Skip to content

LLMs that support tool calling

804 models are declared by their gateway as accepting tool-calling or structured-output parameters — the prerequisite for using one in an agent loop.

ModelVendorTypeAvailable onContextInput / Mtok
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 DeepSeek Multimodal BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.050–$0.300
GLM 5.3 z-ai/glm-5.3 Z.ai Multimodal BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.078–$1.40
GLM 5.3 Flash z-ai/glm-5.3-flash Z.ai Multimodal BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel 1M $0.029–$0.150
Claude Fable 5 anthropic/claude-fable-5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $8.36–$10.00
Claude Fable 5.1 anthropic/claude-fable-5.1 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $6.50–$10.00
Claude Haiku 4.5 anthropic/claude-haiku-4.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 200K $0.850–$1.00
Claude Opus 4.6 anthropic/claude-opus-4.6 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $3.45–$5.00
Claude Opus 4.7 anthropic/claude-opus-4.7 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $3.58–$5.50
Claude Opus 4.8 anthropic/claude-opus-4.8 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $3.25–$5.50
Claude Opus 5 anthropic/claude-opus-5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $3.45–$5.50
Claude Opus 5.5 anthropic/claude-opus-5.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $3.34–$4.40
Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $2.01–$3.00
Claude Sonnet 5 anthropic/claude-sonnet-5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $1.30–$2.20
Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampRequestyVercel 1M $1.43–$2.20
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash DeepSeek Multimodal BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel 1M $0.045–$0.300
Muse Spark Open meta-llama/muse-spark-open Meta Multimodal BasetenCheaper InferenceCloudflareConcentrateExperiential LabsFireworksNanoGPTOpenRouterRampRequestyVercel 1M $1.06–$1.25
Kimi K3 moonshotai/kimi-k3 Moonshot AI Multimodal BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel 1M $0.149–$3.00
o3 openai/o3 OpenAI Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterRampRequestySayGMVercel 200K $1.30–$2.00
Qwen3.8 27B qwen/qwen3.8-27b Qwen Text Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequestySayGMVercel 1M $0.049–$0.500
Claude Haiku 5.5 anthropic/claude-haiku-5.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterRampRequestyVercel 1M $0.065–$0.100
Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterRampRequestyVercel 1M $1.95–$3.00
Muse Spark 1.1 meta-llama/muse-spark-1.1 Meta Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampVercel 1M $1.06–$1.25
Muse Spark 1.2 meta-llama/muse-spark-1.2 Meta Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRampVercel 1M $1.06–$1.25
Muse Spark 1.3 meta-llama/muse-spark-1.3 Meta Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterRampRequestyVercel 1M $1.06–$1.25
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Multimodal Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250
Qwen 3.5 9B qwen/qwen3.5-9b Qwen Multimodal Cheaper InferenceCloudflareConcentrateDarkbloomExperiential LabsLLM GatewayNanoGPTOpenRouterRequestyTogether 262.1K $0.040–$0.170
Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterSailSayGM 1M $0.076–$0.248
Qwen3.7 Plus qwen/qwen3.7-plus Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequestyTogether 1M $0.265–$0.400
Qwen3.8 Max qwen/qwen3.8-max Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsFireworksLLM GatewayNanoGPTOrcaRouterRampRequesty 1M $1.41–$2.00
MiMo V2.6 Flash xiaomi/mimo-v2.6-flash Xiaomi Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequestyVercel 1.1M $0.118–$0.140
Claude 4.5 Opus anthropic/claude-opus-4.5 Anthropic Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsNanoGPTOpenRouterOrcaRouterRequestyVercel 200K $3.25–$5.00
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 DeepSeek Text BasetenCloudflareMorphNanoGPTOpenRouterOrcaRouterRequestySailVercel 1M $0.050–$0.220
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 DeepSeek Text BasetenCloudflareNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel 1M $0.115–$1.32
Qwen3.5 27B qwen/qwen3.5-27b Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.086–$0.300
Qwen3.6 Plus qwen/qwen3.6-plus Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterTogether 1M $0.276–$0.500
Qwen3.7 Flash qwen/qwen3.7-flash Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterVercel 1M $0.025–$0.030
Qwen3.7 Max qwen/qwen3.7-max Qwen Text Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterTogether 1M $1.25–$2.50
Qwen Flash qwen/qwen3.8-flash Qwen Text Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouterTogether 1M $0.050–$0.150
GLM 5.2 z-ai/glm-5.2 Z.ai Multimodal BasetenCloudflareNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel 1M $0.0060–$1.40
Gemma 4 26B google/gemma-4-26b-a4b-it Google Multimodal CloudflareConcentrateDarkbloomNanoGPTOpenRouterOrcaRouterRequestyVercel 262.1K $0.023–$0.150
Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor Meta Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterVercel 1M $0.065–$0.100
Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor Meta Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterVercel 1M $0.073–$0.100
MiniMax M3.1 Flash minimax/minimax-m3.1-flash MiniMax Multimodal CloudflareFireworksNanoGPTOpenRouterOrcaRouterRequestyTogetherVercel 1M $0.150–$0.300
OpenAI GPT 120B openai/gpt-oss-120b OpenAI Text BasetenCloudflareFireworksNanoGPTOpenRouterRequestyTogetherVercel 131.1K $0.030–$0.150
Qwen3 32B qwen/qwen3-32b Qwen Text CloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterRequestyVercel 131.1K $0.080–$0.610
Qwen3.5 122B A10B qwen/qwen3.5-122b-a10b Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterOrcaRouter 262.1K $0.115–$0.400
Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b Qwen Multimodal Cheaper InferenceCloudflareConcentrateExperiential LabsNanoGPTOpenRouterOrcaRouterRequesty 262.1K $0.172–$0.600
Qwen3.6 27B qwen/qwen3.6-27b Qwen Text Cheaper InferenceCloudflareConcentrateExperiential LabsLLM GatewayNanoGPTOpenRouterVercel 262.1K $0.150–$0.600
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b Qwen Text Cheaper InferenceCloudflareExperiential LabsFireworksLLM GatewayOpenRouterRequestyTogether 1M $1.70–$2.50
Gemma 4 31B google/gemma-4-31b-it Google Multimodal CloudflareNanoGPTOpenRouterOrcaRouterRequestySailVercel 262.1K Free–$0.200

Showing the top 50 of 804. Search the full catalog to go further.

How this is measured. Taken from each gateway's own `supported_parameters` list: a model appears here when a gateway declares support for `tools`, `tool_choice`, `structured_outputs`, or `response_format`. That is a statement by the gateway, not a judgement by us, and not a measure of how *well* a model uses tools — no benchmark data is involved. Gateways that publish no parameter list contribute nothing here, so absence from this page is not evidence a model lacks the capability.