jishie

LLM Gateway

187 models · llmgateway · prices provider-declared (via models.dev). Machine: GET /v1/models?provider=llmgateway.

ModelInput $/1MOutput $/1MContextCapabilities
Claude Haiku 4.5 (latest)claude-haiku-4-5-freefreefree200ktools · vision
Auto Routeautofreefree128ktools · vision
Custom Modelcustomfreefree128ktools · vision
Llama 3.2 3B Instructllama-3.2-3b-instruct$0.03$0.0533k
Qwen3.7 Flashqwen3.7-flash$0.03$0.131000ktools · reasoning · vision
GPT OSS 120Bgpt-oss-120b$0.032$0.14131ktools · reasoning
GPT OSS 20Bgpt-oss-20b$0.04$0.15131ktools · reasoning
DeepSeek V4 Flashdeepseek-v4-flash$0.076$0.1531050ktools · reasoning
Ministral 3Bministral-3b-2512$0.1$0.1131kvision
GLM-4 32B (0414-128k)glm-4-32b-0414-128k$0.1$0.1128ktools
Nemotron 3 Nano Omninemotron-3-nano-omni$0.06$0.24262ktools · reasoning · vision
Nemotron 3 Nano 30Bnemotron-3-nano-30b$0.06$0.24262ktools · reasoning
Qwen3.5 9Bqwen3.5-9b$0.1$0.15262ktools · reasoning · vision
Qwen3-Coder 30B-A3B Instructqwen3-coder-30b-a3b-instruct$0.07$0.27262ktools
Seed 1.6 Flash (250715)seed-1-6-flash-250715$0.07$0.3256ktools · reasoning · vision
GLM-4.6V FlashXglm-4.6v-flashx$0.04$0.4128ktools · reasoning · vision
Llama 3.2 11B Instructllama-3.2-11b-instruct$0.07$0.33128k
Gemma 4 26B A4B ITgemma-4-26b-a4b-it$0.07$0.34262ktools · reasoning · vision
Qwen Flashqwen-flash$0.05$0.41000ktools · reasoning
Qwen3 VL Flashqwen3-vl-flash$0.05$0.4262ktools · vision
GPT-5 Nanogpt-5-nano$0.05$0.4400ktools · reasoning · vision
MiniMax-M2.7minimax-m2.7$0.08$0.32205ktools · reasoning
GLM-4.7-Flashglm-4.7-flash$0.06$0.4200ktools · reasoning
Ministral 8Bministral-8b-2512$0.15$0.15262kvision
Mistral Small 3.2mistral-small-2506$0.1$0.3128ktools · vision
Qwen3 32Bqwen3-32b$0.1$0.341ktools · reasoning
Cosmos 3 Super Reasonercosmos3-super-reasoner$0.1$0.3262ktools · reasoning · vision
Gemma 3 27Bgemma-3-27b$0.1$0.3110ktools · vision
Qwen3 30B A3B Instruct (2507)qwen3-30b-a3b-instruct-2507$0.1$0.3262ktools
Gemma 4 31B ITgemma-4-31b-it$0.102$0.297262ktools · reasoning · vision
GLM-4.7-FlashXglm-4.7-flashx$0.07$0.4200ktools · reasoning
GPT-4.1 nanogpt-4.1-nano$0.1$0.41000ktools · vision
MiMo-V2.5mimo-v2.5$0.14$0.281000ktools · reasoning · vision
Gemini 2.5 Flash-Litegemini-2.5-flash-lite$0.1$0.41049ktools · reasoning · vision
Llama-3.3-70B-Instructllama-3.3-70b-instruct$0.13$0.4131ktools
Hermes 4 70Bhermes-4-70b$0.13$0.4131ktools · reasoning
Ministral 14Bministral-14b-2512$0.2$0.2262kvision
MiniMax M2.1 Lightningminimax-m2.1-lightning$0.12$0.48197kreasoning
Qwen3 235B A22B Instruct (2507)qwen3-235b-a22b-instruct-2507$0.09$0.58262ktools
Qwen3 Coder Nextqwen3-coder-next$0.108$0.675262ktools · reasoning
Hy3hy3$0.14$0.58262ktools · reasoning
GPT-4o minigpt-4o-mini$0.15$0.6128ktools · vision
Qwen3 VL 30B A3B Instructqwen3-vl-30b-a3b-instruct$0.15$0.6262ktools · vision
GPT-4o Mini Search Previewgpt-4o-mini-search-preview$0.15$0.6128kvision
Grok 4.1 Fast Reasoninggrok-4-1-fast-reasoning$0.2$0.52000ktools · reasoning · vision
Grok 4.1 Fast Non-Reasoninggrok-4-1-fast-non-reasoning$0.2$0.52000ktools · vision
Llama 4 Scout 17B Instructllama-4-scout-17b-instruct$0.18$0.59131kvision
DeepSeek V3.2deepseek-v3.2$0.26$0.38164ktools · reasoning · vision
GLM-4.5-Airglm-4.5-air$0.13$0.85131ktools · reasoning
Qwen-Omni Turboqwen-omni-turbo$0.2$0.833ktools · vision
Qwen3 235B A22B FP8qwen3-235b-a22b-fp8$0.2$0.841ktools · reasoning
Qwen3 VL 235B A22B Instructqwen3-vl-235b-a22b-instruct$0.2$0.88262ktools · vision
Qwen2.5-VL 72B Instructqwen2-5-vl-72b-instruct$0.25$0.7532ktools · vision
MiniMax-M2minimax-m2$0.2$1197ktools · reasoning
Qwen3-Next 80B-A3B (Thinking)qwen3-next-80b-a3b-thinking$0.15$1.2131ktools · reasoning
Qwen3-Next 80B-A3B Instructqwen3-next-80b-a3b-instruct$0.15$1.2131ktools
Llama 4 Maverick 17B Instructllama-4-maverick-17b-instruct$0.27$0.851049kvision
MiniMax Text 01minimax-text-01$0.2$1.11000kreasoning
Kimi K2.6kimi-k2.6$0.22$1.137262ktools · reasoning · vision
GLM-4.6Vglm-4.6v$0.3$0.9131ktools · reasoning · vision
Codestralcodestral-2508$0.3$0.9256k
Nemotron 3 Super 120Bnemotron-3-super-120b$0.3$0.9262ktools · reasoning
GPT-5.6 Lunagpt-5.6-luna$0.2$1.21050ktools · reasoning · vision
GPT-5.4 nanogpt-5.4-nano$0.2$1.25400ktools · reasoning · vision
MiniMax-M2.1minimax-m2.1$0.27$1.1205ktools · reasoning
MiniMax-M3minimax-m3$0.3$1.21049ktools · reasoning · vision
MiniMax-M2.5minimax-m2.5$0.3$1.2229ktools · reasoning
DeepSeek V4 Prodeepseek-v4-pro$0.435$0.871050ktools · reasoning
MiMo-V2.5-Promimo-v2.5-pro$0.435$0.871000ktools · reasoning
Qwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instruct$0.3$1.3262ktools
Qwen3-VL Plusqwen3-vl-plus$0.2$1.6262ktools · reasoning · vision
Qwen3.6 35B-A3Bqwen3.6-35b-a3b$0.248$1.485262ktools · reasoning · vision
Gemini 3.1 Flash Litegemini-3.1-flash-lite$0.25$1.51049ktools · reasoning · vision
Qwen3.6 Flashqwen3.6-flash$0.25$1.51000ktools · reasoning · vision
Llama 3 70B Instructllama-3-70b-instruct$0.51$0.748k
Qwen3 Coder Flashqwen3-coder-flash$0.3$1.51000ktools
Qwen Plus Latestqwen-plus-latest$0.4$1.21000ktools · vision
Qwen Plusqwen-plus$0.4$1.2131ktools · reasoning
Qwen Coder Plusqwen-coder-plus$0.502$1.004131ktools
GPT-5.1 Codex minigpt-5.1-codex-mini$0.25$2400ktools · reasoning · vision
Seed 1.8 (251228)seed-1-8-251228$0.25$2256ktools · reasoning · vision
Seed 1.6 (250915)seed-1-6-250915$0.25$2256ktools · reasoning · vision
GPT-5 Minigpt-5-mini$0.25$2400ktools · reasoning · vision
Seed 1.6 (250615)seed-1-6-250615$0.25$2256ktools · reasoning · vision
Qwen3.7 Plusqwen3.7-plus$0.4$1.61000ktools · reasoning · vision
GPT-4.1 minigpt-4.1-mini$0.4$1.61000ktools · vision
Llama 3.1 70B Instructllama-3.1-70b-instruct$0.72$0.72128k
GPT-3.5-turbogpt-3.5-turbo$0.5$1.516k
Mistral Large 3mistral-large-2512$0.5$1.5262ktools · vision
MiniCPM-V 4.5minicpm-v-4.5$0.658$1.1132ktools · vision
GLM-4.7glm-4.7$0.38$1.98205ktools · reasoning
Kimi K2.5kimi-k2.5$0.405$1.98262ktools · reasoning · vision
Devstral 2devstral-2512$0.4$2262ktools
Gemini 2.5 Flashgemini-2.5-flash$0.3$2.51049ktools · reasoning · vision
Gemini 3.5 Flash Litegemini-3.5-flash-lite$0.3$2.51049ktools · reasoning · vision
GLM-5.2glm-5.2$0.55$1.92551049ktools · reasoning
GLM-4.5Vglm-4.5v$0.6$1.8128ktools · reasoning · vision
Llama 3.1 Nemotron Ultra 253Bllama-3.1-nemotron-ultra-253b$0.6$1.8128k
GLM-4.6glm-4.6$0.55$2.2205ktools · reasoning
Qwen3 235B A22B Thinking (2507)qwen3-235b-a22b-thinking-2507$0.3$3262ktools · reasoning
Sonarsonar$1$1130k
GLM-4.5glm-4.5$0.6$2.2131ktools · reasoning
Nemotron 3 Ultra 550B A55Bnemotron-3-ultra-550b$0.5$2.51049ktools · reasoning
Kimi K2kimi-k2$0.57$2.3256ktools
MiniMax-M2.7-highspeedminimax-m2.7-highspeed$0.6$2.4205ktools · reasoning
MiniMax-M2.5-highspeedminimax-m2.5-highspeed$0.6$2.4205ktools · reasoning
Kimi K2 Thinkingkimi-k2-thinking$0.6$2.5262ktools · reasoning
GLM-5glm-5$0.72$2.3203ktools · reasoning
Gemini 3 Flash Previewgemini-3-flash-preview$0.5$31049ktools · reasoning · vision
Qwen3.6 Plusqwen3.6-plus$0.5$3262ktools · reasoning · vision
Grok Build 0.1grok-build-0-1$1$2256ktools · reasoning · vision
Qwen3.5 397B-A17Bqwen35-397b-a17b$0.6$3.6262ktools · reasoning · vision
GLM-5.1glm-5.1$0.931$2.93205ktools · reasoning
Qwen3 Maxqwen3-max$0.845$3.38262ktools
Hermes 4 405Bhermes-4-405b$1$3131ktools · reasoning
Grok 4.3grok-4-3$1.25$2.51000ktools · reasoning · vision
Grok 4.20 (Reasoning)grok-4-20-reasoning$1.25$2.52000ktools · reasoning · vision
Grok 4.20 (Non-Reasoning)grok-4-20-non-reasoning$1.25$2.52000ktools · vision
GPT-5.4 minigpt-5.4-mini$0.75$4.5400ktools · reasoning · vision
Kimi K2.7 Codekimi-k2.7-code$0.95$4262ktools · reasoning · vision
Qwen3 VL 235B A22B Thinkingqwen3-vl-235b-a22b-thinking$0.98$3.95131ktools · reasoning · vision
Qwen3.7 Maxqwen3.7-max$1.25$3.751000ktools · reasoning
o3-minio3-mini$1.1$4.4200ktools · reasoning
o4-minio4-mini$1.1$4.4200ktools · reasoning · vision
GLM-4.5 AirXglm-4.5-airx$1.1$4.5128ktools
Muse Spark 1.1muse-spark-1.1$1.25$4.251049ktools · reasoning · vision
Claude Haiku 4.5 (latest)claude-haiku-4-5$1$5200ktools · reasoning · vision
Muse Spark 1.2muse-spark-1.2$1.25$4.251049ktools · reasoning · vision
Claude Haiku 4.5claude-haiku-4-5-20251001$1$5200ktools · reasoning · vision
Qwen2.5 VL 32B Instructqwen2-5-vl-32b-instruct$1.4$4.2131ktools · vision
GPT-4o Mini Transcribegpt-4o-mini-transcribe$1.25$516ktools
Qwen3.8 Max Previewqwen3.8-max$1.815$5.44611000ktools · reasoning · vision
Qwen Maxqwen-max$1.6$6.433ktools
Qwen Max Latestqwen-max-latest$1.6$6.433ktools · vision
Qwen3.6 Max Previewqwen3.6-max-preview$1.3$7.8262ktools · reasoning
Grok 4.5grok-4-5$2$6500ktools · reasoning · vision
Grok 4.20 (Non-Reasoning)grok-4-20-beta-0309-non-reasoning$2$62000ktools · vision
Grok 4.20 (Reasoning)grok-4-20-beta-0309-reasoning$2$62000ktools · reasoning · vision
Gemini 3.6 Flashgemini-3.6-flash$1.5$7.51049ktools · reasoning · vision
Gemini 3.5 Flashgemini-3.5-flash$1.5$91049ktools · reasoning · vision
Kimi K2.7 Code Highspeedkimi-k2.7-code-highspeed$1.9$8262ktools · reasoning · vision
GPT-5gpt-5$1.25$10400ktools · reasoning · vision
GPT-5.1gpt-5.1$1.25$10400ktools · reasoning · vision
Gemini 2.5 Progemini-2.5-pro$1.25$101049ktools · reasoning · vision
GPT-5.1 Codexgpt-5.1-codex$1.25$10400ktools · reasoning · vision
o3o3$2$8200ktools · reasoning · vision
GPT-4.1gpt-4.1$2$81000ktools · vision
Sonar Reasoning Prosonar-reasoning-pro$2$8128kreasoning · vision
GLM-4.5 Xglm-4.5-x$2.2$8.9128ktools · reasoning
Claude Sonnet 5claude-sonnet-5$2$101000kreasoning · vision
GPT-4ogpt-4o$2.5$10128ktools · vision
GPT-4o Search Previewgpt-4o-search-preview$2.5$10128kvision
GPT-4o Transcribegpt-4o-transcribe$2.5$1016ktools
Gemini Pro Latestgemini-pro-latest$2$121049ktools · reasoning · vision
Gemini 3.1 Pro Previewgemini-3.1-pro-preview$2$121049ktools · reasoning · vision
GPT-5.6 Terragpt-5.6-terra$2$121050ktools · reasoning · vision
GPT-5.2 Codexgpt-5.2-codex$1.75$14400ktools · reasoning · vision
GPT-5.2gpt-5.2$1.75$14400ktools · reasoning · vision
GPT-5.3 Codexgpt-5.3-codex$1.75$14400ktools · reasoning · vision
GPT-5.4gpt-5.4$2.5$151050ktools · reasoning · vision
Grok 4grok-4$3$15256ktools · vision
Claude Sonnet 4.6claude-sonnet-4-6$3$151000ktools · reasoning · vision
Sonar Prosonar-pro$3$15200kvision
Claude Sonnet 4.5 (latest)claude-sonnet-4-5$3$15200ktools · reasoning · vision
Claude Sonnet 4.5claude-sonnet-4-5-20250929$3$15200ktools · reasoning · vision
Kimi K3kimi-k3$3$151049ktools · reasoning · vision
Mistral Large (latest)mistral-large-latest$4$12128ktools · vision
Kimi K3kimi-k3-fast$4.5$22.51040ktools · reasoning · vision
Claude Opus 4.6claude-opus-4-6$5$251000ktools · reasoning · vision
Claude Opus 4.8claude-opus-4-8$5$251000ktools · reasoning · vision
Claude Opus 4.5claude-opus-4-5-20251101$5$25200ktools · reasoning · vision
Claude Opus 4.7claude-opus-4-7$5$251000ktools · reasoning · vision
Claude Opus 5claude-opus-5$5$251000ktools · reasoning · vision
Fugu Ultrafugu-ultra$5$301000ktools · reasoning · vision
GPT-5.6 Solgpt-5.6-sol$5$301050ktools · reasoning · vision
GPT-5.5gpt-5.5$5$301050ktools · reasoning · vision
GPT-4 Turbogpt-4-turbo$10$30128ktools · vision
Qwen3 Coder Plusqwen3-coder-plus$6$601000ktools
Claude Fable 5claude-fable-5$10$501000ktools · reasoning · vision
o1o1$15$60200ktools · reasoning · vision
Claude 3 Opusclaude-3-opus$15$75200ktools · vision
Claude Opus 4.1claude-opus-4-1-20250805$15$75200ktools · reasoning · vision
GPT-4gpt-4$30$608ktools
GPT-5 Progpt-5-pro$15$120400ktools · reasoning · vision
GPT-5.2 Progpt-5.2-pro$21$168400ktools · reasoning · vision
GPT-5.5 Progpt-5.5-pro$30$1801050ktools · reasoning · vision
GPT-5.4 Progpt-5.4-pro$30$1801050ktools · reasoning · vision