Real provider identity
OpenAI, Claude, Gemini, Grok, Mistral, Thinking Machines, DeepSeek, Moonshot, MiniMax, Z.ai, and Echo stay recognizable in the product. They are not blurred into one mushy “smart” setting that erases why you picked them.
Model selection
Every lab.
One surface.
Switch between OpenAI, Claude, Gemini, Grok, DeepSeek, Qwen, and more — all from the same chat interface. The model you pick stays locked to the conversation until you deliberately change it.
No hidden routing. No silent model swaps mid-thread. The selector you see is the one actually answering.
Why it feels better
Model choice should feel intentional, not decorative.
Plenty of products advertise “multiple models” and then blur the differences until the selector becomes theater. This page exists because the differences are the point.
Stable conversation routing
Once a thread starts on a model, it stays on that model until you change it. The point is to compare behavior cleanly, not to wonder whether the app quietly switched labs halfway through.
Access that tells the truth
Base, Premium, and Premium+ remain visible in the interface, so you can choose capability and cost intentionally instead of reverse-engineering it from vibes.
Defaults you set, not guesses
Set your default model in account settings and change it when your workflow or policy shifts. New chats start from what you saved there, so your baseline stays intentional instead of drifting with whatever you last tried in the picker.
Current lineup
Provider by provider, one row per model.
Every model, every provider, side by side — what it costs you and what it costs at the source. Compare before you commit.
Access
BasePremiumPremium+
| Family | Model | Access | Requests | Input (API) | Output (API) |
|---|---|---|---|---|---|
 OpenAIChatGPT families GPT-3.5 through GPT-5.x, plus audio, o-series, and GPT OSS routes. 12 families · 33 models | |||||
GPT-4o Series | GPT-4o · May 2024 gpt-4o-2024-05-13 | Premium+ | 2 premium requests | $5.00 / 1M tokens | $15.00 / 1M tokens |
GPT-4o Series | GPT-4o · Aug. 2024 gpt-4o-2024-08-06 | Premium | 1 premium request | $2.50 / 1M tokens | $10.00 / 1M tokens |
GPT-4o Series | GPT-4o · Nov. 2024 gpt-4o-2024-11-20 | Premium | 1 premium request | $2.50 / 1M tokens | $10.00 / 1M tokens |
GPT-4o Series | GPT-4o gpt-4o | Premium | 1 premium request | $2.50 / 1M tokens | $10.00 / 1M tokens |
GPT-4o Series | GPT-4o mini gpt-4o-mini | Base | 1 base request | $0.15 / 1M tokens | $0.60 / 1M tokens |
GPT-3.5 Turbo | GPT-3.5 Turbo gpt-3.5-turbo | Base | 2 base requests | $0.50 / 1M tokens | $1.50 / 1M tokens |
GPT-3.5 Turbo | GPT-3.5 Turbo · 0125 gpt-3.5-turbo-0125 | Base | 2 base requests | $0.50 / 1M tokens | $1.50 / 1M tokens |
GPT-3.5 Turbo | GPT-3.5 Turbo · 1106 gpt-3.5-turbo-1106 | Base | 2 base requests | $0.50 / 1M tokens | $1.50 / 1M tokens |
GPT Audio | GPT audio mini gpt-audio-mini | Base | 3 base requests | $0.60 / 1M tokens | $2.40 / 1M tokens |
GPT Audio | GPT audio mini · Dec. 2025 gpt-audio-mini-2025-12-15 | Base | 3 base requests | $0.60 / 1M tokens | $2.40 / 1M tokens |
GPT-5.6 Series | GPT-5.6 Sol gpt-5.6-sol | Premium+ | 5 premium requests | $5.00 / 1M tokens | $30.00 / 1M tokens |
GPT-5.6 Series | GPT-5.6 Terra gpt-5.6-terra | Premium | 2 premium requests | $2.50 / 1M tokens | $15.00 / 1M tokens |
GPT-5.6 Series | GPT-5.6 Luna gpt-5.6-luna | Premium | 1 premium request | $1.00 / 1M tokens | $6.00 / 1M tokens |
GPT-5.4 Series | GPT-5.4 gpt-5.4 | Premium+ | 2 premium requests | $2.50 / 1M tokens | $15.00 / 1M tokens |
GPT-5.4 Series | GPT-5.4 mini gpt-5.4-mini | Premium | 1 premium request | $0.75 / 1M tokens | $4.50 / 1M tokens |
GPT-5.4 Series | GPT-5.4 nano gpt-5.4-nano | Base | 2 base requests | $0.20 / 1M tokens | $1.25 / 1M tokens |
GPT-5.3 Series | GPT-5.3 latest gpt-5.3-chat-latest | Premium+ | 1 premium request | $1.75 / 1M tokens | $14.00 / 1M tokens |
GPT-5.3 Series | GPT-5.3-Codex gpt-5.3-codex | Premium+ | 1 premium request | $1.75 / 1M tokens | $14.00 / 1M tokens |
GPT-5.2 Series | GPT-5.2 latest gpt-5.2-chat-latest | Premium+ | 1 premium request | $1.75 / 1M tokens | $14.00 / 1M tokens |
GPT-5.2 Series | GPT-5.2 gpt-5.2-2025-12-11 | Premium+ | 1 premium request | $1.75 / 1M tokens | $14.00 / 1M tokens |
GPT-5.1 Series | GPT-5.1 gpt-5.1 | Premium | 1 premium request | $1.25 / 1M tokens | $10.00 / 1M tokens |
GPT-5 Series | GPT-5 gpt-5 | Premium | 1 premium request | $1.25 / 1M tokens | $10.00 / 1M tokens |
GPT-5 Series | GPT-5 mini gpt-5-mini | Base | 3 base requests | $0.25 / 1M tokens | $2.00 / 1M tokens |
GPT-5 Series | GPT-5 nano gpt-5-nano | Base | 1 base request | $0.05 / 1M tokens | $0.40 / 1M tokens |
GPT-4.1 Series | GPT-4.1 gpt-4.1 | Premium | 1 premium request | $2.00 / 1M tokens | $8.00 / 1M tokens |
GPT-4.1 Series | GPT-4.1 mini gpt-4.1-mini | Base | 2 base requests | $0.40 / 1M tokens | $1.60 / 1M tokens |
GPT-4.1 Series | GPT-4.1 nano gpt-4.1-nano | Base | 1 base request | $0.10 / 1M tokens | $0.40 / 1M tokens |
o-Series | o3 o3 | Premium+ | 1 premium request | $2.00 / 1M tokens | $8.00 / 1M tokens |
o-Series | o4 mini o4-mini | Premium | 1 premium request | $1.10 / 1M tokens | $4.40 / 1M tokens |
o-Series | o3 mini o3-mini | Premium | 1 premium request | $1.10 / 1M tokens | $4.40 / 1M tokens |
GPT OSS | GPT OSS 120b gpt-oss-120b | Base | 1 base request | $0.15 / 1M tokens | $0.60 / 1M tokens |
GPT OSS | GPT OSS 120B Fast gpt-oss-120b-fast | Premium | 1 premium request | $0.35 / 1M tokens | $0.75 / 1M tokens |
GPT OSS | GPT OSS 20b gpt-oss-20b | Base | 1 base request | $0.07 / 1M tokens | $0.30 / 1M tokens |
 AnthropicClaude families Sonnet and Haiku without leaving the same chat surface. 1 family · 3 models | |||||
Claude | Claude Sonnet 4.6 claude-sonnet-4-6 | Premium+ | 5 premium requests | $3.00 / 1M tokens | $15.00 / 1M tokens |
Claude | Claude Sonnet 4.5 claude-sonnet-4-5 | Premium+ | 5 premium requests | $3.00 / 1M tokens | $15.00 / 1M tokens |
Claude | Claude Haiku 4.5 claude-haiku-4-5 | Premium | 1 premium request | $1.00 / 1M tokens | $5.00 / 1M tokens |
 GoogleGemini families Gemini multimodal and long-context families in the same selector. 5 families · 9 models | |||||
Gemini 2.5 Series | Gemini 2.5 Pro gemini-2.5-pro | Premium | 1 premium request | $1.25 / 1M tokens | $10.00 / 1M tokens |
Gemini 2.5 Series | Gemini 2.5 Flash gemini-2.5-flash | Base | 3 base requests | $0.30 / 1M tokens | $2.50 / 1M tokens |
Gemini 2.5 Series | Gemini 2.5 Flash-Lite gemini-2.5-flash-lite | Base | 1 base request | $0.10 / 1M tokens | $0.40 / 1M tokens |
Gemini 3.1 Series | Gemini 3.1 Pro Preview gemini-3.1-pro-preview | Premium+ | 3 premium requests | $2 / 1M (<200k) · $4 / 1M (>200k) | $12 / 1M (<200k) · $18 / 1M (>200k) |
Gemini 3.1 Series | Gemini 3.1 Flash-Lite gemini-3.1-flash-lite | Base | 2 base requests | $0.25 / 1M (text/image/video) · $0.50 (audio) | $1.50 / 1M tokens |
Gemini 3 Series | Gemini 3 Flash Preview gemini-3-flash-preview | Base | 4 base requests | $0.50 / 1M tokens | $3.00 / 1M tokens |
Gemini 3.5 Family | Gemini 3.5 Flash gemini-3.5-flash | Premium | 2 premium requests | $1.50 / 1M tokens | $9.00 / 1M tokens |
Gemini 3.5 Family | Gemini 3.5 Flash-Lite gemini-3.5-flash-lite | Base | 3 base requests | $0.30 / 1M tokens | $2.50 / 1M tokens |
gemini 3.6 family | Gemini 3.6 Flash gemini-3.6-flash | Premium | 2 premium requests | $1.50 / 1M tokens | $7.50 / 1M tokens |
 xAIGrok families Grok 3, Grok 4, Grok 4.3, Grok 4.5, Grok Code, and Grok Build kept in one workflow. 5 families · 6 models | |||||
Grok 3 | Grok-3 Mini grok-3-mini | Base | 1 base request | $0.30 / 1M tokens | $0.50 / 1M tokens |
Grok 4.20 | Grok-4.20 Reasoning grok-4.20-beta-0309-reasoning | Premium+ | 1 premium request | $1.25 / 1M tokens | $2.50 / 1M tokens |
Grok 4.20 | Grok-4.20 Non-Reasoning grok-4.20-beta-0309-non-reasoning | Premium | 1 premium request | $1.25 / 1M tokens | $2.50 / 1M tokens |
Grok 4.3 | Grok 4.3 grok-4.3 | Premium | 1 premium request | $1.25 / 1M tokens | $2.50 / 1M tokens |
Grok 4.5 | Grok 4.5 grok-4.5 | Premium | 1 premium request | $2.00 / 1M tokens | $6.00 / 1M tokens |
Grok Build | Grok Build 0.1 grok-build-0.1 | Premium | 1 premium request | $1.00 / 1M tokens | $2.00 / 1M tokens |
 MistralModel families Provider families currently surfaced in the selector. 5 families · 6 models | |||||
Mistral Large | Mistral Large 3 mistral-large-3 | Base | 2 base requests | $0.50 / 1M tokens | $1.50 / 1M tokens |
Mistral Medium | Mistral Medium 3.5 mistral-medium-3.5 | Premium | 3 premium requests | $1.50 / 1M tokens | $7.50 / 1M tokens |
Magistral | Magistral Medium magistral-medium | Premium | 2 premium requests | $2.00 / 1M tokens | $5.00 / 1M tokens |
Devstral | Devstral 2 devstral-2 | Base | 3 base requests | $0.40 / 1M tokens | $2.00 / 1M tokens |
Devstral | Devstral Small 2 devstral-small-2 | Base | 1 base request | $0.10 / 1M tokens | $0.30 / 1M tokens |
Ministral | Ministral 14B ministral-14b | Base | 1 base request | $0.20 / 1M tokens | $0.20 / 1M tokens |
 Thinking MachinesInkling families Inkling open-weights multimodal MoE via the Vercel AI Gateway, with image input and controllable thinking effort on the base tier. 1 family · 1 model | |||||
Inkling | Inkling inkling | Base | 4 base requests | $1.00 / 1M tokens | $4.05 / 1M tokens |
 DeepSeekDeepSeek families Reasoning-heavy DeepSeek routes for people who want that behavior on purpose. 1 family · 2 models | |||||
DeepSeek | DeepSeek V4 Flash deepseek-v4-flash | Base | 1 base request | $0.14 / 1M tokens | $0.28 / 1M tokens |
DeepSeek | DeepSeek V4 Pro deepseek-v4-pro | Premium | 1 premium request | $1.74 / 1M tokens | $3.48 / 1M tokens |
 QwenQwen families Alibaba Qwen routed through Fireworks and the Vercel AI Gateway for strong multimodal and tool-capable chat at the base tier. 1 family · 1 model | |||||
Qwen | Qwen 3.7 Plus qwen3p7-plus | Base | 2 base requests | $0.40 / 1M tokens | $1.60 / 1M tokens |
 MoonshotKimi families Kimi models from Moonshot, including K2.6, for fast reasoning and multimodal work. 1 family · 3 models | |||||
Kimi | Kimi K2.6 kimi-k2p6 | Premium | 2 premium requests | $0.95 / 1M tokens | $4.00 / 1M tokens |
Kimi | Kimi K2.7 Code kimi-k2p7-code | Premium | 2 premium requests | $0.95 / 1M tokens | $4.00 / 1M tokens |
Kimi | Kimi K2.7 Code Highspeed kimi-k2p7-code-highspeed | Premium | 3 premium requests | $1.90 / 1M tokens | $8.00 / 1M tokens |
 MiniMaxMiniMax families MiniMax M2.5 and M2.7 for agentic, multilingual, and office-style tasks. 1 family · 2 models | |||||
MiniMax | MiniMax M2.7 minimax-m2p7 | Base | 2 base requests | $0.30 / 1M tokens | $1.20 / 1M tokens |
MiniMax | MiniMax M3 minimax-m3 | Base | 2 base requests | $0.30 / 1M tokens | $1.20 / 1M tokens |
 Z.aiGLM families GLM 4.7, GLM 5, and GLM 5.1 families for coding-heavy and high-context chats. 2 families · 2 models | |||||
GLM 4.7 Family | GLM 4.7 Fast glm-4p7-fast | Premium | 2 premium requests | $2.25 / 1M tokens | $2.75 / 1M tokens |
GLM 5 Family | GLM 5.2 glm-5p2 | Premium | 2 premium requests | $1.40 / 1M tokens | $4.40 / 1M tokens |
 NVIDIANemotron families NVIDIA Nemotron open mixture-of-experts models for high-throughput reasoning and agentic work. 1 family · 1 model | |||||
Nemotron | Nemotron 3 Ultra nemotron-3-ultra | Base | 2 base requests | $0.37 / 1M tokens | $1.08 / 1M tokens |
 just4o.chatEcho families Echo and Echo mini, native to the product instead of routed from a third party. 1 family · 3 models | |||||
Echo | Echo mini echo-mini | Base | 1 base request | — | — |
Echo | Echo echo | Premium+ | 1 premium request | — | — |
Echo | Echo max echo-max | Premium+ | 3 premium requests | — | — |
API input/output figures are provider list prices as tracked in the catalog (usually per 1M tokens); request cost is the flat per-send unit before length and tool multipliers. Echo models have no separate per-token pass-through. New chats inherit your last model choice, so comparing providers stays quick.
Try the switchboard
If model behavior matters to you, the selector should mean something.
Open a chat, pick the family you want, and compare it against the rest without leaving the same workspace or wondering who is actually answering.