vercel

Vercel AI Gateway

All current catalogue offerings from this provider. Documentation remains authoritative.

Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)

327 offerings

ModelContext / outputCapabilitiesLowest inputProviders
DeepSeek V4 Flashdeepseek-v4-flash · deepseek-flash1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0055fresh
DeepSeek V4 Prodeepseek-v4-pro · deepseek-thinking1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0055fresh
Kimi K2.7 Codekimi-k2.7-code · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0047fresh
Kimi K2.5kimi-k2.5 · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0049fresh
Claude Opus 4.7claude-opus-4.7 · claude-opus1.05MOutput 128K
Tool callingReasoningImage inputJSON
$4.00out $20.0011fresh
GPT-5.5gpt-5.5 · gpt1.05MOutput 128K
Tool callingReasoningImage inputJSON
$0.19out $1.1335fresh
GLM 5.2glm-5.2 · glm1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0065fresh
GLM-5.1glm-5.1 · glm205KOutput 205K
Tool callingReasoningJSONOpen weights
$0.00out $0.0047fresh
MiniMax-M2.5minimax-m2.5 · minimax223KOutput 204K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0045fresh
GPT-5.6 Solgpt-5.6-sol · gpt-sol1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$1.50out $12.0025fresh
GPT-5.6 Lunagpt-5.6-luna · gpt-luna1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.10out $0.6025fresh
GPT-5.6 Terragpt-5.6-terra · gpt-terra1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$1.00out $2.0025fresh
GPT-5.4gpt-5.4 · gpt1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.75out $6.0035fresh
Qwen3 Max Previewqwen3-max-preview256KOutput 64K
Tool calling
$0.00out $0.003fresh
DeepSeek-R1deepseek-r11MOutput 384K
Tool callingReasoningJSONOpen weights
$0.00out $0.0019fresh
DeepSeek-V3.1deepseek-v3.1164KOutput 164K
Tool callingReasoningJSONOpen weights
$0.20out $0.7015fresh
DeepSeek-V3deepseek-v3164KOutput 164K
Tool callingJSONOpen weights
$0.00out $0.0015fresh
Gemini 2.5 Flash Litegemini-2.5-flash-lite1.05MOutput 64K
Tool callingReasoningImage inputJSON
$0.070out $0.1021fresh
Kimi K2kimi-k2256KOutput 256K
Tool callingJSONOpen weights
$0.00out $0.008fresh
gpt-oss-120bgpt-oss-120b128KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0055fresh
Gemini 2.5 Flashgemini-2.5-flash1.07MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.090out $0.7130fresh
Qwen3 Next 80B A3B Thinkingqwen3-next-80b-a3b-thinking256KOutput 128K
Tool callingReasoningJSONOpen weights
$0.14out $0.6515fresh
Qwen3 Maxqwen3-max256KOutput 64K
Tool callingReasoningJSON
$0.00out $0.0019fresh
Qwen3 Next 80B A3B Instructqwen3-next-80b-a3b-instruct256KOutput 256K
Tool callingImage inputJSONOpen weights
$0.00out $0.0019fresh
GLM 4.5 Airglm-4.5-air128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.10out $0.2918fresh
Gemini 2.5 Flash Imagegemini-2.5-flash-image32KOutput 64K
ReasoningImage inputJSON
$0.30out $2.5010fresh
Gemini 2.5 Progemini-2.5-pro1.07MOutput 64K
Tool callingReasoningImage inputJSON
$0.87out $7.0029fresh
gpt-oss-20bgpt-oss-20b128KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0034fresh
GLM 4.5glm-4.5128KOutput 96K
Tool callingReasoningJSONOpen weights
$0.00out $0.0018fresh
GLM-4.6glm-4.6 · glm200KOutput 200K
Tool callingReasoningJSONOpen weights
$0.00out $0.0026fresh
GLM-4.7glm-4.7 · glm205KOutput 198K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0036fresh
GLM-5glm-5 · glm205KOutput 205K
Tool callingReasoningJSONOpen weights
$0.00out $0.0043fresh
DeepSeek V3.1 Terminusdeepseek-v3.1-terminus · deepseek164KOutput 164K
Tool callingReasoningJSONOpen weights
$0.25out $0.7011fresh
Kimi K2 Thinkingkimi-k2-thinking · kimi-thinking256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.40out $2.0019fresh
GPT-5gpt-5 · gpt400KOutput 400K
Tool callingReasoningImage inputJSON
$1.07out $8.5028fresh
gpt-5.2gpt-5.2 · gpt400KOutput 128K
Tool callingReasoningImage inputJSON
$0.25out $2.0029fresh
Step 3.5 Flashstep-3.5-flash256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0015fresh
MiniMax-M2.5-highspeedminimax-m2.5-highspeed · minimax200KOutput 128K
Tool callingReasoningJSONOpen weights
$0.00out $0.0010fresh
MiniMax-M2minimax-m2 · minimax1MOutput 400K
Tool callingReasoningJSONOpen weights
$0.00out $0.0018fresh
MiniMax-M2.1minimax-m2.1 · minimax1MOutput 196K
Tool callingReasoningJSONOpen weights
$0.00out $0.0023fresh
Kimi K3kimi-k3 · kimi-k31.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0050fresh
Kimi K3 Fastkimi-k3-fast · kimi-k31.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$3.00out $15.004fresh
GLM 5.2 Fastglm-5.2-fast · glm1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$1.45out $4.503fresh
Kimi K2.6kimi-k2.6 · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0061fresh
Gemma 4 26B A4B ITgemma-4-26b-a4b-it · gemma256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.060out $0.3018fresh
DeepSeek V4 Pro 0813deepseek-v4-pro-0813 · deepseek-thinking1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0019fresh
DeepSeek V4 Flash 0731deepseek-v4-flash-0731 · deepseek-flash1.05MOutput 1.05M
Tool callingReasoningJSONOpen weights
$0.00out $0.0030fresh
GLM-4.7-Flashglm-4.7-flash · glm-flash203KOutput 203K
Tool callingReasoningJSONOpen weights
$0.00out $0.0019fresh
DeepSeek-V3.2-Expdeepseek-v3.2 · deepseek164KOutput 164K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0032fresh
Qwen3.5 Plusqwen3.5-plus · qwen1MOutput 250K
Tool callingReasoningImage input
$0.00out $0.0014fresh
Gemma 4 31B ITgemma-4-31b-it · gemma256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0029fresh
Gemini 3.1 Pro Previewgemini-3.1-pro-preview · gemini-pro1.05MOutput 64K
Tool callingReasoningImage inputJSON
$2.00out $12.0022fresh
Claude Sonnet 4.6claude-sonnet-4.6 · claude-sonnet1MOutput 128K
Tool callingReasoningImage inputJSON
$2.40out $12.0011fresh
Claude Haiku 4.5claude-haiku-4.5 · claude-haiku200KOutput 64K
Tool callingReasoningImage inputJSON
$0.85out $4.309fresh
Claude Opus 4.5claude-opus-4.5 · claude-opus200KOutput 64K
Tool callingReasoningImage inputJSON
$4.30out $21.008fresh
Claude Sonnet 4claude-sonnet-4 · claude-sonnet1MOutput 200K
Tool callingReasoningImage inputJSON
$2.60out $13.0011fresh
Claude Opus 4.6claude-opus-4.6 · claude-opus1MOutput 128K
Tool callingReasoningImage inputJSON
$4.00out $20.0010fresh
Anthropic: Claude Opus 4claude-opus-4 · claude-opus200KOutput 32K
Tool callingReasoningImage input
$13.00out $64.007fresh
Claude Sonnet 4.5claude-sonnet-4.5 · claude-sonnet1MOutput 64K
Tool callingReasoningImage inputJSON
$2.60out $13.008fresh
Grok 4.3grok-4.3 · grok1MOutput 1M
Tool callingReasoningImage inputJSON
$1.25out $2.5018fresh
GPT-4ogpt-4o · gpt128KOutput 128K
Tool callingImage inputJSON
$2.50out $10.0021fresh
GPT-5 Nanogpt-5-nano · gpt-nano400KOutput 400K
Tool callingReasoningImage inputJSON
$0.045out $0.3625fresh
GPT-4o minigpt-4o-mini · gpt-mini128KOutput 128K
Tool callingImage inputJSON
$0.14out $0.5420fresh
GPT-3.5-turbogpt-3.5-turbo · gpt16KOutput 4K
Tool callingImage inputJSON
$0.45out $1.4012fresh
GPT-5.5 Progpt-5.5-pro · gpt-pro1.05MOutput 128K
Tool callingReasoningImage inputJSON
$27.27out $163.6414fresh
GPT-4 Turbogpt-4-turbo · gpt128KOutput 4K
Tool callingImage inputJSON
$9.00out $27.0014fresh
GPT-5.4 Progpt-5.4-pro · gpt-pro1.05MOutput 128K
Tool callingReasoningImage inputJSON
$27.00out $160.0016fresh
gpt-5.1-codex-minigpt-5.1-codex-mini · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$0.22out $1.8017fresh
gpt-5-codexgpt-5-codex · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$1.07out $8.5012fresh
GPT-5 Minigpt-5-mini · gpt-mini400KOutput 400K
Tool callingReasoningImage inputJSON
$0.040out $0.2930fresh
GPT-5.3 Codexgpt-5.3-codex · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$1.60out $13.0023fresh
GPT-4.1 nanogpt-4.1-nano · gpt-nano1.05MOutput 1.05M
Tool callingImage inputJSON
$0.080out $0.2621fresh
GPT-5.4 minigpt-5.4-mini · gpt-mini400KOutput 128K
Tool callingReasoningImage inputJSON
$0.38out $4.0029fresh
gpt-5-progpt-5-pro · gpt-pro400KOutput 272K
Tool callingReasoningImage inputJSON
$13.50out $108.0016fresh
gpt-5.2-codexgpt-5.2-codex · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$0.14out $1.1420fresh
GPT-4.1gpt-4.1 · gpt1.05MOutput 1.05M
Tool callingImage inputJSON
$1.80out $7.2026fresh
gpt-5.2-progpt-5.2-pro · gpt-pro400KOutput 128K
Tool callingReasoningImage inputJSON
$18.90out $150.0011fresh
gpt-5.1-codex-maxgpt-5.1-codex-max · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$1.10out $9.0013fresh
gpt-5.1-codexgpt-5.1-codex · gpt-codex400KOutput 128K
Tool callingReasoningImage inputJSON
$1.07out $8.5018fresh
GPT-4.1 minigpt-4.1-mini · gpt-mini1.05MOutput 1.05M
Tool callingImage inputJSON
$0.36out $1.4024fresh
GPT-5.4 nanogpt-5.4-nano · gpt-nano1.05MOutput 128K
Tool callingReasoningImage inputJSON
$0.18out $1.1026fresh
Qwen3.6 Plusqwen3.6-plus · qwen1MOutput 500K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0022fresh
MiniMax-M2.7-highspeedminimax-m2.7-highspeed · minimax200KOutput 128K
Tool callingReasoningJSONOpen weights
$0.00out $0.0013fresh
MiniMax-M2.7minimax-m2.7 · minimax256KOutput 192K
Tool callingReasoningJSONOpen weights
$0.00out $0.0035fresh
Nemotron 3 Nano 30B A3Bnemotron-3-nano-30b-a3b · nemotron256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.008fresh
Nemotron-nano 12b v2-vlnemotron-nano-12b-v2-vl · nemotron128KOutput 128K
Tool callingReasoningImage inputOpen weights
$0.00out $0.003fresh
Nemotron 3 Super 120B A12Bnemotron-3-super-120b-a12b · nemotron1MOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0010fresh
Nemotron 3 Ultra 550B A55Bnemotron-3-ultra-550b-a55b · nemotron1MOutput 500K
Tool callingReasoningJSONOpen weights
$0.00out $0.008fresh
Muse Glimmer 30Bmuse-glimmer-30b · muse128KOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.008fresh
Step 3.7 Flashstep-3.7-flash256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0013fresh
Inklinginkling · ling1.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0018fresh
MiniMax-M3minimax-m3 · minimax1.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0036fresh
Qwen3.6 27Bqwen3.6-27b · qwen256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0024fresh
Qwen3-Coder-Plusqwen3-coder-plus · qwen1.05MOutput 250K
Tool callingJSONOpen weights
$0.00out $0.0015fresh
GLM-5V-Turboglm-5v-turbo · glm198KOutput 198K
Tool callingReasoningImage inputJSON
$0.00out $0.0015fresh
Gemini 3.5 Flash Litegemini-3.5-flash-lite · gemini-flash-lite1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.30out $2.5017fresh
Qwen3 Coder Nextqwen3-coder-next · qwen256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0015fresh
Claude Sonnet 5claude-sonnet-5 · claude-sonnet1MOutput 1M
Tool callingReasoningImage inputJSON
$0.00out $0.0028fresh
nova-2-litenova-2-lite1MOutput 1M
Tool callingReasoningImage inputJSON
$0.30out $2.502fresh
Gemini 3.5 Flashgemini-3.5-flash · gemini-flash1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.19out $1.1125fresh
GLM-5-Turboglm-5-turbo · glm198KOutput 198K
Tool callingReasoningJSON
$0.00out $0.0016fresh
Gemini 3.1 Flash Litegemini-3.1-flash-lite · gemini-flash-lite1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.25out $1.5019fresh
Gemini 3.6 Flashgemini-3.6-flash · gemini-flash1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.75out $3.7518fresh
mistral-medium-3.5mistral-medium-3.5256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$1.50out $5.574fresh
Claude Opus 5claude-opus-5 · claude-opus1MOutput 1M
Tool callingReasoningImage inputJSON
$5.00out $25.0023fresh
Gemini 3.7 Flashgemini-3.7-flash · gemini-flash1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.38out $1.8816fresh
Qwen3.8 2.4T A95Bqwen3.8-2.4t-a95b · qwen1.05MOutput 256K
Tool callingReasoningJSONOpen weights
$2.00out $6.007fresh
Qwen3.7 Maxqwen3.7-max · qwen1MOutput 500K
Tool callingReasoningJSON
$0.00out $0.0027fresh
Perplexity Simplesonar · sonar130KOutput 128K
Tool callingImage input
$0.25out $1.0010fresh
Qwen3.5 Flashqwen3.5-flash · qwen1.02MOutput 1.02M
Tool callingReasoningImage inputJSON
$0.029out $0.296fresh
Mercury Coder Smallmercury-coder-small · mercury32KOutput 16K
Tool calling
$0.25out $1.002fresh
Mercury 2mercury-2 · mercury128KOutput 128K
Tool callingReasoningJSON
$0.25out $0.756fresh
Qwen3.8 Maxqwen3.8-max · qwen1MOutput 1M
Tool callingReasoningImage inputJSON
$0.00out $0.0019fresh
Qwen3.7 Plusqwen3.7-plus · qwen1MOutput 128K
Tool callingReasoningImage inputJSON
$0.00out $0.0023fresh
Qwen3.7 Flashqwen3.7-flash · qwen1MOutput 1M
Tool callingReasoningImage inputJSON
$0.030out $0.128fresh
Perplexity Reasoning Prosonar-reasoning-pro · sonar-reasoning128KOutput 128K
ReasoningImage input
$2.00out $8.009fresh
Perplexity Prosonar-pro · sonar-pro200KOutput 128K
Tool callingImage input
$3.00out $15.0010fresh
Hy3hy3 · Hy256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0012fresh
GLM-4.5Vglm-4.5v · glm128KOutput 96K
Tool callingReasoningImage inputJSONOpen weights
$0.29out $0.8612fresh
Trinity Large Thinkingarcee-ai/trinity-large-thinking · trinity256KOutput 256K
Tool callingReasoningJSONOpen weights
$0.22out $0.854fresh
Muse Spark 1.2muse-spark-1.2 · muse1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$1.25out $4.259fresh
Muse Spark 1.1muse-spark-1.1 · muse1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$1.25out $4.259fresh
Muse Spark 1.2 Contributormuse-spark-1.2-contributor · muse1.05MOutput 1.05M
Tool callingReasoningImage inputJSON
$0.10out $0.204fresh
Laguna S 2.1laguna-s-2.1 · laguna1.05MOutput 128K
Tool callingReasoningOpen weights
$0.00out $0.006fresh
Grok 4.6grok-4.6 · grok500KOutput 500K
Tool callingReasoningImage inputJSON
$1.50out $4.5012fresh
Grok 4.5grok-4.5 · grok1MOutput 1M
Tool callingReasoningImage inputJSON
$2.00out $6.0018fresh
Grok Build 0.1grok-build-0.1 · grok-build256KOutput 256K
Tool callingReasoningImage inputJSON
$1.00out $2.0013fresh
Kimi K2.7 Code HighSpeedkimi-k2.7-code-highspeed · kimi-k2256KOutput 256K
Tool callingReasoningImage inputJSONOpen weights
$1.90out $8.009fresh
Claude Opus 4.8claude-opus-4.8 · claude-opus1.05MOutput 128K
Tool callingReasoningImage inputJSON
$4.00out $20.0011fresh
Claude Fable 5claude-fable-5 · claude-fable1MOutput 128K
Tool callingReasoningImage inputJSON
$0.00out $0.0029fresh
OpenAI o3 Deep Researchopenai/o3-deep-research · o200KOutput 100K
Tool callingReasoningImage input
$9.00out $36.003fresh
o1o1 · o200KOutput 100K
Tool callingReasoningImage inputJSON
$14.00out $54.0014fresh
o3o3200KOutput 128K
Tool callingReasoningImage inputJSON
$1.80out $7.2018fresh
o4-minio4-mini · o-mini200KOutput 100K
Tool callingReasoningImage inputJSON
$0.99out $4.0019fresh
o3-minio3-mini · o200KOutput 128K
Tool callingReasoningImage inputJSON
$0.99out $4.0018fresh
GPT-4o Mini Search Previewgpt-4o-mini-search-preview · gpt128KOutput 16K
Image input
$0.15out $0.603fresh
GPT OSS Safeguard 20Bopenai/gpt-oss-safeguard-20b · gpt-oss128KOutput 64K
Tool callingReasoningJSONOpen weights
$0.075out $0.305fresh
Qwen3 VL 235B A22B Instructqwen3-vl-235b-a22b-instruct · qwen256KOutput 256K
Tool callingImage inputJSONOpen weights
$0.20out $0.8810fresh
Qwen3 Coder 480B A35B Instruct Turboqwen3-coder · qwen256KOutput 65K
Tool callingReasoningImage inputJSONOpen weights
$0.13out $0.507fresh
MiMo-V2.5mimo-v2.5 · mimo1.05MOutput 128K
Tool callingReasoningImage inputJSONOpen weights
$0.00out $0.0019fresh
MiMo-V2.5-Promimo-v2.5-pro · mimo1.05MOutput 256K
Tool callingReasoningJSONOpen weights
$0.00out $0.0022fresh
Fugu Ultrafugu-ultra · fugu1MOutput 1M
Tool callingReasoningImage inputJSON
$5.00out $30.009fresh
GLM-4.6Vglm-4.6v · glm200KOutput 64K
Tool callingReasoningImage inputJSONOpen weights
$0.14out $0.4213fresh
Inkling Smallthinkingmachines/inkling-small · ling1.05MOutput 1.05M
Tool callingReasoningImage inputJSONOpen weights
$0.45out $1.208fresh
InclusionAI Ling 3.0 Flashling-3.0-flash · ling256KOutput 256K
Tool callingReasoningOpen weights
$0.021out $0.0635fresh
Llama 4 Maverickllama-4-maverick · llama1.05MOutput 64K
Tool callingImage inputJSONOpen weights
$0.00out $0.007fresh
Meta Llama 4 Scout 17B 16Ellama-4-scout · llama1.31MOutput 64K
Tool callingImage inputJSONOpen weights
$0.00out $0.005fresh
KAT Coder Pro V2.5kwaipilot/kat-coder-pro-v2.5 · kat-coder256KOutput 80K
Tool callingReasoningImage inputJSON
$0.74out $2.964fresh
KAT Coder Air V2.5kwaipilot/kat-coder-air-v2.5 · kat-coder256KOutput 80K
Tool callingReasoningImage inputJSON
$0.15out $0.604fresh
KAT Coder Pro V2kwaipilot/kat-coder-pro-v2 · kat-coder256KOutput 256K
Tool callingReasoningJSON
$0.30out $1.204fresh
Nano Banana Progemini-3-pro-image · gemini-pro128KOutput 64K
Tool callingReasoningImage inputJSON
$2.00out $12.008fresh
Gemini Embedding 001gemini-embedding-001 · gemini8KOutput 4K
$0.15out $0.004fresh
Nano Banana 2gemini-3.1-flash-image · gemini-flash1.05MOutput 64K
ReasoningImage inputJSON
$0.50out $3.008fresh
Nano Banana 2 Litegemini-3.1-flash-lite-image · gemini-flash-lite64KOutput 66K
Tool callingReasoningImage inputJSON
$0.25out $1.505fresh
Gemini Omni Flash Previewgemini-omni-flash-preview · gemini1MOutput 64K
ReasoningImage input
$1.50out $9.002fresh
Gemini Embedding 2gemini-embedding-2 · gemini8KOutput 1
Image input
$0.20out $0.002fresh
Nano Banana 2gemini-3.1-flash-image-preview · gemini-flash1.05MOutput 64K
ReasoningImage inputJSON
$0.50out $3.008fresh
Qwen3-Embedding-8Bqwen3-embedding-8b · qwen40KOutput 32K
Open weights
$0.00out $0.007fresh
Qwen3-Embedding 4Bqwen3-embedding-4b · qwen32KOutput 32K
Open weights
$0.010out $0.004fresh
Claude 3 Haikuanthropic/claude-3-haiku · claude200KOutput 4K
Tool callingImage input
$0.25out $1.253fresh
Claude Opus 4.8anthropic/claude-opus-4.8-fast · claude-opus1MOutput 128K
Tool callingReasoningImage inputJSON
$10.00out $50.003fresh
Claude Opus 5 Fastclaude-opus-5-fast · claude-opus1MOutput 128K
Tool callingReasoningImage inputJSON
$10.00out $50.004fresh
Command Acohere/command-a · command-a256KOutput 8K
Tool callingJSONOpen weights
$2.50out $10.003fresh
o3-proo3-pro · o-pro200KOutput 100K
Tool callingReasoningImage inputJSON
$18.00out $40.009fresh
Mistral Nemomistral-nemo · mistral-nemo128KOutput 128K
Tool callingImage inputJSONOpen weights
$0.019out $0.0306fresh
Morph v3 Largemorph-v3-large · morph256KOutput 128K
JSON
$0.90out $1.904fresh
Morph v3 Fastmorph-v3-fast · morph80KOutput 38K
$0.80out $1.204fresh
GPT-Image-2gpt-image-2 · gpt-image272KOutput 16K
Image input
$0.00out $0.006fresh
GLM-4.7-FlashXglm-4.7-flashx · glm-flash200KOutput 128K
Tool callingReasoningOpen weights
$0.060out $0.408fresh
gpt-image-1.5gpt-image-1.5 · gpt-image128K
Image input
$5.00out $32.004fresh
gpt-image-1-minigpt-image-1-mini · gpt-image0
Tool callingImage input
$2.00out $8.003fresh
text-embedding-ada-002text-embedding-ada-002 · text-embedding8KOutput 2K
$0.10out $0.004fresh
gpt-image-1gpt-image-1 · gpt-image128K
Tool callingImage input
$5.00out $40.004fresh
GPT-Realtime-2.1gpt-realtime-2.1 · gpt128KOutput 32K
Tool callingReasoningImage input
$4.00out $24.002fresh
text-embedding-3-smalltext-embedding-3-small · text-embedding8KOutput 2K
$0.020out $0.005fresh
text-embedding-3-largetext-embedding-3-large · text-embedding8KOutput 3K
$0.090out $0.005fresh
Grok Imagine Videogrok-imagine-video · grok1K
Image input
Unavailableper 1M tokens2fresh
Grok Imagine Video 1.5grok-imagine-video-1.5 · grok1K
Image input
Unavailableper 1M tokens2fresh
Grok Imagine Image 2.0grok-imagine-image-2.0 · grok8K
Image input
Unavailableper 1M tokens2fresh
Grok Imagine Imagegrok-imagine-image · grok8K
Image input
Unavailableper 1M tokens2fresh
Qwen3 Embedding 0.6Bqwen3-embedding-0.6b · text-embedding40KOutput 32K
Open weights
$0.010out $0.003fresh
Nemotron Nano 9Bnvidia/nemotron-nano-9b-v2 · nemotron128KOutput 128K
Tool callingReasoningOpen weights
$0.060out $0.232fresh
GPT Realtime 1.5openai/gpt-realtime-1.5 · gpt32KOutput 4K
Tool callingImage input
$4.00out $16.002fresh
MiniMax M2.1 Lightningminimax-m2.1-lightning · minimax200KOutput 128K
Tool callingReasoningOpen weights
$0.12out $0.483fresh
Qwen3 235B A22B Thinkingqwen3-235b-a22b-thinking · qwen256KOutput 80K
Tool callingReasoningImage input
$0.30out $2.902fresh
Mistral Small 3.2mistral-small · mistral-small128KOutput 16K
Tool callingImage inputOpen weights
$0.075out $0.202fresh
Gemini 3 Flash Previewgemini-3-flash · gemini-flash1.05MOutput 64K
Tool callingReasoningImage inputJSON
$0.40out $2.405fresh
Ministral 3Bministral-3b · ministral128KOutput 128K
Tool callingOpen weights
$0.040out $0.0403fresh
DeepSeek-V3.2-Thinkingdeepseek-v3.2-thinking128KOutput 128K
Tool callingReasoning
$0.29out $0.432fresh
Laguna S 2.1 Freelaguna-s-2.1-free · laguna256KOutput 32K
Tool callingReasoningOpen weights
$0.00out $0.002fresh
Grok-4.1-Fast-Reasoningxai/grok-4.1-fast-reasoning · grok2MOutput 1M
Tool callingReasoningImage input
$0.20out $0.502fresh
Grok-4.1-Fast-Non-Reasoningxai/grok-4.1-fast-non-reasoning · grok2MOutput 1M
Tool callingImage input
$0.20out $0.502fresh
Grok-4.20-Multi-Agentxai/grok-4.20-multi-agent2MOutput 2M
Tool callingReasoningImage input
$1.25out $2.502fresh
Magistral Smallmagistral-small · magistral-small128KOutput 128K
Tool callingReasoningOpen weights
$0.50out $1.502fresh
Pixtral 12Bpixtral-12b · pixtral128KOutput 128K
Tool callingImage inputOpen weights
$0.15out $0.152fresh
Mistral Embedmistral-embed · mistral-embed8KOutput 3K
$0.10out $0.002fresh
S1fish-audio/s1 · o0
Unavailableper 1M tokens1fresh
Transcribe-1fish-audio/transcribe-1 · o0
Unavailableper 1M tokens1fresh
S2 Profish-audio/s2-pro · o0
Unavailableper 1M tokens1fresh
S2.1 Profish-audio/s2.1-pro · o0
Unavailableper 1M tokens1fresh
Kling v3.0 Text-to-Videoklingai/kling-v3.0-t2v · ling0
Unavailableper 1M tokens1fresh
Kling v2.6 Text-to-Videoklingai/kling-v2.6-t2v · ling0
Unavailableper 1M tokens1fresh
Kling v2.6 Motion Controlklingai/kling-v2.6-motion-control · ling0
Unavailableper 1M tokens1fresh
Kling v2.5 Turbo Text-to-Videoklingai/kling-v2.5-turbo-t2v · ling0
Unavailableper 1M tokens1fresh
Kling v3.0 Image-to-Videoklingai/kling-v3.0-i2v · ling0
Unavailableper 1M tokens1fresh
Kling v3.0 Motion Controlklingai/kling-v3.0-motion-control · ling0
Unavailableper 1M tokens1fresh
Kling v2.6 Image-to-Videoklingai/kling-v2.6-i2v · ling0
Unavailableper 1M tokens1fresh
Kling v2.5 Turbo Image-to-Videoklingai/kling-v2.5-turbo-i2v · ling0
Unavailableper 1M tokens1fresh
Trinity Miniarcee-ai/trinity-mini · trinity128KOutput 128K
Open weights
$0.045out $0.151fresh
Veo 3.0 Fast Generategoogle/veo-3.0-fast-generate-001 · veo0
Unavailableper 1M tokens1fresh
Imagen 4 Ultragoogle/imagen-4.0-ultra-generate-001 · imagen480
Unavailableper 1M tokens1fresh
Text Embedding 005google/text-embedding-005 · text-embedding8KOutput 2K
Unavailableper 1M tokens1fresh
Imagen 4google/imagen-4.0-generate-001 · imagen480
Unavailableper 1M tokens1fresh
Imagen 4 Fastgoogle/imagen-4.0-fast-generate-001 · imagen480
Unavailableper 1M tokens1fresh
Text Multilingual Embedding 002google/text-multilingual-embedding-002 · text-embedding8KOutput 2K
Unavailableper 1M tokens1fresh
Veo 3.0google/veo-3.0-generate-001 · veo0
Unavailableper 1M tokens1fresh
Veo 3.1google/veo-3.1-generate-001 · veo0
Unavailableper 1M tokens1fresh
Veo 3.1 Lite Generategoogle/veo-3.1-lite-generate-001 · veo0
Unavailableper 1M tokens1fresh
Veo 3.1 Fast Generategoogle/veo-3.1-fast-generate-001 · veo0
Unavailableper 1M tokens1fresh
Llama 3.1 8B Instructmeta/llama-3.1-8b · llama128KOutput 8K
Tool calling
$0.22out $0.221fresh
Llama 3.1 70B Instructmeta/llama-3.1-70b · llama128KOutput 8K
Tool calling
$0.72out $0.721fresh
Llama 3.3 70Bllama-3.3-70b · llama128KOutput 4K
Tool callingOpen weights
$0.00out $0.002fresh
FLUX.1 Kontext Probfl/flux-kontext-pro · flux512
Unavailableper 1M tokens1fresh
FLUX.2 [klein] 4Bbfl/flux-2-klein-4b · flux0
Unavailableper 1M tokens1fresh
FLUX1.1 [pro] Ultrabfl/flux-pro-1.1-ultra · flux512
Unavailableper 1M tokens1fresh
FLUX.2 [max]bfl/flux-2-max · flux66KOutput 66K
Unavailableper 1M tokens1fresh
Flux 3bfl/flux-3-video · flux0
Unavailableper 1M tokens1fresh
FLUX1.1 [pro]bfl/flux-pro-1.1 · flux512
Unavailableper 1M tokens1fresh
FLUX.1 Fill [pro]bfl/flux-pro-1.0-fill · flux512
Unavailableper 1M tokens1fresh
FLUX.2 [klein] 9Bbfl/flux-2-klein-9b · flux0
Unavailableper 1M tokens1fresh
FLUX.1 Kontext Maxbfl/flux-kontext-max · flux512
Unavailableper 1M tokens1fresh
FLUX.2 [pro]bfl/flux-2-pro · flux66KOutput 66K
Unavailableper 1M tokens1fresh
FLUX.2 [flex]bfl/flux-2-flex · flux0
Unavailableper 1M tokens1fresh
voyage-4-litevoyage/voyage-4-lite · voyage32K
Unavailableper 1M tokens1fresh
Voyage Rerank 2.5voyage/rerank-2.5 · voyage32KOutput 32K
Unavailableper 1M tokens1fresh
voyage-4voyage/voyage-4 · voyage32K
Unavailableper 1M tokens1fresh
voyage-law-2voyage/voyage-law-2 · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-code-2voyage/voyage-code-2 · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-3-largevoyage/voyage-3-large · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-3.5voyage/voyage-3.5 · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-finance-2voyage/voyage-finance-2 · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-3.5-litevoyage/voyage-3.5-lite · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-code-3voyage/voyage-code-3 · voyage8KOutput 2K
Unavailableper 1M tokens1fresh
voyage-4-largevoyage/voyage-4-large · voyage32K
Unavailableper 1M tokens1fresh
Voyage Rerank 2.5 Litevoyage/rerank-2.5-lite · voyage32KOutput 32K
Unavailableper 1M tokens1fresh
Embed v4.0cohere/embed-v4.0 · cohere-embed128KOutput 2K
Unavailableper 1M tokens1fresh
Cohere Rerank 3.5cohere/rerank-v3.5 · o4KOutput 4K
Unavailableper 1M tokens1fresh
Cohere Rerank 4 Procohere/rerank-v4-pro · o32KOutput 32K
Unavailableper 1M tokens1fresh
Cohere Rerank 4 Fastcohere/rerank-v4-fast · o32KOutput 32K
Unavailableper 1M tokens1fresh
GLM-4.6V-Flashzai/glm-4.6v-flash · glm128KOutput 24K
Tool callingReasoningImage input
Unavailableper 1M tokens1fresh
Seedream 5.0 Probytedance/seedream-5.0-pro · seed0
Unavailableper 1M tokens1fresh
Seed 1.8bytedance/seed-1.8 · seed256KOutput 64K
Tool callingReasoningImage input
$0.25out $2.001fresh
Seedance 2.5bytedance/seedance-2.5 · seed0
Unavailableper 1M tokens1fresh
Seedance v1.0 Probytedance/seedance-v1.0-pro · seed0
Unavailableper 1M tokens1fresh
Seedance 2.0bytedance/seedance-2.0 · seed0
Image input
Unavailableper 1M tokens1fresh
Seedream 4.0bytedance/seedream-4.0 · seed0
Unavailableper 1M tokens1fresh
Seedance v1.0 Pro Fastbytedance/seedance-v1.0-pro-fast · seed0
Unavailableper 1M tokens1fresh
Seedream 5.0 Litebytedance/seedream-5.0-lite · seed0
Unavailableper 1M tokens1fresh
Seedream 4.5bytedance/seedream-4.5 · seed0
Unavailableper 1M tokens1fresh
Seed 1.6bytedance/seed-1.6 · seed256KOutput 32K
Tool callingReasoningImage input
$0.25out $2.001fresh
Seedance v1.5 Probytedance/seedance-v1.5-pro · seed0
Unavailableper 1M tokens1fresh
Seedance 2.0 Fastbytedance/seedance-2.0-fast · seed0
Image input
Unavailableper 1M tokens1fresh
GPT 5.1 Thinkingopenai/gpt-5.1-thinking · gpt400KOutput 128K
Tool callingReasoningImage input
$1.25out $10.001fresh
GPT-4o Mini Transcribegpt-4o-mini-transcribe · gpt16KOutput 16K
Tool calling
$1.25out $5.002fresh
GPT-4o Transcribegpt-4o-transcribe · gpt16KOutput 16K
Tool calling
$2.50out $10.002fresh
TTS-1 HDopenai/tts-1-hd · o0
Unavailableper 1M tokens1fresh
TTS-1openai/tts-1 · o0
Unavailableper 1M tokens1fresh
GPT-Realtime miniopenai/gpt-realtime-mini · gpt0
$0.60out $2.401fresh
gpt-realtime-whisperopenai/gpt-realtime-whisper · whisper0
Unavailableper 1M tokens1fresh
Whisperopenai/whisper-1 · whisper0
Unavailableper 1M tokens1fresh
gpt-realtime-2openai/gpt-realtime-2 · gpt0
$4.00out $24.001fresh
Grok 4.20 Reasoningxai/grok-4.20-reasoning · grok2MOutput 2M
Tool callingReasoningImage input
$1.25out $2.501fresh
Grok 4.20 Multi Agent Betaxai/grok-4.20-multi-agent-beta · grok2MOutput 2M
Tool callingReasoningImage input
$1.25out $2.501fresh
Grok 4.20 Beta Reasoningxai/grok-4.20-reasoning-beta · grok2MOutput 2M
Tool callingReasoningImage input
$1.25out $2.501fresh
Grok 4.20 Beta Non-Reasoningxai/grok-4.20-non-reasoning-beta · grok2MOutput 2M
Tool callingImage input
$1.25out $2.501fresh
Grok TTSxai/grok-tts · grok0
Unavailableper 1M tokens1fresh
Grok Voice Think Fast 1.0xai/grok-voice-think-fast-1.0 · grok0
Unavailableper 1M tokens1fresh
Grok Imagine Video 1.5 Previewxai/grok-imagine-video-1.5-preview · grok0
Unavailableper 1M tokens1fresh
Grok 4.20 Non-Reasoningxai/grok-4.20-non-reasoning · grok2MOutput 2M
Tool callingImage input
$1.25out $2.501fresh
Grok STTxai/grok-stt · grok0
Unavailableper 1M tokens1fresh
Grok Voice Think Fast 2.0xai/grok-voice-think-fast-2.0 · grok0
Unavailableper 1M tokens1fresh
Arrow 1.1quiverai/arrow-1.1 · o128KOutput 128K
Unavailableper 1M tokens1fresh
Qwen3 235B A22B Instruct 2507alibaba/qwen-3-235b · qwen256KOutput 16K
Tool callingReasoning
$0.22out $0.881fresh
Qwen 3.6 Max Previewalibaba/qwen-3.6-max-preview · qwen240KOutput 64K
Tool callingReasoningOpen weights
$1.30out $7.801fresh
Wan v2.5 Text-to-Video Previewalibaba/wan-v2.5-t2v-preview · o0
Unavailableper 1M tokens1fresh
Qwen3 VL Instructalibaba/qwen3-vl-instruct · qwen128KOutput 126K
Tool callingImage inputOpen weights
$0.40out $1.601fresh
Qwen3-14Balibaba/qwen-3-14b · qwen40KOutput 16K
Tool callingReasoning
$0.12out $0.241fresh
Wan v2.7 Reference-to-Videoalibaba/wan-v2.7-r2v · o0
Unavailableper 1M tokens1fresh
Qwen 3.32Balibaba/qwen-3-32b · qwen128KOutput 8K
Tool callingReasoning
$0.16out $0.641fresh
Wan v2.7 Text-to-Videoalibaba/wan-v2.7-t2v · o0
Unavailableper 1M tokens1fresh
Qwen3-30B-A3Balibaba/qwen-3-30b · qwen40KOutput 16K
Tool callingReasoning
$0.12out $0.501fresh
Qwen 3 Coder 30B A3B Instructalibaba/qwen3-coder-30b-a3b · qwen256KOutput 8K
Tool callingReasoning
$0.15out $0.601fresh
Wan v2.6 Image-to-Video Flashalibaba/wan-v2.6-i2v-flash · o0
Unavailableper 1M tokens1fresh
Wan v2.6 Reference-to-Video Flashalibaba/wan-v2.6-r2v-flash · o0
Unavailableper 1M tokens1fresh
Qwen 3 Max Thinkingalibaba/qwen3-max-thinking · qwen256KOutput 64K
Tool callingReasoningOpen weights
$1.20out $6.001fresh
Qwen3 VL Thinkingalibaba/qwen3-vl-thinking · qwen128KOutput 32K
Tool callingReasoningImage inputOpen weights
$0.40out $4.001fresh
Wan v2.6 Reference-to-Videoalibaba/wan-v2.6-r2v · o0
Unavailableper 1M tokens1fresh
Wan v2.6 Text-to-Videoalibaba/wan-v2.6-t2v · o0
Unavailableper 1M tokens1fresh
Wan v2.6 Image-to-Videoalibaba/wan-v2.6-i2v · o0
Unavailableper 1M tokens1fresh
Sakana Namazusakana/namazu256KOutput 256K
Tool callingReasoningImage input
$0.95out $4.001fresh
Embed v1 4bperplexity/pplx-embed-v1-4b32K
Unavailableper 1M tokens1fresh
Embed v1 0.6bperplexity/pplx-embed-v1-0.6b · v032K
Unavailableper 1M tokens1fresh
Recraft V4.1recraft/recraft-v4.1 · recraft0
Unavailableper 1M tokens1fresh
Recraft V4.1 Utility Prorecraft/recraft-v4.1-utility-pro · recraft0
Unavailableper 1M tokens1fresh
Recraft V2recraft/recraft-v2 · recraft512
Unavailableper 1M tokens1fresh
Recraft V4.1 Prorecraft/recraft-v4.1-pro · recraft0
Unavailableper 1M tokens1fresh
Recraft V4.1 Utilityrecraft/recraft-v4.1-utility · recraft0
Unavailableper 1M tokens1fresh
Recraft V3recraft/recraft-v3 · recraft512
Unavailableper 1M tokens1fresh
Recraft V4recraft/recraft-v4 · recraft0
Unavailableper 1M tokens1fresh
Recraft V4 Prorecraft/recraft-v4-pro · recraft0
Unavailableper 1M tokens1fresh
Devstral Small 2mistral/devstral-small-2 · devstral256KOutput 256K
Tool callingImage input
$0.10out $0.301fresh
Mistral Medium 3.1mistral/mistral-medium · mistral-medium128KOutput 64K
Tool callingImage input
$0.40out $2.001fresh
Mistral Large 3mistral-large-3 · mistral-large256KOutput 256K
Tool callingImage inputOpen weights
$0.50out $1.502fresh
Ministral 14Bmistral/ministral-14b · ministral256KOutput 256K
Image input
$0.20out $0.201fresh
Devstral 2devstral-2 · devstral256KOutput 256K
Tool callingOpen weights
$0.40out $2.002fresh
Codestral Embedmistral/codestral-embed · codestral-embed8KOutput 2K
Unavailableper 1M tokens1fresh
Codestralmistral/codestral · codestral256KOutput 4K
Tool callingOpen weights
$0.30out $0.901fresh
Magistral Mediummistral/magistral-medium · magistral-medium128KOutput 16K
Tool callingReasoningOpen weights
$2.00out $5.001fresh
Ministral 8Bmistral/ministral-8b · ministral128KOutput 128K
Tool callingOpen weights
$0.10out $0.101fresh
Titan Text Embeddings V2amazon/titan-embed-text-v2 · titan-embed8KOutput 2K
Unavailableper 1M tokens1fresh
Nova Liteamazon/nova-lite · nova-lite300KOutput 8K
Tool callingImage input
$0.060out $0.241fresh
Nova Proamazon/nova-pro · nova-pro300KOutput 8K
Tool callingImage input
$0.80out $3.201fresh
Nova Microamazon/nova-micro · nova-micro128KOutput 8K
Tool calling
$0.035out $0.141fresh
Flux Schnellprodia/flux-fast-schnell · flux512
Unavailableper 1M tokens1fresh
Interfaze Betainterfaze/interfaze-beta1MOutput 32K
ReasoningImage input
$1.50out $3.501fresh
KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1 · kat-coder256KOutput 32K
Reasoning
$0.30out $1.201fresh
MiniMax H3minimax/minimax-h3 · minimax0
Image input
Unavailableper 1M tokens1fresh

Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.