Models
114 models are available in BotConnector Cloud right now; 4 are free with a Starter account. Use them in the web app, in BCCLI, or by their id in the API.
| Model | Context | First token | Access | Price |
|---|---|---|---|---|
| OpenAI | ||||
GPT-6 Lunagpt-6-lunaTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.09 / $0.45input / output per 1M tokensCurrent promotional rate |
GPT-6 Solgpt-6-solTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $2 / $10input / output per 1M tokens |
GPT-5.6 Terragpt-5.6-terraTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $2 / $12input / output per 1M tokens |
GPT-5.6 Solgpt-5.6-solTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $4 / $20input / output per 1M tokens |
GPT Image 2.5 Flaregpt-image-2.5-flareImage Generation | — | — | Pay as you go | Based on actual usagedepends on usage and quality |
GPT Image 2.5 Sunburstgpt-image-2.5-sunburstImage Generation | — | — | Pay as you go | Based on actual usagedepends on usage and quality |
GPT-OSS 120Bgpt-oss-120bTools · Reasoning · Coding | 131K | 4.2 s | Free | $0.037 / $0.17input / output per 1M tokens |
GPT-OSS 20Bgpt-oss-20bTools · Reasoning · Coding | 131K | 7.9 s | Included in Plus+ | $0.03 / $0.14input / output per 1M tokens |
GPT-OSS Safeguard 120Bgpt-oss-safeguard-120bReasoning · Tools | 131K | — | Pay as you go | $0.15 / $0.6input / output per 1M tokens |
GPT-OSS Safeguard 20Bgpt-oss-safeguard-20bReasoning · Tools | 131K | — | Pay as you go | $0.07 / $0.3input / output per 1M tokens |
| Anthropic | ||||
Claude Haiku 5.5claude-haiku-5-5Tools · Vision · Reasoning · Coding | 1M | — | Pay as you go | $0.1–$0.5 / $0.5–$2.5input / output per 1M tokens · 2 context tiers |
Claude Opus 5.5claude-opus-5-5Tools · Vision · Reasoning · Coding | 1M | — | Pay as you go | $4 / $20input / output per 1M tokens |
Claude Sonnet 5.5claude-sonnet-5-5Tools · Vision · Reasoning · Coding | 1M | — | Pay as you go | $2 / $10input / output per 1M tokens |
Gemini 3.8 Flashgemini-3.8-flashTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.6 / $3input / output per 1M tokensCurrent promotional rate |
Gemini 3.7 Flashgemini-3.7-flashTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.75 / $3.75input / output per 1M tokens |
Gemini 3.6 Flashgemini-3.6-flashTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.75 / $3.75input / output per 1M tokens |
Gemini 3.5 Flashgemini-3.5-flashTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $1.5 / $9input / output per 1M tokens |
Gemini 3.5 Flash Litegemini-3.5-flash-liteTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.3 / $2.5input / output per 1M tokens |
Gemini 2.5 Flash Litegemini-2.5-flash-liteTools · Vision · Reasoning · Coding | 1.05M | — | Available | $0.1 / $0.4input / output per 1M tokens |
Gemini 3.1 Flash Litegemini-3.1-flash-liteTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $0.25 / $1.5input / output per 1M tokens |
Gemini 3.1 Pro Previewgemini-3.1-pro-previewTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $2–$4 / $12–$18input / output per 1M tokens · 2 context tiers |
Gemini 3.1 Flash Imagegemini-3.1-flash-imageImage Generation · Vision | — | — | Pay as you go | $0.045/image · 0.5k |
Gemini 3.1 Flash Lite Imagegemini-3.1-flash-lite-imageImage Generation | — | — | Pay as you go | $0.0336/image · 1k |
Veo 3.1 Fastveo-3.1-fast-generate-previewVideo Generation | — | — | Pay as you go | $0.1/second · 720p |
Veo 3.1 Liteveo-3.1-lite-generate-previewVideo Generation | — | — | Pay as you go | $0.05/second · 720p |
Lyria 3.5lyria-3.5Music Generation | — | — | Not available yet | $0.08/request |
Gemini 2.5 Flashgemini-2.5-flashVision · Reasoning · Tools · Coding | 1.05M | — | Pay as you go | $0.3 / $2.5input / output per 1M tokens |
Gemini 2.5 Flash TTSgemini-2.5-flash-preview-ttsText to Speech | — | — | Pay as you go | $0.07/10k_characters · global |
Gemini 2.5 Progemini-2.5-proVision · Reasoning · Tools · Coding | 1.05M | — | Pay as you go | $1.25 / $10input / output per 1M tokens |
Gemini 3 Pro Imagegemini-3-pro-imageImage Generation · Vision · Reasoning | — | — | Pay as you go | $0.134/image · 1k |
Gemini 4 Argongemini-4-argonTools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $2 / $10input / output per 1M tokensCurrent provider promotion |
Gemini Flash Litegemini-flash-lite-latestVision · Reasoning · Coding | 1.05M | — | Available | Standard rate not yet verified |
Gemma 3 12B ITgemma-3-12b-itVision · Tools | 131K | — | Pay as you go | $0.08 / $0.24input / output per 1M tokens |
Gemma 3 27B ITgemma-3-27b-itVision · Tools · Coding | 131K | — | Pay as you go | $0.15 / $0.4input / output per 1M tokens |
Gemma 3 4B ITgemma-3-4b-itVision | 131K | — | Pay as you go | $0.04 / $0.1input / output per 1M tokens |
Gemma 4 26B A4Bgemma-4-26b-a4b-it-freeVision · Tools · Reasoning | 262K | — | Available | $0.13 / $0.4input / output per 1M tokens |
Gemma 4 31Bgemma-4-31b-it-freeVision · Tools · Reasoning | 262K | — | Available | $0.14 / $0.4input / output per 1M tokens |
| DeepSeek | ||||
DeepSeek V4.1 Flashdeepseek-v4.1-flashTools · Vision · Reasoning · Coding | 1.05M | 2.9 s | Pay as you go | $0.15 / $0.6input / output per 1M tokens |
DeepSeek V4 Prodeepseek-v4-proTools · Reasoning · Coding | 1.05M | — | Pay as you go | $0.66 / $1.98input / output per 1M tokens |
DeepSeek R1 (0528)deepseek-r1-0528Reasoning · Tools · Coding | 164K | — | Pay as you go | $0.55 / $2.19input / output per 1M tokens |
DeepSeek V3.1deepseek-v3.1Reasoning · Tools · Coding | 164K | — | Pay as you go | $0.55 / $1.65input / output per 1M tokens |
DeepSeek V3.2deepseek-v3.2Reasoning · Tools · Coding | 164K | — | Pay as you go | $0.56 / $1.68input / output per 1M tokens |
| Z.AI | ||||
GLM 5.3 Flashglm-5.3-flashTools · Vision · Reasoning · Coding | 1.05M | 2.9 s | Pay as you go | $0.15 / $0.5input / output per 1M tokens |
GLM 5.3glm-5.3Tools · Reasoning · Coding | — | — | Pay as you go | $1.4 / $4.4input / output per 1M tokens |
GLM 5.2glm-5.2Tools · Reasoning · Coding | 1M | — | Pay as you go | $1.4 / $4.4input / output per 1M tokens |
GLM 4.6glm-4.6Reasoning · Tools · Coding | 200K | — | Pay as you go | $0.5 / $1.8input / output per 1M tokens |
GLM 4.7glm-4.7Reasoning · Tools · Coding | 200K | — | Pay as you go | $0.6 / $2.2input / output per 1M tokens |
GLM 4.7 Flashglm-4.7-flashReasoning · Tools · Coding | 200K | — | Pay as you go | $0.1 / $0.4input / output per 1M tokens |
GLM 5glm-5Reasoning · Tools · Coding | 200K | — | Pay as you go | $1 / $3.2input / output per 1M tokens |
| Qwen | ||||
Qwen3.8 Flashqwen3.8-flashTools · Vision · Reasoning | 1M | — | Pay as you go | $0.128 / $0.376input / output per 1M tokensCurrent promotional rate |
Qwen3.5 397B A17Bqwen3.5-397b-a17bTools · Vision · Reasoning · Coding | 262K | — | Pay as you go | $0.6 / $3.6input / output per 1M tokens |
Qwen3 Coder 30B A3B Instructqwen3-coder-30b-a3b-instructTools · Coding | 262K | — | Pay as you go | $0.45–$1.2 / $2.25–$6input / output per 1M tokens · 3 context tiers |
Qwen3 Coder 480B A35Bqwen3-coder-480b-a35b-instructTools · Coding | 262K | — | Pay as you go | $1.5–$4.5 / $7.5–$22.5input / output per 1M tokens · 3 context tiers |
Qwen Imageqwen-image-text-to-imageImage Generation | — | — | Not available yet | $0.02/image |
Qwen Image Editqwen-image-editimage | — | — | Not available yet | $0.02/image |
Qwen Audio 3.0 TTS Flashqwen-audio-3.0-tts-flashText to Speech | — | — | Not available yet | $0.15/10k_characters · international |
Qwen3 TTS Flashqwen3-tts-flashText to Speech | — | — | Pay as you go | $0.1/10k_characters · international |
Qwen Image 3qwen-image-3Image Generation | — | — | Available | Standard rate not yet verified |
Qwen3 235B A22B (2507)qwen3-235b-a22b-instruct-2507Tools · Coding | 262K | — | Pay as you go | $0.22 / $0.88input / output per 1M tokens |
Qwen3 32Bqwen3-32bReasoning · Tools · Coding | 131K | — | Pay as you go | $0.2 / $0.6input / output per 1M tokens |
Qwen3 Coder Nextqwen3-coder-nextTools · Coding | 200K | — | Pay as you go | $0.5 / $2input / output per 1M tokens |
Qwen3 VL 235B A22Bqwen3-vl-235b-a22bVision · Tools · Coding | 200K | — | Pay as you go | $0.6 / $2.4input / output per 1M tokens |
Qwen3-Next 80B Instructqwen3-next-80b-a3b-instructTools · Coding | 262K | — | Pay as you go | $0.15 / $0.6input / output per 1M tokens |
Qwen3-Next 80B Thinkingqwen3-next-80b-a3b-thinkingReasoning · Tools · Coding | 262K | — | Pay as you go | $0.15 / $1.2input / output per 1M tokens |
Qwen3.8 Maxqwen3.8-maxTools · Vision · Reasoning | 262K | — | Pay as you go | $1.6 / $4.8input / output per 1M tokensCurrent promotional rate |
| Kimi | ||||
Kimi K3kimi-k3Tools · Vision · Reasoning · Coding | 1.05M | — | Pay as you go | $3 / $15input / output per 1M tokens |
Kimi K2.6kimi-k2.6Tools · Vision · Reasoning · Coding | 262K | — | Pay as you go | $0.95 / $4input / output per 1M tokens |
Kimi K2 Thinkingkimi-k2-thinkingReasoning · Tools · Coding | 256K | — | Pay as you go | $0.6 / $2.5input / output per 1M tokens |
Kimi K2.7 Codekimi-k2.7-codeTools · Vision · Reasoning · Coding | 262K | — | Pay as you go | $0.95 / $4input / output per 1M tokens |
| MiniMax | ||||
MiniMax M3minimax-m3Tools · Vision · Reasoning · Coding | 1M | — | Pay as you go | $0.3 / $1.2input / output per 1M tokens |
MiniMax Hailuo Video 01minimax-hailuo-01-t2vVideo Generation | — | — | Pay as you go | $0.058333/second · 720p |
MiniMax M2minimax-m2Reasoning · Tools · Coding | 200K | — | Pay as you go | $0.3 / $1.2input / output per 1M tokens |
MiniMax M2.1minimax-m2.1Reasoning · Tools · Coding | 200K | — | Pay as you go | $0.25 / $1input / output per 1M tokens |
MiniMax M2.5minimax-m2.5Reasoning · Tools · Coding | 200K | — | Pay as you go | $0.3 / $1.2input / output per 1M tokens |
| Solar | ||||
Solar Mini 4solar-mini4Reasoning · Coding | 524K | — | Pay as you go | $0.3 / $1.2input / output per 1M tokens |
Solar Pro 4solar-pro4Reasoning · Coding | 524K | — | Pay as you go | $0.3 / $1.2input / output per 1M tokens |
| FLUX | ||||
FLUX.2 [klein] 4Bflux-2-klein-4bImage Generation | — | — | Pay as you go | Based on actual usagedepends on usage and quality |
FLUX.1 Schnellflux-1-schnell-freeImage Generation | — | — | Available | $0.003per megapixel |
| Ming | ||||
Ming Image 0.1 Designming-image-0.1-designImage Generation | — | — | Free | Standard rate not yet verified |
Ling 3.0 Flashling-3.0-flashTools · Reasoning | 262K | — | Available | $0.06 / $0.18input / output per 1M tokens |
Ling 3.0 Flash Santeling-3.0-flash-santeTools · Reasoning · Coding | 262K | — | Available | $0.075 / $0.22input / output per 1M tokens |
| Agnes | ||||
Agnes 3.0 Flashagnes-3.0-flashTools · Vision · Reasoning · Coding | 524K | 0.9 s | Free | $0.05 / $0.15input / output per 1M tokensList rate · currently free promotion |
| Agnes AI | ||||
Agnes Image 2.1 Flashagnes-image-2.1-flashImage Generation | — | — | Available | $0.01per imageList rate · currently free promotion |
| Alibaba | ||||
Wan 3.0 Primewan-3.0-primeVideo Generation | — | — | Pay as you go | $0.1/second · 720p |
Wan 3.0 Videowan-3.0-videoVideo Generation | — | — | Pay as you go | $0.1/second · 720p |
| Apodex | ||||
Apodex 1.1 Miniapodex-1.1-miniTools · Coding | 262K | — | Available | $0 / $0input / output per 1M tokensTemporary free promotion |
| ByteDance | ||||
SDXL Lightningsdxl-lightning-freeImage Generation | — | — | Available | ≈$0.0034per imageUsage estimate; may vary |
| Dots Studio | ||||
Dots 3 Note Previewdots-3-note-preview-freeReasoning · Coding | 512K | — | Included in Plus+ | Standard rate not yet verified |
| Grok | ||||
Grok 4.20 Fastgrok-4.20-non-reasoningTools · Coding | 200K | — | Pay as you go | $1.25 / $2.5input / output per 1M tokens |
Grok 4.20 Reasoninggrok-4.20-reasoningReasoning · Tools · Coding | 200K | — | Pay as you go | $1.25 / $2.5input / output per 1M tokens |
| Inception | ||||
Mercury 2.5mercury-2.5Tools · Reasoning · Coding | 260K | — | Pay as you go | $0.04 / $0.15input / output per 1M tokensCurrent provider promotion |
| Kokoro | ||||
Kokoro 82M TTSkokoro-82m-ttsText to Speech | — | — | Pay as you go | $0.01/10k_characters · standard |
| Krea | ||||
Krea 2 Medium Turbokrea-2-medium-turboImage Generation | — | — | Available | Standard rate not yet verified |
| LiquidAI | ||||
LFM 2.5 2.6Blfm-2.5-2.6b-freeCoding | 66K | 0.9 s | Included in Plus+ | Standard rate not yet verified |
| Meta | ||||
Meta Muse Imagemeta-muse-imageImage Generation | — | — | Available | $0.01per image |
| Mistral | ||||
Devstral 2 (123B)devstral-2-123bTools · Coding | 131K | — | Pay as you go | $0.4 / $1.2input / output per 1M tokens |
Magistral Small (2509)magistral-small-2509Reasoning · Tools · Coding | 131K | — | Pay as you go | $0.5 / $1.5input / output per 1M tokens |
Ministral 3 14Bministral-3-14b-instructTools · Coding | 131K | — | Pay as you go | $0.2 / $0.6input / output per 1M tokens |
Ministral 3 3Bministral-3-3b-instructTools | 131K | — | Pay as you go | $0.04 / $0.12input / output per 1M tokens |
Ministral 3 8Bministral-3-8b-instructTools · Coding | 131K | — | Pay as you go | $0.1 / $0.3input / output per 1M tokens |
Mistral Large 3 (675B)mistral-large-3Tools · Coding | 131K | — | Pay as you go | $2 / $6input / output per 1M tokens |
Voxtral Mini 3Bvoxtral-mini-3b-2507Tools | 131K | — | Pay as you go | $0.04 / $0.12input / output per 1M tokens |
Voxtral Small 24Bvoxtral-small-24b-2507Tools | 131K | — | Pay as you go | $0.2 / $0.6input / output per 1M tokens |
| NVIDIA | ||||
Nemotron 3 Nano Omninemotron-3-nano-omni-freeReasoning · Tools · Coding | 256K | — | Included in Plus+ | Standard rate not yet verified |
Nemotron 3 Super (120B)nemotron-3-super-120bTools · Reasoning · Coding | 262K | — | Available | Standard rate not yet verified |
Nemotron 3 Super 120Bnemotron-super-3-120bReasoning · Tools · Coding | 131K | — | Pay as you go | $0.4 / $1.2input / output per 1M tokens |
Nemotron 3 Ultranemotron-3-ultra-freeTools · Reasoning · Coding | 1M | — | Included in Plus+ | $0.5 / $2.2input / output per 1M tokens |
Nemotron Nano 12B v2 VLnemotron-nano-12b-v2Vision · Tools | 131K | — | Pay as you go | $0.1 / $0.3input / output per 1M tokens |
Nemotron Nano 3 30Bnemotron-nano-3-30bTools · Coding | 131K | — | Pay as you go | $0.15 / $0.45input / output per 1M tokens |
Nemotron Nano 9B v2nemotron-nano-9b-v2Reasoning · Tools | 131K | — | Pay as you go | $0.08 / $0.24input / output per 1M tokens |
| Poolside | ||||
Laguna S 2.1laguna-s-2.1Coding | 262K | — | Available | $0.1 / $0.2input / output per 1M tokens |
Laguna Xs 2.1laguna-xs-2.1Tools · Coding | 66K | — | Available | Standard rate not yet verified |
| Recraft | ||||
Recraft V4.1 Flashrecraft-v4.1-flashImage Generation | — | — | Available | Standard rate not yet verified |
| Resemble AI | ||||
Chatterbox Multilingual TTSchatterbox-ttsText to Speech | — | — | Pay as you go | $0.01/10k_characters · multilingual |
| Stability AI | ||||
SDXL Base 1.0sdxl-base-1.0-freeImage Generation | — | — | Available | ≈$0.0043per imageUsage estimate; may vary |
| Writer | ||||
Writer Palmyra Vision 7Bpalmyra-vision-7bVision | 131K | — | Pay as you go | $0.15 / $0.45input / output per 1M tokens |
| Xiaomi | ||||
MiMo V2.5 TTSmimo-v2.5-tts-freeText to Speech | — | — | Free | Standard rate not yet verified |
MiMo V2.6 Flashmimo-v2.6-flashTools · Vision · Reasoning | 1.05M | 3.7 s | Pay as you go | $0.14 / $0.28input / output per 1M tokens |
One price per model: the current rate for PAYG (including promotions and tiers), and a vendor Standard API reference for free/plan models. Actual charges may depend on context, resolution or usage.
Context is the most text a model can read at once, in tokens. First token is the median time to the first word of an answer, measured on real requests over the last week; “—” means there is not enough traffic yet. Current health per model is on the status page.
Models and access routes
Models available through BotConnector are developed by their original model makers. BotConnector does not replace the maker's identity or rename those models as BotConnector models.
BotConnector may access a model through the model maker's official API or through large-scale AI infrastructure providers that serve that model. The access route can differ between models and may change according to availability, performance, and service conditions.
For open-weight models, providers may run the same model with different hardware, runtimes, precision levels, or quantization. As a result, performance or output may differ slightly even when the selected model is the same.