AI for Developers
← Back to providers

LLM Gateway

Model Family External ID Context
Auto Route auto auto 128000
Claude 3.5 Haiku claude claude-3-5-haiku 200000
Claude 3.5 Sonnet claude claude-3-5-sonnet 200000
Claude 3.5 Sonnet (2024-10-22) claude claude-3-5-sonnet-20241022 200000
Claude 3.7 Sonnet claude claude-3-7-sonnet 200000
Claude 3.7 Sonnet (2025-02-19) claude claude-3-7-sonnet-20250219 200000
Claude 3 Haiku claude claude-3-haiku 200000
Claude 3 Haiku (2024-03-07) claude claude-3-haiku-20240307 200000
Claude 3 Opus claude claude-3-opus 200000
Claude Haiku 4.5 claude claude-haiku-4-5 200000
Claude Haiku 4.5 (2025-10-01) claude claude-haiku-4-5-20251001 200000
Claude Opus 4.1 claude claude-opus-4-1-20250805 200000
Claude Opus 4 (2025-05-14) claude claude-opus-4-20250514 200000
Claude Opus 4.5 claude claude-opus-4-5-20251101 200000
Claude Opus 4.6 claude claude-opus-4-6 1000000
Claude Sonnet 4 (2025-05-14) claude claude-sonnet-4-20250514 200000
Claude Sonnet 4.5 claude claude-sonnet-4-5 200000
Claude Sonnet 4.5 (2025-09-29) claude claude-sonnet-4-5-20250929 200000
Claude Sonnet 4.6 claude claude-sonnet-4-6 200000
Codestral mistral codestral-2508 256000
CogView-4 glm cogview-4 2000
Custom Model auto custom 128000
DeepSeek R1 (0528) deepseek deepseek-r1-0528 64000
DeepSeek V3.1 deepseek deepseek-v3.1 128000
DeepSeek V3.2 deepseek deepseek-v3.2 163840
Devstral 2 mistral devstral-2512 262144
Devstral Small 1.1 mistral devstral-small-2507 131072
Gemini 2.0 Flash gemini gemini-2.0-flash 1048576
Gemini 2.0 Flash Lite gemini gemini-2.0-flash-lite 1048576
Gemini 2.5 Flash gemini gemini-2.5-flash 1048576
Gemini 2.5 Flash Image gemini gemini-2.5-flash-image 32768
Gemini 2.5 Flash Image (Preview) gemini gemini-2.5-flash-image-preview 32768
Gemini 2.5 Flash Lite gemini gemini-2.5-flash-lite 1048576
Gemini 2.5 Flash Lite Preview (09-2025) gemini gemini-2.5-flash-lite-preview-09-2025 1048576
Gemini 2.5 Pro gemini gemini-2.5-pro 1048576
Gemini 3.1 Flash Image (Preview) gemini gemini-3.1-flash-image-preview 65536
Gemini 3.1 Flash Lite (Preview) gemini gemini-3.1-flash-lite-preview 1048576
Gemini 3.1 Pro (Preview) gemini gemini-3.1-pro-preview 1048576
Gemini 3 Flash (Preview) gemini gemini-3-flash-preview 1048576
Gemini 3 Pro Image (Preview) gemini gemini-3-pro-image-preview 65536
Gemini Pro Latest gemini gemini-pro-latest 1048576
Gemma 2 27B IT gemma gemma-2-27b-it-together 8192
Gemma 3 12B IT gemma gemma-3-12b-it 1000000
Gemma 3 1B IT gemma gemma-3-1b-it 1000000
Gemma 3 27B gemma gemma-3-27b 128000
Gemma 3 4B IT gemma gemma-3-4b-it 1000000
Gemma 3n E2B IT gemma gemma-3n-e2b-it 1000000
Gemma 3n E4B IT gemma gemma-3n-e4b-it 1000000
GLM-4 32B (0414-128k) glm glm-4-32b-0414-128k 128000
GLM-4.5 glm glm-4.5 128000
GLM-4.5 Air glm glm-4.5-air 128000
GLM-4.5 AirX glm glm-4.5-airx 128000
GLM-4.5 Flash glm glm-4.5-flash 128000
GLM-4.5V glm glm-4.5v 128000
GLM-4.5 X glm glm-4.5-x 128000
GLM-4.6 glm glm-4.6 200000
GLM-4.6V glm glm-4.6v 128000
GLM-4.6V Flash glm glm-4.6v-flash 128000
GLM-4.6V FlashX glm glm-4.6v-flashx 128000
GLM-4.7 glm glm-4.7 200000
GLM-4.7 Flash glm glm-4.7-flash 200000
GLM-4.7 FlashX glm glm-4.7-flashx 200000
GLM-5 glm glm-5 202800
GLM-Image glm glm-image 2000
GPT-3.5 Turbo gpt gpt-3.5-turbo 16385
GPT-4 gpt gpt-4 8192
GPT-4.1 gpt gpt-4.1 1000000
GPT-4.1 Mini gpt gpt-4.1-mini 1000000
GPT-4.1 Nano gpt gpt-4.1-nano 1000000
GPT-4o gpt gpt-4o 128000
GPT-4o Mini gpt gpt-4o-mini 128000
GPT-4o Mini Search Preview gpt gpt-4o-mini-search-preview 128000
GPT-4o Search Preview gpt gpt-4o-search-preview 128000
GPT-4 Turbo gpt gpt-4-turbo 128000
GPT-5 gpt gpt-5 400000
GPT-5.1 gpt gpt-5.1 400000
GPT-5.1 Codex gpt gpt-5.1-codex 400000
GPT-5.1 Codex mini gpt gpt-5.1-codex-mini 400000
GPT-5.2 gpt gpt-5.2 400000
GPT-5.2 Chat gpt gpt-5.2-chat-latest 128000
GPT-5.2 Codex gpt gpt-5.2-codex 400000
GPT-5.2 Pro gpt gpt-5.2-pro 400000
GPT-5.3 Chat gpt gpt-5.3-chat-latest 128000
GPT-5.3 Codex gpt gpt-5.3-codex 400000
GPT-5.4 gpt gpt-5.4 1050000
GPT-5.4 Mini gpt gpt-5.4-mini 400000
GPT-5.4 Nano gpt gpt-5.4-nano 400000
GPT-5.4 Pro gpt gpt-5.4-pro 1050000
GPT-5 Chat Latest gpt gpt-5-chat-latest 400000
GPT-5 Mini gpt gpt-5-mini 400000
GPT-5 Nano gpt gpt-5-nano 400000
GPT-5 Pro gpt gpt-5-pro 400000
GPT OSS 120B gpt-oss gpt-oss-120b 131072
GPT OSS 20B gpt-oss gpt-oss-20b 131072
Grok-3 grok grok-3 131072
Grok 4 grok grok-4 256000
Grok 4 (0709) grok grok-4-0709 256000
Grok 4.1 Fast grok grok-4-1-fast 2000000
Grok 4.1 Fast Non-Reasoning grok grok-4-1-fast-non-reasoning 2000000
Grok 4.1 Fast Reasoning grok grok-4-1-fast-reasoning 2000000
Grok 4.20 Beta Non-Reasoning (0309) grok grok-4-20-beta-0309-non-reasoning 2000000
Grok 4.20 Beta Reasoning (0309) grok grok-4-20-beta-0309-reasoning 2000000
Grok 4.20 Multi-Agent Beta (0309) grok grok-4-20-multi-agent-beta-0309 2000000
Grok 4 Fast grok grok-4-fast 2000000
Grok 4 Fast Non-Reasoning grok grok-4-fast-non-reasoning 2000000
Grok 4 Fast Reasoning grok grok-4-fast-reasoning 2000000
Grok Code Fast 1 grok grok-code-fast-1 256000
Grok Imagine Image grok grok-imagine-image 2000
Grok Imagine Image Pro grok grok-imagine-image-pro 2000
Hermes 2 Pro Llama 3 8B nousresearch hermes-2-pro-llama-3-8b 8192
Kimi K2 kimi kimi-k2 131072
Kimi K2.5 kimi kimi-k2.5 262144
Kimi K2 Thinking kimi kimi-k2-thinking 262144
Kimi K2 Thinking Turbo kimi kimi-k2-thinking-turbo 262144
Llama 3.1 70B Instruct llama llama-3.1-70b-instruct 128000
Llama 3.1 8B Instruct llama llama-3.1-8b-instruct 128000
Llama 3.1 Nemotron Ultra 253B llama llama-3.1-nemotron-ultra-253b 128000
Llama 3.2 11B Instruct llama llama-3.2-11b-instruct 128000
Llama 3.2 3B Instruct llama llama-3.2-3b-instruct 32768
Llama 3.3 70B Instruct llama llama-3.3-70b-instruct 128000
Llama 3 70B Instruct llama llama-3-70b-instruct 8192
Llama 3 8B Instruct llama llama-3-8b-instruct 8192
Llama 4 Maverick 17B Instruct llama llama-4-maverick-17b-instruct 8192
Llama 4 Scout llama llama-4-scout 32768
Llama 4 Scout 17B Instruct llama llama-4-scout-17b-instruct 8192
Llama Guard 4 12B llama llama-guard-4-12b 131072
MiniMax M2 minimax minimax-m2 196608
MiniMax M2.1 minimax minimax-m2.1 196608
MiniMax M2.1 Lightning minimax minimax-m2.1-lightning 196608
MiniMax M2.5 minimax minimax-m2.5 204800
MiniMax M2.5 Highspeed minimax minimax-m2.5-highspeed 204800
MiniMax M2.7 minimax minimax-m2.7 204800
MiniMax M2.7 Highspeed minimax minimax-m2.7-highspeed 204800
MiniMax Text 01 minimax minimax-text-01 1000000
Ministral 14B mistral ministral-14b-2512 262144
Ministral 3B mistral ministral-3b-2512 131072
Ministral 8B mistral ministral-8b-2512 262144
Mistral Large 3 mistral mistral-large-2512 262144
Mistral Large Latest mistral mistral-large-latest 128000
Mistral Small 3.2 mistral mistral-small-2506 128000
Mixtral 8x7B Instruct mistral mixtral-8x7b-instruct-together 32768
o1 gpt o1 200000
o3 gpt o3 200000
o3 Mini gpt o3-mini 200000
o4 Mini gpt o4-mini 200000
Pixtral Large Latest mistral pixtral-large-latest 128000
Qwen2.5 Coder 7B qwen qwen25-coder-7b 32768
Qwen2.5 VL 32B Instruct qwen qwen2-5-vl-32b-instruct 131072
Qwen2.5 VL 72B Instruct qwen qwen2-5-vl-72b-instruct 32768
Qwen3 235B A22B FP8 qwen qwen3-235b-a22b-fp8 40960
Qwen3 235B A22B Instruct 2507 qwen qwen3-235b-a22b-instruct-2507 262000
Qwen3 235B A22B Thinking 2507 qwen qwen3-235b-a22b-thinking-2507 262000
Qwen3 30B A3B FP8 qwen qwen3-30b-a3b-fp8 40960
Qwen3 30B A3B Instruct 2507 qwen qwen3-30b-a3b-instruct-2507 262000
Qwen3 30B A3B Thinking 2507 qwen qwen3-30b-a3b-thinking-2507 262000
Qwen3 32B qwen qwen3-32b 32768
Qwen3 32B FP8 qwen qwen3-32b-fp8 40960
Qwen3 4B FP8 qwen qwen3-4b-fp8 128000
Qwen3.5 397B A17B qwen qwen35-397b-a17b 262144
Qwen3 Coder 30B A3B Instruct qwen qwen3-coder-30b-a3b-instruct 262000
Qwen3 Coder 480B A35B Instruct qwen qwen3-coder-480b-a35b-instruct 262000
Qwen3 Coder Flash qwen qwen3-coder-flash 1000000
Qwen3 Coder Next qwen qwen3-coder-next 262144
Qwen3 Coder Plus qwen qwen3-coder-plus 1000000
Qwen3 Max qwen qwen3-max 256000
Qwen3 Max 2026-01-23 qwen qwen3-max-2026-01-23 262144
Qwen3 Next 80B A3B Instruct qwen qwen3-next-80b-a3b-instruct 129024
Qwen3 Next 80B A3B Thinking qwen qwen3-next-80b-a3b-thinking 131072
Qwen3 VL 235B A22B Instruct qwen qwen3-vl-235b-a22b-instruct 131072
Qwen3 VL 235B A22B Thinking qwen qwen3-vl-235b-a22b-thinking 131072
Qwen3 VL 30B A3B Instruct qwen qwen3-vl-30b-a3b-instruct 131072
Qwen3 VL 30B A3B Thinking qwen qwen3-vl-30b-a3b-thinking 131072
Qwen3 VL 8B Instruct qwen qwen3-vl-8b-instruct 131072
Qwen3 VL Flash qwen qwen3-vl-flash 262144
Qwen3 VL Plus qwen qwen3-vl-plus 262144
Qwen Coder Plus qwen qwen-coder-plus 131072
Qwen Flash qwen qwen-flash 1000000
Qwen Image qwen qwen-image 2000
Qwen Image Edit Max qwen qwen-image-edit-max 2000
Qwen Image Edit Plus qwen qwen-image-edit-plus 2000
Qwen Image Max qwen qwen-image-max 2000
Qwen Image Max 2025-12-30 qwen qwen-image-max-2025-12-30 2000
Qwen Image Plus qwen qwen-image-plus 2000
Qwen Max qwen qwen-max 131072
Qwen Max Latest qwen qwen-max-latest 131072
Qwen Omni Turbo qwen qwen-omni-turbo 32768
Qwen Plus qwen qwen-plus 131072
Qwen Plus Latest qwen qwen-plus-latest 1000000
Qwen Turbo qwen qwen-turbo 1000000
Qwen VL Max qwen qwen-vl-max 131072
Qwen VL Plus qwen qwen-vl-plus 131072
QwQ Plus qwen qwq-plus 131072
Seed 1.6 (250615) seed seed-1-6-250615 256000
Seed 1.6 (250915) seed seed-1-6-250915 256000
Seed 1.6 Flash (250715) seed seed-1-6-flash-250715 256000
Seed 1.8 (251228) seed seed-1-8-251228 256000
Seedream 4.0 seed seedream-4-0 2000
Seedream 4.5 seed seedream-4-5 2000
Sonar sonar sonar 130000
Sonar Pro sonar sonar-pro 200000
Sonar Reasoning Pro sonar sonar-reasoning-pro 128000
Veo 3.1 gemini veo-3.1-generate-preview 32768
Veo 3.1 Fast gemini veo-3.1-fast-generate-preview 32768