tokens
Long ContextVision

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.

Anthropic: Claude Opus 5.5
Anthropic
claude-opus-5.5
1 Credit = 2,500 Tokens
Long ContextReasoning

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

OpenAI: GPT Mini Latest
Community
gpt-mini-latest
1 Credit = 13,333 Tokens
Long ContextVision

This model always redirects to the latest model in the GPT Mini family.

Google: Gemini Omni 1.2 Flash
Google
NEW
gemini-omni-1.2-flash
1 Credit = 6,667 Tokens
Mid ContextVision

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash.

Meta: Muse Spark 1.3 Contributor
Meta
muse-spark-1.3-contributor
1 Credit = 100,000 Tokens
Long ContextVision

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and…

Xiaomi: MiMo-V2.5
Xiaomi
mimo-v2.5
1 Credit = 25,000 Tokens
Long ContextVision

MiMo-V2.5 is a native omnimodal model by Xiaomi.

Qwen: Qwen3.8 Omni Flash
Alibaba
qwen3.8-omni-flash
1 Credit = 66,667 Tokens
Long ContextVision

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audi…

AionLabs: Aion-2.0
Community
aion-2.0
1 Credit = 12,500 Tokens
Mid Context

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.

Tencent: Hy-MT2-1.8B
Tencent
hy-mt2-1.8b
1 Credit = 227,273 Tokens
Mid Context

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.

inclusionAI: Ling 3.0 Flash
Community
ling-3.0-flash
1 Credit = 476,190 Tokens
Long Context

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

Z.ai: GLM 5.3 Flash (batch)
Z.ai
glm-5.3-flash:batch
1 Credit = 416,667 Tokens
Long ContextVision

GLM-5.3-Flash is a native multimodal model from Z.ai.

SpaceXAI: Grok 4.5
xAI
grok-4.5
1 Credit = 5,000 Tokens
Long ContextReasoning

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

MoonshotAI: Kimi K2.7 Code
Community
kimi-k2.7-code
1 Credit = 15,385 Tokens
Long ContextVision

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reli…

MiniMax: MiniMax M2.5
Community
minimax-m2.5
1 Credit = 33,898 Tokens
Mid Context

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Mistral Large 2407
Mistral
mistral-large-2407
1 Credit = 5,000 Tokens
Mid Context

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407).

DeepSeek: DeepSeek V4 Flash Vision Exp
DeepSeek
deepseek-v4-flash-vision-exp
1 Credit = 22,727 Tokens
Long ContextVision

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee…

NVIDIA: Nemotron 3 Ultra
Community
nemotron-3-ultra-550b-a55b
1 Credit = 20,000 Tokens
Long Context

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…

Cohere: Command R (08-2024)
Cohere
command-r-08-2024
1 Credit = 66,667 Tokens
Mid ContextCode

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmente…

OpenRouter: Fusion
Community
fusion
Pricing on request
Long Context

Fusion turns your prompt into a small multi-model deliberation.

Perplexity: Sonar
Perplexity
sonar
1 Credit = 10,000 Tokens
Mid ContextVision

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.

Amazon: Nova Micro 1.0
Community
nova-micro-v1
1 Credit = 285,714 Tokens
Mid Context

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low c…

Meta: Llama 4 Scout
Meta
llama-4-scout
1 Credit = 100,000 Tokens
Long ContextVision

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of…

OpenAI: GPT-5.5 Pro (batch)
OpenAI
gpt-5.5-pro:batch
1 Credit = 667 Tokens
Long ContextVision

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.

Anthropic: Claude Fable 5.1 (batch)
Anthropic
claude-fable-5.1:batch
1 Credit = 2,000 Tokens
Long ContextVision

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…

Google: Gemini Omni 1.1 Flash
Google
NEW
gemini-omni-1.1-flash
1 Credit = 6,667 Tokens
Mid ContextVision

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni…

Meta: Muse Spark 1.2
Meta
muse-spark-1.2
1 Credit = 8,000 Tokens
Long ContextVision

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.

Qwen: Qwen3.8 2.4T A95B
Alibaba
qwen3.8-2.4t-a95b
1 Credit = 5,000 Tokens
Long Context

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-…

AionLabs: Aion-RP 1.0 (8B)
Community
aion-rp-llama-3.1-8b
1 Credit = 12,500 Tokens
Mid Context

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant…

Tencent: Hy-MT2-7B
Tencent
hy-mt2-7b
1 Credit = 135,135 Tokens
Mid Context

Hy-MT2-7B is a 7B-parameter translation model from Tencent.

Z.ai: GLM 5.3 (batch)
Z.ai
glm-5.3:batch
1 Credit = 35,587 Tokens
Long Context

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

SpaceXAI: Grok Build 0.1
xAI
grok-build-0.1
1 Credit = 10,000 Tokens
Long ContextVision

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows.

MoonshotAI: Kimi K2.6
Community
kimi-k2.6
1 Credit = 15,385 Tokens
Long ContextVision

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-…

Mistral: Mixtral 8x22B Instruct
Mistral
mixtral-8x22b-instruct
1 Credit = 5,000 Tokens
Mid Context

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).

DeepSeek: DeepSeek V4 Pro 0813
DeepSeek
deepseek-v4-pro-0813
1 Credit = 90,090 Tokens
Long Context

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.

NVIDIA: Nemotron 3.5 Content Safety
Community
nemotron-3.5-content-safety
1 Credit = 50,000 Tokens
Mid ContextVision

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.

Cohere: Command R7B (12-2024)
Cohere
command-r7b-12-2024
1 Credit = 266,667 Tokens
Mid ContextCode

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024.

Pareto Code Router
Community
pareto-code
Pricing on request
Long ContextCode

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) c…

Meta: Llama 3.2 3B Instruct
Meta
llama-3.2-3b-instruct
1 Credit = 196,464 Tokens
Mid Context

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like di…

OpenAI: GPT-6.2 Astra Pro (batch)
OpenAI
NEW
gpt-6.2-astra-pro:batch
1 Credit = 2,500 Tokens
Long ContextVision

GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mod…

Anthropic: Claude Sonnet 5.5
Anthropic
claude-sonnet-5.5
1 Credit = 5,000 Tokens
Long ContextReasoning

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.

Google: Gemini 4 Carbon (batch)
Google
NEW
gemini-4-carbon:batch
1 Credit = 10,000 Tokens
Long ContextVision

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.

Meta: Muse Spark 1.2 Contributor
Meta
muse-spark-1.2-contributor
1 Credit = 100,000 Tokens
Long ContextVision

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost.

Qwen: Qwen3.8 Flash
Alibaba
qwen3.8-flash
1 Credit = 66,667 Tokens
Long ContextVision

Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

Tencent: Hy3
Tencent
hy3
1 Credit = 75,758 Tokens
Long Context

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic w…

Z.ai: GLM 5.3
Z.ai
glm-5.3
1 Credit = 143,062 Tokens
Long Context

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

SpaceXAI: Grok 4.3
xAI
grok-4.3
1 Credit = 8,000 Tokens
Long ContextReasoning

Grok 4.3 is a reasoning model from SpaceXAI.

MoonshotAI: Kimi K2.5
Community
kimi-k2.5
1 Credit = 20,000 Tokens
Long ContextVision

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm…

Mistral Large
Mistral
mistral-large
1 Credit = 5,000 Tokens
Mid Context

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`).

DeepSeek: DeepSeek V4 Flash 0731
DeepSeek
deepseek-v4-flash-0731
1 Credit = 161,290 Tokens
Long Context

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

NVIDIA: Nemotron 3 Ultra (free)
Community
nemotron-3-ultra-550b-a55b:free
Pricing on request
Long Context

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…

Body Builder (beta)
Community
bodybuilder
Pricing on request
Mid Context

Transform your natural language requests into structured OpenRouter API request objects.

Meta: Llama 3.2 1B Instruct
Meta
llama-3.2-1b-instruct
1 Credit = 370,370 Tokens
Mid Context

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dia…

OpenAI: GPT-6.2 Astra (batch)
OpenAI
NEW
gpt-6.2-astra:batch
1 Credit = 2,500 Tokens
Long ContextVision

GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.

Anthropic: Claude Opus 5
Anthropic
claude-opus-5
1 Credit = 2,000 Tokens
Long ContextReasoning

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Google: Gemini 4 Hydrogen (batch)
Google
NEW
gemini-4-hydrogen:batch
1 Credit = 13,333 Tokens
Long ContextVision

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows,…

Meta: Muse Glimmer 30B
Meta
muse-glimmer-30b
1 Credit = 28,571 Tokens
Mid ContextVision

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…

Qwen: Qwen3.8 27B (batch)
Alibaba
qwen3.8-27b:batch
1 Credit = 62,500 Tokens
Long ContextVision

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

Tencent: Hy3 preview
Tencent
hy3-preview
1 Credit = 55,556 Tokens
Long Context

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use.

Z.ai: GLM 5.2
Z.ai
glm-5.2
1 Credit = 16,129 Tokens
Long Context

GLM 5.2 is a large-scale reasoning model from Z.ai.

SpaceXAI: Grok 4.3 (batch)
xAI
grok-4.3:batch
1 Credit = 10,000 Tokens
Long ContextReasoning

Grok 4.3 is a reasoning model from SpaceXAI.

MoonshotAI: Kimi K2 Thinking
Community
kimi-k2-thinking
1 Credit = 16,667 Tokens
Long ContextReasoning

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Mistral: Devstral 2 2512
Mistral
devstral-2512
1 Credit = 25,000 Tokens
Long Context

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.

DeepSeek: DeepSeek V4 Flash 0731 (batch)
DeepSeek
deepseek-v4-flash-0731:batch
1 Credit = 208,333 Tokens
Long Context

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

NVIDIA: Nemotron 3 Nano Omni (free)
Community
nemotron-3-nano-omni-30b-a3b-reasoning:free
Pricing on request
Long ContextReasoning

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise…

Meta: Llama 3.1 8B Instruct
Meta
llama-3.1-8b-instruct
1 Credit = 500,000 Tokens
Mid Context

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.

OpenAI: GPT-5.4 Pro
OpenAI
gpt-5.4-pro
1 Credit = 333 Tokens
Long ContextVision

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…

Anthropic: Claude Opus 5.5 (batch)
Anthropic
claude-opus-5.5:batch
1 Credit = 5,000 Tokens
Long ContextReasoning

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

Google: Gemini 4 Argon
Google
gemini-4-argon
1 Credit = 5,000 Tokens
Long ContextVision

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem sol…

Meta: Muse Glimmer 30B (batch)
Meta
muse-glimmer-30b:batch
1 Credit = 41,667 Tokens
Mid ContextVision

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…

Qwen: Qwen3.8 27B
Alibaba
qwen3.8-27b
1 Credit = 166,667 Tokens
Long ContextVision

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

Z.ai: GLM 5.2 (batch)
Z.ai
glm-5.2:batch
1 Credit = 31,056 Tokens
Long Context

GLM 5.2 is a large-scale reasoning model from Z.ai.

SpaceXAI: Grok 4.20 Multi-Agent
xAI
grok-4.20-multi-agent
1 Credit = 8,000 Tokens
Long ContextReasoning

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.

MoonshotAI: Kimi K2 0905
Community
kimi-k2-0905
1 Credit = 16,667 Tokens
Long Context

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).

Mistral: Mistral Large 3 2512
Mistral
mistral-large-2512
1 Credit = 20,000 Tokens
Long ContextVision

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active paramete…

DeepSeek: DeepSeek V4 Pro 0423
DeepSeek
deepseek-v4-pro
1 Credit = 11,111 Tokens
Long Context

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporti…

NVIDIA: Nemotron 3 Super
Community
nemotron-3-super-120b-a12b
1 Credit = 133,333 Tokens
Long Context

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accu…

OpenAI: GPT-5.4 Pro (batch)
OpenAI
gpt-5.4-pro:batch
1 Credit = 667 Tokens
Long ContextVision

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…

Anthropic: Claude Sonnet 5.5 (batch)
Anthropic
claude-sonnet-5.5:batch
1 Credit = 10,000 Tokens
Long ContextReasoning

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.

Google: Nano Banana 2.1
Google
gemini-nano-banana-2.1
1 Credit = 6,667 Tokens
Mid ContextVision

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and N…

Meta: Muse Spark 1.1
Meta
muse-spark-1.1
1 Credit = 8,000 Tokens
Long ContextVision

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.

Qwen: Qwen3.7 Flash
Alibaba
qwen3.7-flash
1 Credit = 333,333 Tokens
Long ContextVision

Qwen3.7 Flash is a vision-language reasoning model from Alibaba.

Z.ai: GLM 5.1
Z.ai
glm-5.1
1 Credit = 8,403 Tokens
Long Context

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.

SpaceXAI: Grok 4.20
xAI
grok-4.20
1 Credit = 8,000 Tokens
Long ContextReasoning

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.

MoonshotAI: Kimi K2 0711
Community
kimi-k2
1 Credit = 17,544 Tokens
Mid Context

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters…

Mistral: Ministral 3 14B 2512
Mistral
ministral-14b-2512
1 Credit = 50,000 Tokens
Long ContextVision

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistra…

DeepSeek: DeepSeek V4 Flash 0423
DeepSeek
deepseek-v4-flash
1 Credit = 111,111 Tokens
Long Context

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated paramete…

NVIDIA: Nemotron 3 Nano 30B A3B
Community
nemotron-3-nano-30b-a3b
1 Credit = 166,667 Tokens
Long Context

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build special…

OpenAI: GPT-6.2 Sol Pro
OpenAI
NEW
gpt-6.2-sol-pro
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set…

Anthropic: Claude Haiku 5.5
Anthropic
claude-haiku-5.5
1 Credit = 100,000 Tokens
Long ContextVision

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

Google: Gemini 4 Argon (batch)
Google
gemini-4-argon:batch
1 Credit = 10,000 Tokens
Long ContextVision

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem sol…

Qwen: Qwen3.7 Max
Alibaba
qwen3.7-max
1 Credit = 6,780 Tokens
Long ContextReasoning

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.

Z.ai: GLM 5V Turbo
Z.ai
glm-5v-turbo
1 Credit = 8,333 Tokens
Long ContextVision

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks.

Mistral: Ministral 3 8B 2512
Mistral
ministral-8b-2512
1 Credit = 66,667 Tokens
Long ContextVision

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

DeepSeek: DeepSeek V3.2
DeepSeek
deepseek-v3.2
1 Credit = 38,462 Tokens
Mid Context

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use pe…

NVIDIA: Switchyard
Community
switchyard
Pricing on request
Long Context

Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.

OpenAI: GPT-6.2 Sol
OpenAI
NEW
gpt-6.2-sol
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.

Anthropic: Claude Haiku 5.5 (batch)
Anthropic
claude-haiku-5.5:batch
1 Credit = 200,000 Tokens
Long ContextVision

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

Google: Gemini 3.8 Flash
Google
gemini-3.8-flash
1 Credit = 12,121 Tokens
Long ContextVision

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…

Qwen: Qwen3.7 Plus
Alibaba
qwen3.7-plus
1 Credit = 31,250 Tokens
Long ContextVision

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

Z.ai: GLM 5 Turbo
Z.ai
glm-5-turbo
1 Credit = 8,333 Tokens
Long Context

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw sce…

Mistral: Ministral 3 3B 2512
Mistral
ministral-3b-2512
1 Credit = 100,000 Tokens
Mid ContextVision

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

DeepSeek: R1 0528
DeepSeek
deepseek-r1-0528
1 Credit = 17,513 Tokens
Mid ContextReasoning

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced an…

OpenAI: GPT-6 Astra (batch)
OpenAI
gpt-6-astra:batch
1 Credit = 2,000 Tokens
Long ContextVision

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.

Anthropic: Claude Fable 5 (batch)
Anthropic
claude-fable-5:batch
1 Credit = 2,000 Tokens
Long ContextVision

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.

Google: Gemini 3.8 Flash (batch)
Google
gemini-3.8-flash:batch
1 Credit = 26,667 Tokens
Long ContextVision

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…

Qwen: Qwen3.7 Plus (batch)
Alibaba
qwen3.7-plus:batch
1 Credit = 43,478 Tokens
Long ContextVision

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

Z.ai: GLM 5
Z.ai
glm-5
1 Credit = 10,000 Tokens
Long Context

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.

Mistral: Mistral Medium 3.1
Mistral
mistral-medium-3.1
1 Credit = 22,727 Tokens
Mid ContextVision

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to del…

DeepSeek: DeepSeek V3 0324
DeepSeek
deepseek-chat-v3-0324
1 Credit = 34,483 Tokens
Mid Context

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

OpenAI: GPT-6 Astra Pro (batch)
OpenAI
gpt-6-astra-pro:batch
1 Credit = 2,000 Tokens
Long ContextVision

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…

Anthropic: Claude Opus 4.1
Anthropic
claude-opus-4.1
1 Credit = 667 Tokens
Long ContextReasoning

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

Google: Gemini 3.7 Flash
Google
gemini-3.7-flash
1 Credit = 13,333 Tokens
Long ContextVision

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

Qwen: Qwen3.6 27B
Alibaba
qwen3.6-27b
1 Credit = 31,250 Tokens
Long ContextVision

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

Z.ai: GLM 4.7 Flash
Z.ai
glm-4.7-flash
1 Credit = 165,289 Tokens
Long Context

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.

Mistral: Mistral Medium 3
Mistral
mistral-medium-3
1 Credit = 22,727 Tokens
Mid ContextVision

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly r…

DeepSeek: DeepSeek V3.2 Exp
DeepSeek
deepseek-v3.2-exp
1 Credit = 37,037 Tokens
Mid Context

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectu…

OpenAI: GPT-6.2 Sol Pro (batch)
OpenAI
NEW
gpt-6.2-sol-pro:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set…

Anthropic: Claude Opus 5 (batch)
Anthropic
claude-opus-5:batch
1 Credit = 4,000 Tokens
Long ContextReasoning

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Google: Gemini 3.7 Flash (batch)
Google
gemini-3.7-flash:batch
1 Credit = 26,667 Tokens
Long ContextVision

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

Qwen: Qwen3.5 Plus 2026-04-20
Alibaba
qwen3.5-plus-20260420
1 Credit = 33,333 Tokens
Long ContextVision

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba.

Z.ai: GLM 4.7
Z.ai
glm-4.7
1 Credit = 25,000 Tokens
Long Context

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-ste…

Mistral: Mistral Small 3.1 24B
Mistral
mistral-small-3.1-24b-instruct
1 Credit = 28,490 Tokens
Mid ContextVision

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal…

DeepSeek: DeepSeek V3.1 Terminus
DeepSeek
deepseek-v3.1-terminus
1 Credit = 37,037 Tokens
Mid Context

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities whi…

OpenAI: GPT-6.2 Sol (batch)
OpenAI
NEW
gpt-6.2-sol:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.

Anthropic: Claude Opus 4.8
Anthropic
claude-opus-4.8
1 Credit = 2,000 Tokens
Long ContextReasoning

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.

Google: Gemini 3.6 Flash
Google
gemini-3.6-flash
1 Credit = 13,333 Tokens
Long ContextVision

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.

Qwen: Qwen3.6 Flash
Alibaba
qwen3.6-flash
1 Credit = 53,333 Tokens
Long ContextVision

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.

Z.ai: GLM 4.6V
Z.ai
glm-4.6v
1 Credit = 33,333 Tokens
Mid ContextVision

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents,…

Mistral: Codestral 2508
Mistral
codestral-2508
1 Credit = 33,333 Tokens
Long ContextCode

Mistral's cutting-edge language model for coding released end of July 2025.

DeepSeek: DeepSeek V3
DeepSeek
deepseek-chat
1 Credit = 38,850 Tokens
Mid Context

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous vers…

OpenAI: GPT-6.1 Terra Pro
OpenAI
NEW
gpt-6.1-terra-pro
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mod…

Anthropic: Claude Sonnet 5
Anthropic
claude-sonnet-5
1 Credit = 5,000 Tokens
Long ContextReasoning

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

Google: Gemini 3.6 Flash (batch)
Google
gemini-3.6-flash:batch
1 Credit = 26,667 Tokens
Long ContextVision

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.

Qwen: Qwen3.6 35B A3B
Alibaba
qwen3.6-35b-a3b
1 Credit = 100,000 Tokens
Long ContextVision

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters pe…

Z.ai: GLM 4.5V
Z.ai
glm-4.5v
1 Credit = 16,667 Tokens
Mid ContextVision

GLM-4.5V is a vision-language foundation model for multimodal agent applications.

Mistral: Saba
Mistral
mistral-saba
1 Credit = 50,000 Tokens
Mid Context

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextu…

DeepSeek: DeepSeek V3.1
DeepSeek
deepseek-chat-v3.1
1 Credit = 40,000 Tokens
Mid Context

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prom…

OpenAI: GPT-6.1 Terra
OpenAI
NEW
gpt-6.1-terra
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.

Anthropic: Claude Opus 4.7
Anthropic
claude-opus-4.7
1 Credit = 2,000 Tokens
Long ContextReasoning

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.

Google: Nano Banana Pro (Gemini 3 Pro Image)
Google
gemini-3-pro-image
1 Credit = 5,000 Tokens
Mid ContextReasoning

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.

Qwen: Qwen3.6 Plus
Alibaba
qwen3.6-plus
1 Credit = 30,769 Tokens
Long ContextVision

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling s…

Z.ai: GLM 4.5
Z.ai
glm-4.5
1 Credit = 16,667 Tokens
Mid Context

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications.

Mistral: Voxtral Small 24B 2507
Mistral
voxtral-small-24b-2507
1 Credit = 100,000 Tokens
Mid Context

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class…

OpenAI: GPT-6.1 Sol Pro
OpenAI
gpt-6.1-sol-pro
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set…

Anthropic: Claude Sonnet 5 (batch)
Anthropic
claude-sonnet-5:batch
1 Credit = 10,000 Tokens
Long ContextReasoning

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

Google: Gemini 3.5 Flash Lite
Google
gemini-3.5-flash-lite
1 Credit = 33,333 Tokens
Long ContextVision

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.

Qwen: Qwen3.5-9B
Alibaba
qwen3.5-9b
1 Credit = 58,824 Tokens
Long ContextVision

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understandi…

Z.ai: GLM 4.6
Z.ai
glm-4.6
1 Credit = 20,000 Tokens
Long Context

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from…

Mistral: Mistral Small 3.2 24B
Mistral
mistral-small-3.2-24b-instruct
1 Credit = 133,333 Tokens
Long ContextVision

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduct…

OpenAI: GPT-6.1 Sol
OpenAI
gpt-6.1-sol
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.

Anthropic: Claude Opus 4.8 (batch)
Anthropic
claude-opus-4.8:batch
1 Credit = 4,000 Tokens
Long ContextReasoning

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.

Google: Gemini 3.5 Flash Lite (batch)
Google
gemini-3.5-flash-lite:batch
1 Credit = 66,667 Tokens
Long ContextVision

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.

Qwen: Qwen3.5-122B-A10B
Alibaba
qwen3.5-122b-a10b
1 Credit = 38,462 Tokens
Long ContextVision

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a…

Z.ai: GLM 4.5 Air
Z.ai
glm-4.5-air
1 Credit = 76,923 Tokens
Mid Context

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.

Mistral: Mistral Small 3
Mistral
mistral-small-24b-instruct-2501
1 Credit = 200,000 Tokens
Mid Context

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

OpenAI: GPT-6.1 Terra Pro (batch)
OpenAI
NEW
gpt-6.1-terra-pro:batch
1 Credit = 20,000 Tokens
Long ContextVision

GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mod…

Anthropic: Claude Opus 4.7 (batch)
Anthropic
claude-opus-4.7:batch
1 Credit = 4,000 Tokens
Long ContextReasoning

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Google
gemini-3.1-flash-lite-image
1 Credit = 40,000 Tokens
Mid ContextVision

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity dev…

Qwen: Qwen3.5-27B
Alibaba
qwen3.5-27b
1 Credit = 51,282 Tokens
Long ContextVision

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balanc…

Mistral: Mistral Nemo
Mistral
mistral-nemo
1 Credit = 344,828 Tokens
Mid Context

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

OpenAI: GPT-6.1 Terra (batch)
OpenAI
NEW
gpt-6.1-terra:batch
1 Credit = 20,000 Tokens
Long ContextVision

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.

Anthropic: Claude Opus 4.6
Anthropic
claude-opus-4.6
1 Credit = 2,000 Tokens
Long ContextReasoning

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.

Google: Nano Banana 2 (Gemini 3.1 Flash Image)
Google
gemini-3.1-flash-image
1 Credit = 20,000 Tokens
Mid ContextVision

Gemini 3.1 Flash Image, a.k.a.

Qwen: Qwen3.5-35B-A3B
Alibaba
qwen3.5-35b-a3b
1 Credit = 71,429 Tokens
Long ContextVision

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechani…

OpenAI: GPT-6 Sol Pro
OpenAI
gpt-6-sol-pro
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `p…

Anthropic: Claude Sonnet 4.6
Anthropic
claude-sonnet-4.6
1 Credit = 3,333 Tokens
Long ContextReasoning

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.

Google: Gemini 3.5 Flash
Google
gemini-3.5-flash
1 Credit = 6,667 Tokens
Long ContextVision

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.

Qwen: Qwen3.5-Flash
Alibaba
qwen3.5-flash-02-23
1 Credit = 153,846 Tokens
Long ContextVision

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sp…

OpenAI: GPT-6 Sol
OpenAI
gpt-6-sol
1 Credit = 5,000 Tokens
Long ContextVision

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT…

Anthropic: Claude Opus 4.1 (batch)
Anthropic
claude-opus-4.1:batch
1 Credit = 1,333 Tokens
Long ContextReasoning

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

Google: Gemini 3.5 Flash (batch)
Google
gemini-3.5-flash:batch
1 Credit = 13,333 Tokens
Long ContextVision

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.

Qwen: Qwen3.5 397B A17B
Alibaba
qwen3.5-397b-a17b
1 Credit = 22,222 Tokens
Long ContextVision

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism…

OpenAI: GPT-6.1 Sol Pro (batch)
OpenAI
gpt-6.1-sol-pro:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set…

Anthropic: Claude Opus 4.6 (batch)
Anthropic
claude-opus-4.6:batch
1 Credit = 4,000 Tokens
Long ContextReasoning

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.

Google: Gemini 3.1 Flash Lite
Google
gemini-3.1-flash-lite
1 Credit = 40,000 Tokens
Long ContextVision

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.

Qwen: Qwen3.5 Plus 2026-02-15
Alibaba
qwen3.5-plus-02-15
1 Credit = 38,462 Tokens
Long ContextVision

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with…

OpenAI: GPT-6.1 Sol (batch)
OpenAI
gpt-6.1-sol:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.

Anthropic: Claude Sonnet 4.6 (batch)
Anthropic
claude-sonnet-4.6:batch
1 Credit = 6,667 Tokens
Long ContextReasoning

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.

Google: Gemini 3.1 Flash Lite (batch)
Google
gemini-3.1-flash-lite:batch
1 Credit = 80,000 Tokens
Long ContextVision

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.

Qwen: Qwen3 Coder Next
Alibaba
qwen3-coder-next
1 Credit = 83,333 Tokens
Long ContextCode

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.

OpenAI: GPT-6 Sol Pro (batch)
OpenAI
gpt-6-sol-pro:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `p…

Anthropic: Claude Opus 4.5
Anthropic
claude-opus-4.5
1 Credit = 2,000 Tokens
Long ContextReasoning

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…

Google: Gemini 3.1 Pro Preview Custom Tools
Google
gemini-3.1-pro-preview-customtools
1 Credit = 5,000 Tokens
Long ContextReasoning

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a gener…

Qwen: Qwen2.5 VL 72B Instruct
Alibaba
qwen2.5-vl-72b-instruct
1 Credit = 12,500 Tokens
Mid ContextVision

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.

OpenAI: GPT-6 Sol (batch)
OpenAI
gpt-6-sol:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT…

Anthropic: Claude Sonnet 4.5
Anthropic
claude-sonnet-4.5
1 Credit = 3,333 Tokens
Long ContextReasoning

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.

Google: Gemma 4 31B
Google
gemma-4-31b-it
1 Credit = 50,000 Tokens
Long ContextVision

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

Qwen2.5 Coder 32B Instruct
Alibaba
qwen-2.5-coder-32b-instruct
1 Credit = 15,152 Tokens
Mid ContextCode

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).

OpenAI: GPT-5.2 Pro
OpenAI
gpt-5.2-pro
1 Credit = 476 Tokens
Long ContextVision

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.

Anthropic: Claude Opus 4.5 (batch)
Anthropic
claude-opus-4.5:batch
1 Credit = 4,000 Tokens
Long ContextReasoning

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…

Google: Gemma 4 26B A4B
Google
gemma-4-26b-a4b-it
1 Credit = 111,111 Tokens
Long ContextVision

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Qwen: Qwen3 235B A22B Thinking 2507
Alibaba
qwen3-235b-a22b-thinking-2507
1 Credit = 22,222 Tokens
Mid ContextReasoning

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning…

OpenAI: GPT-5.4 Image 2
OpenAI
gpt-5.4-image-2
1 Credit = 1,250 Tokens
Long ContextVision

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabiliti…

Anthropic: Claude Sonnet 4.5 (batch)
Anthropic
claude-sonnet-4.5:batch
1 Credit = 6,667 Tokens
Long ContextReasoning

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.

Google: Gemma 4 26B A4B (free)
Google
gemma-4-26b-a4b-it:free
Pricing on request
Long ContextVision

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Qwen2.5 72B Instruct
Alibaba
qwen-2.5-72b-instruct
1 Credit = 27,778 Tokens
Mid Context

Qwen2.5 72B is the latest series of Qwen large language models.

OpenAI: GPT-5.6 Sol Pro
OpenAI
gpt-5.6-sol-pro
1 Credit = 2,500 Tokens
Long ContextVision

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set…

Anthropic: Claude Haiku 4.5
Anthropic
claude-haiku-4.5
1 Credit = 10,000 Tokens
Long ContextReasoning

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…

Google: Gemma 4 31B (free)
Google
gemma-4-31b-it:free
Pricing on request
Long ContextVision

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

Qwen: Qwen3 Coder 480B A35B
Alibaba
qwen3-coder
1 Credit = 33,333 Tokens
Long ContextCode

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

OpenAI: GPT-5.6 Sol
OpenAI
gpt-5.6-sol
1 Credit = 2,500 Tokens
Long ContextVision

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.

Anthropic: Claude Haiku 4.5 (batch)
Anthropic
claude-haiku-4.5:batch
1 Credit = 20,000 Tokens
Long ContextReasoning

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…

Google: Gemini 3.1 Pro Preview
Google
gemini-3.1-pro-preview
1 Credit = 5,000 Tokens
Long ContextReasoning

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…

Qwen: Qwen-Plus
Alibaba
qwen-plus
1 Credit = 38,462 Tokens
Long Context

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

OpenAI: GPT-6 Luna Pro
OpenAI
gpt-6-luna-pro
1 Credit = 100,000 Tokens
Long ContextVision

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to…

Google: Lyria 3 Pro Preview
Google
lyria-3-pro-preview
Pricing on request
Long ContextVision

Full-length songs are priced at $0.08 per song.

Qwen: Qwen3 VL 8B Instruct
Alibaba
qwen3-vl-8b-instruct
1 Credit = 40,000 Tokens
Long ContextVision

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning…

OpenAI: GPT-6 Luna
OpenAI
gpt-6-luna
1 Credit = 100,000 Tokens
Long ContextVision

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Google: Lyria 3 Clip Preview
Google
lyria-3-clip-preview
Pricing on request
Long ContextVision

30 second duration clips are priced at $0.04 per clip.

Qwen: Qwen3 VL 235B A22B Instruct
Alibaba
qwen3-vl-235b-a22b-instruct
1 Credit = 47,619 Tokens
Long ContextVision

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across image…

OpenAI: GPT-6 Luna Pro (batch)
OpenAI
gpt-6-luna-pro:batch
1 Credit = 200,000 Tokens
Long ContextVision

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to…

Google: Gemini 3.1 Pro Preview (batch)
Google
gemini-3.1-pro-preview:batch
1 Credit = 10,000 Tokens
Long ContextReasoning

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…

Qwen: Qwen3 Coder Flash
Alibaba
qwen3-coder-flash
1 Credit = 51,282 Tokens
Long ContextCode

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus.

OpenAI: GPT-6 Luna (batch)
OpenAI
gpt-6-luna:batch
1 Credit = 200,000 Tokens
Long ContextVision

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google
gemini-3.1-flash-image-preview
1 Credit = 20,000 Tokens
Mid ContextVision

Gemini 3.1 Flash Image Preview, a.k.a.

Qwen: Qwen3 VL 30B A3B Instruct
Alibaba
qwen3-vl-30b-a3b-instruct
1 Credit = 66,667 Tokens
Long ContextVision

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos.

OpenAI: GPT-5 Pro
OpenAI
gpt-5-pro
1 Credit = 667 Tokens
Long ContextVision

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

Google: Gemini 3.1 Flash Lite Preview
Google
gemini-3.1-flash-lite-preview
1 Credit = 40,000 Tokens
Long ContextVision

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases.

Qwen: Qwen3 Coder 30B A3B Instruct
Alibaba
qwen3-coder-30b-a3b-instruct
1 Credit = 66,667 Tokens
Long ContextCode

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed f…

OpenAI: o3 Pro
OpenAI
o3-pro
1 Credit = 500 Tokens
Long ContextReasoning

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
Google
gemini-3-pro-image-preview
1 Credit = 5,000 Tokens
Mid ContextReasoning

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.

Qwen: Qwen3 235B A22B Instruct 2507
Alibaba
qwen3-235b-a22b-2507
1 Credit = 71,429 Tokens
Long Context

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture…

OpenAI: GPT-4
OpenAI
gpt-4
1 Credit = 333 Tokens
Mid Context

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy tha…

Google: Gemini 3 Flash Preview
Google
gemini-3-flash-preview
1 Credit = 20,000 Tokens
Long ContextVision

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.

Qwen: Qwen3 30B A3B
Alibaba
qwen3-30b-a3b
1 Credit = 83,333 Tokens
Mid Context

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to e…

OpenAI: GPT-5.6 Terra Pro
OpenAI
gpt-5.6-terra-pro
1 Credit = 5,000 Tokens
Long ContextVision

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mod…

Google: Gemini 3 Flash Preview (batch)
Google
gemini-3-flash-preview:batch
1 Credit = 40,000 Tokens
Long ContextVision

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.

Qwen: Qwen3 14B
Alibaba
qwen3-14b
1 Credit = 83,333 Tokens
Mid Context

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialo…

OpenAI: GPT-5.6 Terra
OpenAI
gpt-5.6-terra
1 Credit = 5,000 Tokens
Long ContextVision

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.

Google: Gemini 2.5 Pro
Google
gemini-2.5-pro
1 Credit = 8,000 Tokens
Long ContextReasoning

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

Qwen: Qwen3 Next 80B A3B Instruct
Alibaba
qwen3-next-80b-a3b-instruct
1 Credit = 100,000 Tokens
Long Context

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thi…

OpenAI: GPT-5.6 Sol Pro (batch)
OpenAI
gpt-5.6-sol-pro:batch
1 Credit = 5,000 Tokens
Long ContextVision

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set…

Google: Gemini 2.5 Pro Preview 06-05
Google
gemini-2.5-pro-preview
1 Credit = 8,000 Tokens
Long ContextReasoning

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

Qwen: Qwen3 30B A3B Instruct 2507
Alibaba
qwen3-30b-a3b-instruct-2507
1 Credit = 100,000 Tokens
Long Context

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.

OpenAI: GPT-5.6 Sol (batch)
OpenAI
gpt-5.6-sol:batch
1 Credit = 5,000 Tokens
Long ContextVision

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.

Google: Gemma 2 27B
Google
gemma-2-27b-it
1 Credit = 15,385 Tokens
Mid Context

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini).

Qwen: Qwen3 32B
Alibaba
qwen3-32b
1 Credit = 125,000 Tokens
Mid Context

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dial…

OpenAI: GPT Chat Latest
OpenAI
gpt-chat-latest
1 Credit = 2,000 Tokens
Long ContextVision

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.

Google: Nano Banana (Gemini 2.5 Flash Image)
Google
gemini-2.5-flash-image
1 Credit = 33,333 Tokens
Mid ContextVision

Gemini 2.5 Flash Image, a.k.a.

OpenAI: GPT-5.5
OpenAI
gpt-5.5
1 Credit = 2,000 Tokens
Long ContextVision

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…

Google: Gemini 2.5 Flash
Google
gemini-2.5-flash
1 Credit = 33,333 Tokens
Long ContextVision

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and sci…

OpenAI: GPT-5.6 Terra Pro (batch)
OpenAI
gpt-5.6-terra-pro:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mod…

Google: Gemini 2.5 Flash Lite
Google
gemini-2.5-flash-lite
1 Credit = 100,000 Tokens
Long ContextVision

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.

OpenAI: GPT-5.6 Terra (batch)
OpenAI
gpt-5.6-terra:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.

Google: Gemma 3 27B
Google
gemma-3-27b-it
1 Credit = 125,000 Tokens
Mid ContextVision

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

OpenAI: GPT-5.6 Luna Pro
OpenAI
gpt-5.6-luna-pro
1 Credit = 50,000 Tokens
Long ContextVision

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode`…

Google: Gemma 3 4B
Google
gemma-3-4b-it
1 Credit = 200,000 Tokens
Mid ContextVision

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

OpenAI: GPT-5.6 Luna
OpenAI
gpt-5.6-luna
1 Credit = 50,000 Tokens
Long ContextVision

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

Google: Gemma 3 12B
Google
gemma-3-12b-it
1 Credit = 200,000 Tokens
Mid ContextVision

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

OpenAI: GPT-5.6 Luna Pro (batch)
OpenAI
gpt-5.6-luna-pro:batch
1 Credit = 100,000 Tokens
Long ContextVision

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode`…

OpenAI: GPT-5.6 Luna (batch)
OpenAI
gpt-5.6-luna:batch
1 Credit = 100,000 Tokens
Long ContextVision

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

OpenAI: GPT-5.2 Pro (batch)
OpenAI
gpt-5.2-pro:batch
1 Credit = 952 Tokens
Long ContextVision

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.

OpenAI: GPT-5.5 (batch)
OpenAI
gpt-5.5:batch
1 Credit = 4,000 Tokens
Long ContextVision

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…

OpenAI: GPT-5 Image
OpenAI
gpt-5-image
1 Credit = 1,000 Tokens
Long ContextVision

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities.

OpenAI: GPT-5.4
OpenAI
gpt-5.4
1 Credit = 4,000 Tokens
Long ContextVision

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

OpenAI: GPT-5 Pro (batch)
OpenAI
gpt-5-pro:batch
1 Credit = 1,333 Tokens
Long ContextVision

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

OpenAI: GPT-5.4 Mini
OpenAI
gpt-5.4-mini
1 Credit = 13,333 Tokens
Long ContextVision

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

OpenAI: GPT-5.3-Codex
OpenAI
gpt-5.3-codex
1 Credit = 5,714 Tokens
Long ContextVision

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex wi…

OpenAI: GPT-5.4 (batch)
OpenAI
gpt-5.4:batch
1 Credit = 8,000 Tokens
Long ContextVision

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

OpenAI: GPT-5.4 Mini (batch)
OpenAI
gpt-5.4-mini:batch
1 Credit = 26,667 Tokens
Long ContextVision

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

OpenAI: GPT-5.4 Nano
OpenAI
gpt-5.4-nano
1 Credit = 50,000 Tokens
Long ContextVision

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.

OpenAI: GPT-5.4 Nano (batch)
OpenAI
gpt-5.4-nano:batch
1 Credit = 100,000 Tokens
Long ContextVision

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.

OpenAI: GPT Audio
OpenAI
gpt-audio
1 Credit = 4,000 Tokens
Mid Context

The gpt-audio model is OpenAI's first generally available audio model.

OpenAI: GPT-4o (2024-05-13)
OpenAI
gpt-4o-2024-05-13
1 Credit = 2,000 Tokens
Mid ContextVision

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

OpenAI: GPT-4 Turbo (batch)
OpenAI
gpt-4-turbo:batch
1 Credit = 2,000 Tokens
Mid ContextVision

The latest GPT-4 Turbo model with vision capabilities.

OpenAI: GPT-5.2-Codex
OpenAI
gpt-5.2-codex
1 Credit = 5,714 Tokens
Long ContextVision

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.

OpenAI: GPT Audio Mini
OpenAI
gpt-audio-mini
1 Credit = 16,667 Tokens
Mid Context

A cost-efficient version of GPT Audio.

OpenAI: GPT-3.5 Turbo 16k
OpenAI
gpt-3.5-turbo-16k
1 Credit = 3,333 Tokens
Mid Context

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single reque…

OpenAI: GPT-5.2 Chat
OpenAI
gpt-5.2-chat
1 Credit = 5,714 Tokens
Mid ContextVision

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong gener…

OpenAI: GPT-5.2
OpenAI
gpt-5.2
1 Credit = 5,714 Tokens
Long ContextVision

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.

OpenAI: GPT-5 Image Mini
OpenAI
gpt-5-image-mini
1 Credit = 4,000 Tokens
Long ContextVision

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with…

OpenAI: GPT-4o (2024-11-20)
OpenAI
gpt-4o-2024-11-20
1 Credit = 4,000 Tokens
Mid ContextVision

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improv…

OpenAI: GPT-4o (2024-08-06)
OpenAI
gpt-4o-2024-08-06
1 Credit = 4,000 Tokens
Mid ContextVision

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respo…

OpenAI: GPT-4o
OpenAI
gpt-4o
1 Credit = 4,000 Tokens
Mid ContextVision

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

OpenAI: GPT-5.1-Codex-Max
OpenAI
gpt-5.1-codex-max
1 Credit = 8,000 Tokens
Long ContextVision

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.

OpenAI: o3
OpenAI
o3
1 Credit = 5,000 Tokens
Long ContextReasoning

o3 is a well-rounded and powerful model across domains.

OpenAI: GPT-4.1
OpenAI
gpt-4.1
1 Credit = 5,000 Tokens
Long ContextVision

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…

OpenAI: GPT-5.2 (batch)
OpenAI
gpt-5.2:batch
1 Credit = 11,429 Tokens
Long ContextVision

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.

OpenAI: GPT-5.1
OpenAI
gpt-5.1
1 Credit = 8,000 Tokens
Long ContextVision

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…

OpenAI: GPT-5.1-Codex
OpenAI
gpt-5.1-codex
1 Credit = 8,000 Tokens
Long ContextVision

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.

OpenAI: GPT-5
OpenAI
gpt-5
1 Credit = 8,000 Tokens
Long ContextVision

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

OpenAI: GPT-4o (batch)
OpenAI
gpt-4o:batch
1 Credit = 8,000 Tokens
Mid ContextVision

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

OpenAI: o3 (batch)
OpenAI
o3:batch
1 Credit = 10,000 Tokens
Long ContextReasoning

o3 is a well-rounded and powerful model across domains.

OpenAI: GPT-4.1 (batch)
OpenAI
gpt-4.1:batch
1 Credit = 10,000 Tokens
Long ContextVision

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…

OpenAI: GPT-3.5 Turbo (older v0613)
OpenAI
gpt-3.5-turbo-0613
1 Credit = 10,000 Tokens
Mid Context

GPT-3.5 Turbo is OpenAI's fastest model.

OpenAI: GPT-5.1 (batch)
OpenAI
gpt-5.1:batch
1 Credit = 16,000 Tokens
Long ContextVision

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…

OpenAI: GPT-5 (batch)
OpenAI
gpt-5:batch
1 Credit = 16,000 Tokens
Long ContextVision

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

OpenAI: o4 Mini (batch)
OpenAI
o4-mini:batch
1 Credit = 18,182 Tokens
Long ContextReasoning

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multim…

OpenAI: o3 Mini (batch)
OpenAI
o3-mini:batch
1 Credit = 18,182 Tokens
Long ContextReasoning

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and…

OpenAI: GPT-4.1 Mini
OpenAI
gpt-4.1-mini
1 Credit = 25,000 Tokens
Long ContextVision

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.

OpenAI: GPT-5.1-Codex-Mini
OpenAI
gpt-5.1-codex-mini
1 Credit = 40,000 Tokens
Long ContextVision

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

OpenAI: GPT-5 Mini
OpenAI
gpt-5-mini
1 Credit = 40,000 Tokens
Long ContextVision

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

OpenAI: GPT-4.1 Mini (batch)
OpenAI
gpt-4.1-mini:batch
1 Credit = 50,000 Tokens
Long ContextVision

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.

OpenAI: gpt-oss-120b
OpenAI
gpt-oss-120b
1 Credit = 66,667 Tokens
Mid Context

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…

OpenAI: GPT-4o-mini
OpenAI
gpt-4o-mini
1 Credit = 66,667 Tokens
Mid ContextVision

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

OpenAI: GPT-4o-mini (2024-07-18)
OpenAI
gpt-4o-mini-2024-07-18
1 Credit = 66,667 Tokens
Mid ContextVision

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

OpenAI: GPT-5 Mini (batch)
OpenAI
gpt-5-mini:batch
1 Credit = 80,000 Tokens
Long ContextVision

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

OpenAI: GPT-4.1 Nano
OpenAI
gpt-4.1-nano
1 Credit = 100,000 Tokens
Long ContextVision

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

OpenAI: gpt-oss-safeguard-20b
OpenAI
gpt-oss-safeguard-20b
1 Credit = 133,333 Tokens
Mid Context

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.

OpenAI: GPT-4o-mini (batch)
OpenAI
gpt-4o-mini:batch
1 Credit = 133,333 Tokens
Mid ContextVision

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

OpenAI: GPT-5 Nano
OpenAI
gpt-5-nano
1 Credit = 200,000 Tokens
Long ContextVision

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…

OpenAI: GPT-4.1 Nano (batch)
OpenAI
gpt-4.1-nano:batch
1 Credit = 200,000 Tokens
Long ContextVision

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

OpenAI: gpt-oss-120b (batch)
OpenAI
gpt-oss-120b:batch
1 Credit = 337,838 Tokens
Mid Context

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…

OpenAI: GPT-5 Nano (batch)
OpenAI
gpt-5-nano:batch
1 Credit = 400,000 Tokens
Long ContextVision

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…

OpenAI: gpt-oss-20b (batch)
OpenAI
gpt-oss-20b:batch
1 Credit = 416,667 Tokens
Mid Context

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

OpenAI: gpt-oss-20b
OpenAI
gpt-oss-20b
1 Credit = 555,556 Tokens
Mid Context

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

Pick a model and ship today.

Spin up any agent framework free, route to any of these models, and only pay for the tokens you use.