Google 4.6
TrustPilot 4.9Every 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.
gpt-astra-latest
1 Credit = 1,000 TokensThis model always redirects to the latest model in the GPT Astra family.
gpt-6-astra1 Credit = 1,000 TokensGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
claude-fable-5.11 Credit = 1,000 TokensClaude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…
claude-fable-latest1 Credit = 1,000 TokensThis model always redirects to the latest model in the Claude Fable family.
fugu-ultra-v21 Credit = 2,000 TokensFugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.
qwen3.8-max-09021 Credit = 5,000 TokensQwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.
muse-spark-1.31 Credit = 8,000 TokensMuse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.
grok-4.61 Credit = 5,000 TokensGrok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
gemini-3.8-flash1 Credit = 13,333 TokensGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…
glm-5.31 Credit = 7,143 TokensGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
kimi-k3:batch1 Credit = 3,333 TokensKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
hy4-preview1 Credit = 11,990 TokensTencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
deepseek-v4.1-flash1 Credit = 66,667 TokensDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)…
schematron-v2-small1 Credit = 200,000 TokensSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.
ling-3.0-flash-vl1 Credit = 166,667 TokensLing 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabiliti…
mercury-2.51 Credit = 250,000 TokensMercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception.
nex-n2.5-mini:freePricing on requestNex-N2.5 is an agentic model built to turn goals into working, verified outcomes.
glm-latest1 Credit = 11,459 TokensThis model always redirects to the latest GLM model from Z.ai.
aion-3.01 Credit = 3,333 TokensAion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
granite-4.2-8b1 Credit = 166,667 TokensGranite 4.2 8B is a dense reasoning model from IBM.
seed-2-1-turbo1 Credit = 20,000 TokensSeed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows.
grok-latest1 Credit = 5,000 TokensThis model always redirects to the latest Grok model from xAI.
dots-3-note-preview:freePricing on requestDots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.
nemotron-3.5-lightning1 Credit = 125,000 TokensNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
solar-pro41 Credit = 111,111 TokensSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window.
lfm-2.5-2.6b:freePricing on requestLFM2.5-2.6B is a compact reasoning model from Liquid AI.
inkling-small:batch1 Credit = 20,000 TokensInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…
deepseek-v4-flash-latest1 Credit = 333,333 TokensThis model always redirects to the latest model in the DeepSeek V4 Flash family.
longcat-2.01 Credit = 33,333 TokensLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.
kat-coder-pro-v2.51 Credit = 13,514 TokensKAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to…
laguna-s-2.11 Credit = 111,111 TokensLaguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>).
north-mini-code:freePricing on requestNorth Mini Code is Cohere's first agentic coding model and the debut of its North family.
kimi-latest1 Credit = 4,211 TokensThis model always redirects to the latest model in the Kimi family.
gemini-pro-latest1 Credit = 5,000 TokensThis model always redirects to the latest model in the Gemini Pro family.
minimax-m31 Credit = 33,333 TokensMiniMax-M3 is a multimodal foundation model from MiniMax.
step-3.7-flash1 Credit = 50,000 TokensStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.
mistral-medium-3-51 Credit = 6,667 TokensMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
perceptron-mk11 Credit = 66,667 TokensPerceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and…
mimo-v2.5-pro1 Credit = 22,989 TokensMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, an…
trinity-large-thinking1 Credit = 40,000 TokensTrinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI.
reka-edge1 Credit = 100,000 TokensReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.
palmyra-x51 Credit = 16,667 TokensPalmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise.
freePricing on requestThe simplest way to get free inference.
sonar-pro-search1 Credit = 3,333 TokensExclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system.
relace-search1 Credit = 10,000 TokensThe 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…
nova-premier-v11 Credit = 4,000 TokensAmazon 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-v4-72b1 Credit = 4,000 TokensThis is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anth…
cydonia-24b-v4.11 Credit = 33,333 TokensUncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
hermes-4-405b1 Credit = 10,000 TokensHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
morph-v3-large1 Credit = 11,111 TokensMorph's high-accuracy apply model for complex code edits.
l3.1-euryale-70b1 Credit = 11,765 TokensEuryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k).
wizardlm-2-8x22b1 Credit = 16,129 TokensWizardLM-2 8x22B is Microsoft AI's most advanced Wizard model.
ernie-4.5-vl-424b-a47b1 Credit = 23,810 TokensERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with…
llama-3.1-70b-instruct1 Credit = 25,000 TokensMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
weaver1 Credit = 25,000 TokensAn attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory.
remm-slerp-l2-13b1 Credit = 28,571 TokensA recreation trial of the original MythoMax-L2-B13 but with updated models.
dolphin-mistral-24b-venice-edition1 Credit = 50,000 TokensVenice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in…
ui-tars-1.5-7b1 Credit = 100,000 TokensUI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobil…
mythomax-l2-13b1 Credit = 166,667 TokensOne of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
gpt-sol-latest1 Credit = 5,000 TokensThis model always redirects to the latest model in the GPT Sol family.
gpt-6-astra-pro1 Credit = 1,000 TokensGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…
claude-fable-51 Credit = 1,000 TokensClaude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
claude-opus-latest1 Credit = 2,000 TokensThis model always redirects to the latest model in the Claude Opus family.
fugu-max1 Credit = 5,000 TokensFugu Max is the cost-performance model in Sakana AI's Fugu family.
qwen3.8-2.4t-a95b1 Credit = 5,000 TokensQwen3.8 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-…
muse-spark-1.3-contributor1 Credit = 100,000 TokensMuse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and…
grok-4.51 Credit = 5,000 TokensGrok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
gemini-3.8-flash:batch1 Credit = 26,667 TokensGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…
glm-5.3:batch1 Credit = 14,286 TokensGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
kimi-k31 Credit = 3,776 TokensKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
hy-mt2-30b-a3b1 Credit = 135,135 TokensHy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.
deepseek-v4-flash-vision-exp1 Credit = 45,455 TokensDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee…
schematron-v2-turbo1 Credit = 333,333 TokensSchematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net.
ling-3.0-flash-vl:freePricing on requestLing 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabiliti…
mercury-21 Credit = 40,000 TokensMercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).
nex-n2.5-pro:freePricing on requestNex-N2.5 is an agentic model built to turn goals into working, verified outcomes.
glm-flash-latest1 Credit = 133,333 TokensThis model always redirects to the latest model in the GLM Flash family.
aion-3.0-mini1 Credit = 14,286 TokensAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
granite-4.0-h-micro1 Credit = 588,235 TokensGranite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models.
seed-2.0-code1 Credit = 20,000 TokensSeed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.
nemotron-3.5-lightning:freePricing on requestNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
solar-pro-31 Credit = 66,667 TokensSolar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model.
inkling-small1 Credit = 22,222 TokensInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…
kat-coder-pro-v21 Credit = 33,333 TokensKAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engin…
laguna-s-2.1:freePricing on requestLaguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>).
command-a1 Credit = 4,000 TokensCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, mult…
gemini-flash-latest1 Credit = 13,333 TokensThis model always redirects to the latest model in the Gemini Flash family.
minimax-m3:batch1 Credit = 33,333 TokensMiniMax-M3 is a multimodal foundation model from MiniMax.
step-3.5-flash1 Credit = 100,000 TokensStep 3.5 Flash is StepFun's most capable open-source foundation model.
mistral-medium-3-5:batch1 Credit = 13,333 TokensMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
mimo-v2.51 Credit = 71,429 TokensMiMo-V2.5 is a native omnimodal model by Xiaomi.
reka-flash-31 Credit = 100,000 TokensReka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.
auto-betaPricing on requestAuto Router (Beta) is a task-aware router from OpenRouter.
sonar-pro1 Credit = 3,333 TokensNote: Sonar Pro pricing includes Perplexity search pricing.
relace-apply-31 Credit = 11,765 TokensRelace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files.
nova-2-lite-v11 Credit = 33,333 TokensNova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.
skyfall-36b-v21 Credit = 18,182 TokensSkyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-pla…
hermes-3-llama-3.1-405b1 Credit = 10,000 TokensHermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better rolepl…
morph-v3-fast1 Credit = 12,500 TokensMorph's fastest apply model for code edits.
l3.3-euryale-70b1 Credit = 15,385 TokensEuryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k).
phi-41 Credit = 142,857 Tokens[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations w…
llama-4-maverick1 Credit = 50,000 TokensLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architec…
gpt-terra-latest1 Credit = 5,000 TokensThis model always redirects to the latest model in the GPT Terra family.
gpt-5.5-pro1 Credit = 333 TokensGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.
claude-fable-5.1:batch1 Credit = 2,000 TokensClaude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…
claude-sonnet-latest1 Credit = 5,000 TokensThis model always redirects to the latest model in the Claude Sonnet family.
fugu-ultra1 Credit = 2,000 TokensFugu Ultra is the higher-performance model in Sakana AI's Fugu family.
qwen3.8-2.4t-a95b:batch1 Credit = 5,000 TokensQwen3.8 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-…
muse-spark-1.21 Credit = 8,000 TokensMuse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.
grok-build-0.11 Credit = 10,000 TokensGrok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows.
gemini-3.7-flash1 Credit = 13,333 TokensGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.
glm-5.3-flash1 Credit = 66,667 TokensGLM-5.3-Flash is a native multimodal model from Z.ai.
kimi-k2.7-code1 Credit = 14,085 TokensMoonshotAI: 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…
hy-mt2-1.8b1 Credit = 227,273 TokensHy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.
deepseek-v4-pro-0813:batch1 Credit = 15,152 TokensDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
ling-3.0-flash-sante:freePricing on requestLing 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active…
aion-2.01 Credit = 12,500 TokensAion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.
seed-2.0-lite1 Credit = 40,000 TokensSeed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering n…
nemotron-3-ultra-550b-a55b1 Credit = 16,000 TokensNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…
inkling1 Credit = 10,000 TokensInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
laguna-xs-2.11 Credit = 166,667 TokensLaguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from thei…
command-r-plus-08-20241 Credit = 4,000 Tokenscommand-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…
minimax-m2.71 Credit = 33,333 TokensMiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
mistral-small-26031 Credit = 66,667 TokensMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into…
fusionPricing on requestFusion turns your prompt into a small multi-model deliberation.
sonar-reasoning-pro1 Credit = 5,000 TokensNote: Sonar Pro pricing includes Perplexity search pricing.
nova-pro-v11 Credit = 12,500 TokensAmazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide…
unslopnemo-12b1 Credit = 25,000 TokensUnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
hermes-3-llama-3.1-70b1 Credit = 14,286 TokensHermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), includ…
l3-lunaris-8b1 Credit = 250,000 TokensLunaris 8B is a versatile generalist and roleplaying model based on Llama 3.
llama-guard-4-12b1 Credit = 55,556 TokensLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.
gpt-luna-latest1 Credit = 50,000 TokensThis model always redirects to the latest model in the GPT Luna family.
gpt-5.5-pro:batch1 Credit = 667 TokensGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.
claude-opus-51 Credit = 2,000 TokensClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
claude-haiku-latest1 Credit = 10,000 TokensThis model always redirects to the latest model in the Claude Haiku family.
sakana-namazu1 Credit = 10,526 TokensSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language…
qwen3.8-flash1 Credit = 66,667 TokensQwen3.8 Flash is a multimodal reasoning model from Alibaba.
muse-spark-1.2-contributor1 Credit = 100,000 TokensMuse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost.
grok-4.31 Credit = 8,000 TokensGrok 4.3 is a reasoning model from SpaceXAI.
gemini-3.7-flash:batch1 Credit = 26,667 TokensGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.
glm-5.3-flash:batch1 Credit = 133,333 TokensGLM-5.3-Flash is a native multimodal model from Z.ai.
kimi-k2.61 Credit = 10,526 TokensKimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-…
hy-mt2-7b1 Credit = 135,135 TokensHy-MT2-7B is a 7B-parameter translation model from Tencent.
deepseek-v4-pro-08131 Credit = 17,257 TokensDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
ling-3.0-flash-fin1 Credit = 166,667 TokensLing 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters ou…
aion-rp-llama-3.1-8b1 Credit = 12,500 TokensAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant…
seed-2.0-mini1 Credit = 100,000 TokensSeed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference…
nemotron-3.5-content-safety1 Credit = 50,000 TokensNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
inkling:batch1 Credit = 10,000 TokensInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
laguna-xs-2.1:freePricing on requestLaguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from thei…
command-r-08-20241 Credit = 66,667 Tokenscommand-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmente…
minimax-m2.51 Credit = 37,037 TokensMiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
mistral-small-2603:batch1 Credit = 133,333 TokensMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into…
pareto-codePricing on requestThe Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) c…
sonar-deep-research1 Credit = 5,000 TokensSonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.
nova-lite-v11 Credit = 166,667 TokensAmazon 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…
llama-4-scout1 Credit = 100,000 TokensLlama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of…
gpt-mini-latest1 Credit = 13,333 TokensThis model always redirects to the latest model in the GPT Mini family.
gpt-5.4-pro1 Credit = 333 TokensGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…
claude-fable-5:batch1 Credit = 2,000 TokensClaude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
qwen3.8-27b1 Credit = 46,729 TokensQwen3.8 27B is an open-weight dense vision-language model from Qwen.
muse-glimmer-30b1 Credit = 33,333 TokensMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…
grok-4.3:batch1 Credit = 10,000 TokensGrok 4.3 is a reasoning model from SpaceXAI.
gemini-3.6-flash1 Credit = 13,333 TokensGemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.
glm-5.2:batch1 Credit = 14,286 TokensGLM 5.2 is a large-scale reasoning model from Z.ai.
kimi-k2.51 Credit = 22,222 TokensKimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm…
hy31 Credit = 121,212 TokensHy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic w…
deepseek-v4-flash-vision-exp:batch1 Credit = 90,909 TokensDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee…
ling-3.0-flash-fin:freePricing on requestLing 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters ou…
seed-1.61 Credit = 40,000 TokensSeed 1.6 is a general-purpose model released by the ByteDance Seed team.
nemotron-3.5-content-safety:freePricing on requestNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
inkling-small:freePricing on requestInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…
command-r7b-12-20241 Credit = 266,667 TokensCommand R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024.
minimax-m2-her1 Credit = 33,333 TokensMiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn co…
devstral-25121 Credit = 25,000 TokensDevstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.
bodybuilderPricing on requestTransform your natural language requests into structured OpenRouter API request objects.
sonar1 Credit = 10,000 TokensSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.
nova-micro-v11 Credit = 285,714 TokensAmazon 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…
llama-3.3-70b-instruct1 Credit = 100,000 TokensThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
gpt-5.4-pro:batch1 Credit = 667 TokensGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…
claude-opus-5:batch1 Credit = 4,000 TokensClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
qwen3.7-flash1 Credit = 333,333 TokensQwen3.7 Flash is a vision-language reasoning model from Alibaba.
muse-glimmer-30b:batch1 Credit = 57,143 TokensMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…
grok-4.20-multi-agent1 Credit = 8,000 TokensGrok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.
gemini-3.6-flash:batch1 Credit = 26,667 TokensGemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.
glm-5.21 Credit = 16,667 TokensGLM 5.2 is a large-scale reasoning model from Z.ai.
kimi-k2-thinking1 Credit = 16,667 TokensKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
hy3-preview1 Credit = 55,556 TokensHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use.
deepseek-v4-flash-0731:batch1 Credit = 90,909 TokensDeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
ling-3.0-flash1 Credit = 476,190 Tokens*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
seed-1.6-flash1 Credit = 133,333 TokensSeed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding.
nemotron-3-ultra-550b-a55b:freePricing on requestNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…
inkling:freePricing on requestInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
minimax-m2.11 Credit = 33,333 TokensMiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application deve…
mistral-large-25121 Credit = 20,000 TokensMistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active paramete…
autoPricing on requestThe Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market.
llama-3.2-3b-instruct1 Credit = 200,000 TokensLlama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like di…
gpt-6-astra:batch1 Credit = 2,000 TokensGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
claude-opus-4.81 Credit = 2,000 TokensClaude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
qwen3.7-max1 Credit = 6,780 TokensQwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.
muse-spark-1.11 Credit = 8,000 TokensMuse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.
grok-4.201 Credit = 8,000 TokensGrok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.
gemini-3-pro-image1 Credit = 5,000 TokensNano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
glm-5.11 Credit = 10,352 TokensGLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.
kimi-k2-09051 Credit = 16,667 TokensKimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).
hunyuan-a13b-instruct1 Credit = 71,429 TokensHunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B…
deepseek-v4-flash-07311 Credit = 250,000 TokensDeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
nemotron-3-nano-omni-30b-a3b-reasoning:freePricing on requestNVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise…
minimax-m21 Credit = 39,216 TokensMiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.
mistral-large-2512:batch1 Credit = 40,000 TokensMistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active paramete…
llama-3.1-8b-instruct1 Credit = 200,000 TokensMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
gpt-6-astra-pro:batch1 Credit = 2,000 TokensGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…
claude-sonnet-51 Credit = 5,000 TokensSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
qwen3.7-plus1 Credit = 31,250 TokensQwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.
gemini-3.5-flash-lite1 Credit = 33,333 TokensGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.
glm-5v-turbo1 Credit = 8,333 TokensGLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks.
kimi-k21 Credit = 17,544 TokensKimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters…
deepseek-v4-pro1 Credit = 6,250 TokensDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporti…
nemotron-3-super-120b-a12b1 Credit = 117,647 TokensNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accu…
minimax-m11 Credit = 18,182 TokensMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference.
ministral-14b-25121 Credit = 50,000 TokensThe largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistra…
llama-3.2-1b-instruct1 Credit = 370,370 TokensLlama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dia…
gpt-5.2-pro1 Credit = 476 TokensGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.
claude-opus-4.71 Credit = 2,000 TokensOpus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
qwen3.6-max-preview1 Credit = 9,737 TokensQwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximate…
gemini-3.5-flash-lite:batch1 Credit = 66,667 TokensGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.
glm-5-turbo1 Credit = 8,333 TokensGLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw sce…
deepseek-v4-flash1 Credit = 152,300 TokensDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated paramete…
nemotron-3-super-120b-a12b:freePricing on requestNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accu…
minimax-011 Credit = 50,000 TokensMiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding.
ministral-8b-25121 Credit = 66,667 TokensA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
gpt-5.4-image-21 Credit = 1,250 Tokens[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…
claude-sonnet-5:batch1 Credit = 10,000 TokensSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
qwen3.5-plus-202604201 Credit = 33,333 TokensQwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba.
gemini-3.1-flash-lite-image1 Credit = 40,000 TokensNano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity dev…
glm-51 Credit = 16,667 TokensGLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.
deepseek-v3.21 Credit = 37,175 TokensDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use pe…
nemotron-3-nano-30b-a3b1 Credit = 200,000 TokensNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build special…
ministral-3b-25121 Credit = 100,000 TokensThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
gpt-5.6-terra-pro1 Credit = 5,000 TokensGPT-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…
claude-opus-4.8:batch1 Credit = 4,000 TokensClaude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
qwen3.6-27b1 Credit = 33,333 TokensQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
gemini-3.1-flash-image1 Credit = 20,000 TokensGemini 3.1 Flash Image, a.k.a.
glm-4.7-flash1 Credit = 165,289 TokensAs a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.
deepseek-v3.2-exp1 Credit = 37,037 TokensDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectu…
ministral-8b-2512:batch1 Credit = 133,333 TokensA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
gpt-5.6-terra1 Credit = 5,000 TokensGPT-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.
claude-opus-4.11 Credit = 667 TokensClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
qwen3.6-flash1 Credit = 53,333 TokensQwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.
gemini-3.5-flash1 Credit = 6,667 TokensGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.
glm-4.71 Credit = 25,000 TokensGLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-ste…
deepseek-r1-distill-llama-70b1 Credit = 12,500 TokensDeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct),…
voxtral-small-24b-25071 Credit = 100,000 TokensVoxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class…
gpt-5.6-sol-pro1 Credit = 5,000 TokensGPT-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…
claude-opus-41 Credit = 667 TokensClaude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-runnin…
qwen3.6-35b-a3b1 Credit = 100,000 TokensQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters pe…
gemini-3.5-flash:batch1 Credit = 13,333 TokensGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.
glm-4.6v1 Credit = 33,333 TokensGLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents,…
deepseek-v3.1-terminus1 Credit = 37,037 TokensDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities whi…
mistral-large-24071 Credit = 5,000 TokensThis is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407).
gpt-5.6-sol1 Credit = 5,000 TokensGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.
claude-opus-4.7:batch1 Credit = 4,000 TokensOpus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
qwen3.6-plus1 Credit = 30,769 TokensQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling s…
gemini-3.1-flash-lite1 Credit = 40,000 TokensGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
glm-4.61 Credit = 23,256 TokensCompared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from…
deepseek-r11 Credit = 14,286 TokensDeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens.
mixtral-8x22b-instruct1 Credit = 5,000 TokensMistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).
gpt-chat-latest1 Credit = 2,000 TokensGPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.
claude-opus-4.61 Credit = 2,000 TokensOpus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
qwen3.5-9b:batch1 Credit = 58,824 TokensQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understandi…
gemini-3.1-flash-lite:batch1 Credit = 80,000 TokensGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
glm-4.5v1 Credit = 16,667 TokensGLM-4.5V is a vision-language foundation model for multimodal agent applications.
deepseek-r1-05281 Credit = 20,000 TokensMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced an…
mistral-large1 Credit = 5,000 TokensThis is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`).
gpt-5-pro1 Credit = 667 TokensGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
claude-sonnet-4.61 Credit = 3,333 TokensSonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
qwen3.5-9b1 Credit = 100,000 TokensQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understandi…
gemma-4-31b-it:batch1 Credit = 25,641 TokensGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
glm-4.51 Credit = 16,667 TokensGLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications.
deepseek-chat1 Credit = 38,850 TokensDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous vers…
mistral-medium-3.11 Credit = 25,000 TokensMistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to del…
gpt-5.51 Credit = 2,000 TokensGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…
claude-opus-4.6:batch1 Credit = 4,000 TokensOpus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
qwen3.5-35b-a3b1 Credit = 32,000 TokensThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechani…
gemini-3.1-pro-preview-customtools1 Credit = 5,000 TokensGemini 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…
glm-4.5-air1 Credit = 76,923 TokensGLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.
deepseek-chat-v3.11 Credit = 40,000 TokensDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prom…
mistral-medium-31 Credit = 25,000 TokensMistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly r…
gpt-5.6-terra-pro:batch1 Credit = 10,000 TokensGPT-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…
claude-sonnet-4.6:batch1 Credit = 6,667 TokensSonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
qwen3.5-122b-a10b1 Credit = 38,462 TokensThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a…
gemma-4-31b-it1 Credit = 111,111 TokensGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
deepseek-chat-v3-03241 Credit = 40,000 TokensDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
mistral-small-3.1-24b-instruct1 Credit = 28,490 TokensMistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal…
gpt-5.6-terra:batch1 Credit = 10,000 TokensGPT-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.
claude-opus-4.51 Credit = 2,000 TokensClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…
qwen3.5-27b1 Credit = 51,282 TokensThe Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balanc…
gemma-4-26b-a4b-it1 Credit = 238,095 TokensGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
codestral-25081 Credit = 33,333 TokensMistral's cutting-edge language model for coding released end of July 2025.
gpt-5.6-sol-pro:batch1 Credit = 10,000 TokensGPT-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…
claude-opus-4.1:batch1 Credit = 1,333 TokensClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
qwen3.5-397b-a17b1 Credit = 18,182 TokensThe Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism…
gemma-4-26b-a4b-it:freePricing on requestGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
mistral-medium-3.1:batch1 Credit = 50,000 TokensMistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to del…
gpt-5.6-sol:batch1 Credit = 10,000 TokensGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.
claude-opus-4.5:batch1 Credit = 4,000 TokensClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…
qwen3.5-flash-02-231 Credit = 153,846 TokensThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sp…
gemma-4-31b-it:freePricing on requestGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
mistral-saba1 Credit = 50,000 TokensMistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextu…
gpt-5.6-luna-pro1 Credit = 50,000 TokensGPT-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`…
claude-sonnet-4.51 Credit = 3,333 TokensClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
qwen3-max-thinking1 Credit = 12,821 TokensQwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi…
gemini-3.1-pro-preview1 Credit = 5,000 TokensGemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…
codestral-2508:batch1 Credit = 66,667 TokensMistral's cutting-edge language model for coding released end of July 2025.
gpt-5.6-luna1 Credit = 50,000 TokensGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
claude-sonnet-41 Credit = 3,333 TokensClaude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with…
qwen3.5-plus-02-151 Credit = 38,462 TokensThe Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with…
lyria-3-pro-previewPricing on requestFull-length songs are priced at $0.08 per song.
mistral-small-3.2-24b-instruct1 Credit = 133,333 TokensMistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduct…
gpt-5.6-luna-pro:batch1 Credit = 100,000 TokensGPT-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`…
claude-haiku-4.51 Credit = 10,000 TokensClaude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…
qwen3-coder-next1 Credit = 83,333 TokensQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.
lyria-3-clip-previewPricing on request30 second duration clips are priced at $0.04 per clip.
mistral-small-24b-instruct-25011 Credit = 200,000 TokensMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.
gpt-5.6-luna:batch1 Credit = 100,000 TokensGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
claude-sonnet-4.5:batch1 Credit = 6,667 TokensClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
qwen3-vl-32b-instruct1 Credit = 96,154 TokensQwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across te…
gemini-3.1-pro-preview:batch1 Credit = 10,000 TokensGemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…
mistral-nemo1 Credit = 526,316 TokensA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
o3-pro1 Credit = 500 TokensThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.
claude-haiku-4.5:batch1 Credit = 20,000 TokensClaude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…
qwen3-vl-8b-thinking1 Credit = 55,556 TokensQwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual rea…
gemini-3.1-flash-image-preview1 Credit = 20,000 TokensGemini 3.1 Flash Image Preview, a.k.a.
o1-pro1 Credit = 67 TokensThe o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.
claude-3-haiku1 Credit = 40,000 TokensClaude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness.
qwen3-vl-8b-instruct1 Credit = 85,470 TokensQwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning…
gemini-3.1-flash-lite-preview1 Credit = 40,000 TokensGemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases.
o11 Credit = 667 TokensThe latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.
qwen3-vl-30b-a3b-thinking1 Credit = 50,000 TokensQwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos.
gemini-3-pro-image-preview1 Credit = 5,000 TokensNano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
gpt-41 Credit = 333 TokensOpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy tha…
qwen3-vl-30b-a3b-instruct1 Credit = 66,667 TokensQwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos.
gemini-3-flash-preview1 Credit = 20,000 TokensGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
gpt-5.2-pro:batch1 Credit = 952 TokensGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.
qwen3-max1 Credit = 12,821 TokensQwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual…
gemini-3-flash-preview:batch1 Credit = 40,000 TokensGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
gpt-5.5:batch1 Credit = 4,000 TokensGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…
qwen3-coder-plus1 Credit = 15,385 TokensQwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B.
gemini-2.5-flash-image1 Credit = 33,333 TokensGemini 2.5 Flash Image, a.k.a.
gpt-5-image1 Credit = 1,000 Tokens[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities.
qwen3-vl-235b-a22b-thinking1 Credit = 25,000 TokensQwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video.
gemini-2.5-pro1 Credit = 8,000 TokensGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
gpt-5.41 Credit = 4,000 TokensGPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.
qwen2.5-vl-72b-instruct1 Credit = 12,500 TokensQwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.
gemini-2.5-pro-preview1 Credit = 8,000 TokensGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
gpt-5.4-mini1 Credit = 13,333 TokensGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
qwen3-vl-235b-a22b-instruct1 Credit = 47,619 TokensQwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across image…
gemini-2.5-pro-preview-05-061 Credit = 8,000 TokensGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
gpt-4-turbo1 Credit = 1,000 TokensThe latest GPT-4 Turbo model with vision capabilities.
qwen-2.5-coder-32b-instruct1 Credit = 15,152 TokensQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).
gemma-2-27b-it1 Credit = 15,385 TokensGemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini).
gpt-4-turbo-preview1 Credit = 1,000 TokensThe preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.
qwen3-235b-a22b1 Credit = 21,978 TokensQwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass.
gemini-2.5-pro:batch1 Credit = 16,000 TokensGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
gpt-5.3-codex1 Credit = 5,714 TokensGPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex wi…
qwen3-coder-flash1 Credit = 51,282 TokensQwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus.
gemini-2.5-flash1 Credit = 33,333 TokensGemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and sci…
gpt-5.4:batch1 Credit = 8,000 TokensGPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.
qwen-2.5-72b-instruct1 Credit = 27,778 TokensQwen2.5 72B is the latest series of Qwen large language models.
gemini-2.5-flash:batch1 Credit = 66,667 TokensGemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and sci…
gpt-5.4-mini:batch1 Credit = 26,667 TokensGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
qwen3-coder1 Credit = 33,333 TokensQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.
gemini-2.5-flash-lite1 Credit = 100,000 TokensGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.
gpt-5.4-nano1 Credit = 50,000 TokensGPT-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.
qwen-plus-2025-07-281 Credit = 38,462 TokensQwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, an…
gemma-3-27b-it1 Credit = 125,000 TokensGemma 3 introduces multimodality, supporting vision-language input and text outputs.
gpt-5.4-nano:batch1 Credit = 100,000 TokensGPT-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.
qwen-plus1 Credit = 38,462 TokensQwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
gemini-2.5-flash-lite:batch1 Credit = 200,000 TokensGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.
gpt-audio1 Credit = 4,000 TokensThe gpt-audio model is OpenAI's first generally available audio model.
qwen3-235b-a22b-thinking-25071 Credit = 43,478 TokensQwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning…
gemma-3-4b-it1 Credit = 200,000 TokensGemma 3 introduces multimodality, supporting vision-language input and text outputs.
gpt-5-pro:batch1 Credit = 1,333 TokensGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
qwen3-14b1 Credit = 43,956 TokensQwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialo…
gemma-3-12b-it1 Credit = 200,000 TokensGemma 3 introduces multimodality, supporting vision-language input and text outputs.
gpt-5.2-codex1 Credit = 5,714 TokensGPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.
qwen3-30b-a3b-thinking-25071 Credit = 50,000 TokensQwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-st…
gpt-audio-mini1 Credit = 16,667 TokensA cost-efficient version of GPT Audio.
qwen3-next-80b-a3b-thinking1 Credit = 66,667 TokensQwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default.
gpt-5.2-chat1 Credit = 5,714 TokensGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong gener…
qwen3-30b-a3b1 Credit = 83,333 TokensQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to e…
gpt-5.21 Credit = 5,714 TokensGPT-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.
qwen3-8b1 Credit = 85,470 TokensQwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dia…
gpt-5.1-codex-max1 Credit = 8,000 TokensGPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.
qwen-2.5-7b-instruct1 Credit = 100,000 TokensQwen2.5 7B is the latest series of Qwen large language models.
gpt-5.2:batch1 Credit = 11,429 TokensGPT-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.
qwen3-next-80b-a3b-instruct1 Credit = 111,111 TokensQwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thi…
gpt-4o-2024-05-131 Credit = 2,000 TokensGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
qwen3-30b-a3b-instruct-25071 Credit = 111,111 TokensQwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.
gpt-4-turbo:batch1 Credit = 2,000 TokensThe latest GPT-4 Turbo model with vision capabilities.
qwen3-235b-a22b-25071 Credit = 114,286 TokensQwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture…
gpt-5.11 Credit = 8,000 TokensGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…
qwen3-32b1 Credit = 125,000 TokensQwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dial…
gpt-5.1-codex1 Credit = 8,000 TokensGPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.
qwen3-coder-30b-a3b-instruct1 Credit = 142,857 TokensQwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed f…
gpt-5-image-mini1 Credit = 4,000 TokensGPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with…
gpt-5.1:batch1 Credit = 16,000 TokensGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…
gpt-5.1-codex-mini1 Credit = 40,000 TokensGPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
gpt-3.5-turbo-16k1 Credit = 3,333 TokensThis 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…
gpt-4o-2024-11-201 Credit = 4,000 TokensThe 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improv…
gpt-4o-2024-08-061 Credit = 4,000 TokensThe 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respo…
gpt-4o1 Credit = 4,000 TokensGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
gpt-oss-safeguard-20b1 Credit = 133,333 Tokensgpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.
o31 Credit = 5,000 Tokenso3 is a well-rounded and powerful model across domains.
gpt-4.11 Credit = 5,000 TokensGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…
gpt-3.5-turbo-instruct1 Credit = 6,667 TokensThis model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations.
gpt-51 Credit = 8,000 TokensGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
gpt-4o:batch1 Credit = 8,000 TokensGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
o4-mini-high1 Credit = 9,091 TokensOpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high.
o4-mini1 Credit = 9,091 TokensOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multim…
o3-mini-high1 Credit = 9,091 TokensOpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high.
o3-mini1 Credit = 9,091 TokensOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and…
o3:batch1 Credit = 10,000 Tokenso3 is a well-rounded and powerful model across domains.
gpt-4.1:batch1 Credit = 10,000 TokensGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…
gpt-3.5-turbo-06131 Credit = 10,000 TokensGPT-3.5 Turbo is OpenAI's fastest model.
gpt-5:batch1 Credit = 16,000 TokensGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
o4-mini:batch1 Credit = 18,182 TokensOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multim…
o3-mini:batch1 Credit = 18,182 TokensOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and…
gpt-3.5-turbo1 Credit = 20,000 TokensGPT-3.5 Turbo is OpenAI's fastest model.
gpt-4.1-mini1 Credit = 25,000 TokensGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.
gpt-5-mini1 Credit = 40,000 TokensGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.
gpt-3.5-turbo:batch1 Credit = 40,000 TokensGPT-3.5 Turbo is OpenAI's fastest model.
gpt-4.1-mini:batch1 Credit = 50,000 TokensGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.
gpt-oss-120b:batch1 Credit = 66,667 Tokensgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…
gpt-4o-mini1 Credit = 66,667 TokensGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.
gpt-4o-mini-2024-07-181 Credit = 66,667 TokensGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.
gpt-5-mini:batch1 Credit = 80,000 TokensGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.
gpt-4.1-nano1 Credit = 100,000 TokensFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.
gpt-4o-mini:batch1 Credit = 133,333 TokensGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.
gpt-5-nano1 Credit = 200,000 TokensGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…
gpt-oss-20b:batch1 Credit = 200,000 Tokensgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
gpt-4.1-nano:batch1 Credit = 200,000 TokensFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.
gpt-oss-120b1 Credit = 270,270 Tokensgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…
gpt-oss-20b1 Credit = 333,333 Tokensgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
gpt-5-nano:batch1 Credit = 400,000 TokensGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…
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.