Pricing
Prepaid credit, not a plan
No monthly fee, no seats, and nothing to cancel. Buy credit from $5, spend it as you use Redrob, and top up when you want to.
Your first payment
$5
minimum, one off
Roughly 58,000 conversations: a question with some context behind it and an answer of a few paragraphs. It is an estimate, and the console shows what you actually spent.
- No plan to choose
- No free trial, no welcome credit
- Card or wallet, through Stripe
Top up when you want
From $5
any amount, any time
One balance for the whole workspace, drawn on by every Redrob application and by the API. It does not expire, and there is nothing to renew.
- Spend it across every application
- Per-request cost in the log
- Runs out and requests stop
Or let it top itself up
+$0
no premium for the convenience
Set the balance to refill at and the amount to add, and an unattended integration keeps running without anyone watching the number.
- Same rate, no premium
- Off by default
- Changed or stopped in Console
What a request costs
What it cost us, plus 5%
A short question
500 in / 300 out
- mistralai/mistral-nemo
- $0.0000252,631/$1
- gpt-5.6-terra
- $0.00483207/$1
- claude-sonnet-5
- $0.00630158/$1
- claude-fable-5
- $0.02147/$1
A coding turn
8,000 in / 1,500 out
- mistralai/mistral-nemo
- $0.000214,830/$1
- gpt-5.6-terra
- $0.03628/$1
- claude-sonnet-5
- $0.04920/$1
- claude-fable-5
- $0.1636/$1
A long document
60,000 in / 2,000 out
- mistralai/mistral-nemo
- $0.00126793/$1
- gpt-5.6-terra
- $0.1516/$1
- claude-sonnet-5
- $0.2214/$1
- claude-fable-5
- $0.7351/$1
Every model is billed at what it costs us, plus 5% for the routing, metering and keys around it. The cost is published beside the price, so the cut is checkable rather than asserted. `auto` is billed the same way, at whatever model it routed the request to.
| Model | Input | Output |
|---|---|---|
| mistralai/mistral-nemotool calling · structured output | $0.0199 ← $0.0190 | $0.0315 ← $0.0300 |
| gpt-5.6-terratool calling · structured output · million-token contextaccepts images | $2.10 ← $2.00$4.20 above 272K | $12.60 ← $12.00$18.90 above 272K |
| claude-sonnet-5tool calling · structured output · adjustable reasoning (low, medium, high, xhigh, max) · priority tieraccepts images | $3.15 ← $3.00 | $15.75 ← $15.00 |
| claude-fable-5tool calling · structured output · adjustable reasoning (low, medium, high, xhigh, max) · priority tieraccepts images | $10.50 ← $10.00 | $52.50 ← $50.00 |
The card above is one model from each price band, not the whole catalogue: 322 models are callable, and the full list with rates and capabilities is a single unauthenticated request to /v1/pricing. 176 of them accept an image in the request and 25 accept audio, priced as the input tokens the vendor reports for it; sending one to a model that cannot read it is a refusal rather than an answer that ignored it. Long-context pricing follows actual input usage, not the selected context limit. Fast mode uses Bedrock Priority and costs 1.75x. Some models require explicit acceptance of their provider data-sharing terms.
Per-model rates
Every model this workspace can call, and what each one costs
322 models, priced per million tokens with our 5% already included, so these are the figures that reach the bill. Read at request time from the gateway that charges them.
auto, the default
auto has no rate of its own. A request on auto is billed at the rate of whichever model the router picked for it, so the range below is the cheapest and the dearest it can reach.
$0.018 to $158 per million input · $0.118 to $630 per million output
| Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|
| Budget176 | |||
| ibm-granite/granite-4.0-h-microIBM: Granite 4.0 Micro | 131K | $0.018 | $0.118 |
| mistralai/mistral-nemoMistral: Mistral Nemo | 131K | $0.020 | $0.032 |
| inclusionai/ling-3.0-flashinclusionAI: Ling 3.0 Flash | 262K | $0.022 | $0.066 |
| meta-llama/llama-3.2-1b-instructMeta: Llama 3.2 1B Instruct | 60K | $0.028 | $0.211 |
| inference-net/schematron-v2-turboInference.net: Schematron V2 Turbo | 128K | $0.032 | $0.158 |
| openai/gpt-oss-20bOpenAI: gpt-oss-20b | 131K | $0.032 | $0.137 |
| qwen/qwen3.7-flashQwen: Qwen3.7 Flash | 1M | $0.032 | $0.137 |
| amazon/nova-micro-v1Amazon: Nova Micro 1.0 | 128K | $0.037 | $0.147 |
| openai/gpt-oss-120bOpenAI: gpt-oss-120b | 131K | $0.039 | $0.178 |
| cohere/command-r7b-12-2024Cohere: Command R7B (12-2024) | 128K | $0.039 | $0.158 |
| inception/mercury-2.5Inception: Mercury 2.5 | 260K | $0.042 | $0.158 |
| sao10k/l3-lunaris-8bSao10K: Llama 3 8B Lunaris | 8K | $0.042 | $0.052 |
| tencent/hy-mt2-1.8bTencent: Hy-MT2-1.8B | 8K | $0.046 | $0.186 |
| qwen/qwen3-30b-a3b-instruct-2507Qwen: Qwen3 30B A3B Instruct 2507 | 262K | $0.051 | $0.203 |
| google/gemma-3-12b-itGoogle: Gemma 3 12B | 131K | $0.052 | $0.158 |
| google/gemma-3-4b-itGoogle: Gemma 3 4B | 131K | $0.052 | $0.105 |
| inference-net/schematron-v2-smallInference.net: Schematron V2 Small | 128K | $0.052 | $0.241 |
| meta-llama/llama-3.1-8b-instructMeta: Llama 3.1 8B Instruct | 131K | $0.052 | $0.084 |
| meta-llama/llama-3.2-3b-instructMeta: Llama 3.2 3B Instruct | 131K | $0.052 | $0.346 |
| mistralai/mistral-small-24b-instruct-2501Mistral: Mistral Small 3 | 33K | $0.052 | $0.084 |
| nvidia/nemotron-3-nano-30b-a3bNVIDIA: Nemotron 3 Nano 30B A3B | 262K | $0.052 | $0.210 |
| openai/gpt-5-nanoOpenAI: GPT-5 Nano | 400K | $0.052 | $0.420 |
| amazon/nova-lite-v1Amazon: Nova Lite 1.0 | 300K | $0.063 | $0.252 |
| deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 | 1.3M | $0.063 | $0.126 |
| gryphe/mythomax-l2-13bMythoMax 13B | 8K | $0.063 | $0.063 |
| ibm-granite/granite-4.2-8bIBM: Granite 4.2 8B | 131K | $0.063 | $0.263 |
| inclusionai/ling-3.0-flash-fininclusionAI: Ling 3.0 Flash Fin | 262K | $0.063 | $0.189 |
| inclusionai/ling-3.0-flash-vlinclusionAI: Ling 3.0 Flash VL | 131K | $0.063 | $0.189 |
| poolside/laguna-xs-2.1Poolside: Laguna XS 2.1 | 262K | $0.063 | $0.126 |
| z-ai/glm-4.7-flashZ.ai: GLM 4.7 Flash | 200K | $0.064 | $0.420 |
| qwen/qwen3.5-flash-02-23Qwen: Qwen3.5-Flash | 1M | $0.068 | $0.273 |
| microsoft/phi-4Microsoft: Phi 4 | 16K | $0.073 | $0.147 |
| qwen/qwen3-coder-30b-a3b-instructQwen: Qwen3 Coder 30B A3B Instruct | 262K | $0.073 | $0.294 |
| tencent/hy-mt2-30b-a3bTencent: Hy-MT2-30B-A3B | 8K | $0.078 | $0.310 |
| tencent/hy-mt2-7bTencent: Hy-MT2-7B | 8K | $0.078 | $0.310 |
| bytedance-seed/seed-1.6-flashByteDance Seed: Seed 1.6 Flash | 262K | $0.079 | $0.315 |
| mistralai/mistral-small-3.2-24b-instructMistral: Mistral Small 3.2 24B | 256K | $0.079 | $0.210 |
| openai/gpt-oss-safeguard-20bOpenAI: gpt-oss-safeguard-20b | 131K | $0.079 | $0.315 |
| z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash | 1.3M | $0.079 | $0.263 |
| google/gemma-3-27b-itGoogle: Gemma 3 27B | 131K | $0.084 | $0.472 |
| nvidia/nemotron-3-super-120b-a12bNVIDIA: Nemotron 3 Super | 262K | $0.084 | $0.472 |
| nvidia/nemotron-3.5-lightningNVIDIA: Nemotron 3.5 Lightning | 262K | $0.084 | $0.210 |
| qwen/qwen3-32bQwen: Qwen3 32B | 131K | $0.084 | $0.294 |
| tencent/hy3Tencent: Hy3 | 262K | $0.087 | $0.346 |
| deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 | 1M | $0.090 | $0.180 |
| qwen/qwen3-235b-a22b-2507Qwen: Qwen3 235B A22B Instruct 2507 | 262K | $0.092 | $0.367 |
| google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B | 262K | $0.095 | $0.315 |
| google/gemma-4-31b-itGoogle: Gemma 4 31B | 262K | $0.095 | $0.357 |
| poolside/laguna-s-2.1Poolside: Laguna S 2.1 | 1M | $0.095 | $0.189 |
| qwen/qwen3-next-80b-a3b-instructQwen: Qwen3 Next 80B A3B Instruct | 262K | $0.095 | $1.16 |
| upstage/solar-pro4Upstage: Solar Pro 4 | 524K | $0.095 | $0.378 |
| bytedance-seed/seed-2.0-miniByteDance Seed: Seed-2.0-Mini | 262K | $0.105 | $0.420 |
| bytedance/ui-tars-1.5-7bByteDance: UI-TARS 7B | 128K | $0.105 | $0.210 |
| google/gemini-2.5-flash-liteGoogle: Gemini 2.5 Flash Lite | 1M | $0.105 | $0.420 |
| meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct | 131K | $0.105 | $0.336 |
| meta-llama/llama-4-scoutMeta: Llama 4 Scout | 1.3M | $0.105 | $0.315 |
| meta/muse-spark-1.2-contributorMeta: Muse Spark 1.2 Contributor | 1M | $0.105 | $0.210 |
| meta/muse-spark-1.3-contributorMeta: Muse Spark 1.3 Contributor | 1M | $0.105 | $0.210 |
| mistralai/ministral-3b-2512Mistral: Ministral 3 3B 2512 | 131K | $0.105 | $0.105 |
| mistralai/voxtral-small-24b-2507Mistral: Voxtral Small 24B 2507 | 33K | $0.105 | $0.315 |
| openai/gpt-4.1-nanoOpenAI: GPT-4.1 Nano | 1M | $0.105 | $0.420 |
| qwen/qwen-2.5-7b-instructQwen: Qwen2.5 7B Instruct | 33K | $0.105 | $0.210 |
| qwen/qwen3.5-9bQwen: Qwen3.5-9B | 262K | $0.105 | $0.158 |
| qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B | 262K | $0.105 | $0.945 |
| rekaai/reka-edgeReka Edge | 16K | $0.105 | $0.105 |
| rekaai/reka-flash-3Reka Flash 3 | 66K | $0.105 | $0.210 |
| stepfun/step-3.5-flashStepFun: Step 3.5 Flash | 262K | $0.105 | $0.315 |
| qwen/qwen3-vl-32b-instructQwen: Qwen3 VL 32B Instruct | 131K | $0.109 | $0.437 |
| qwen/qwen3-8bQwen: Qwen3 8B | 131K | $0.123 | $0.478 |
| qwen/qwen3-vl-8b-instructQwen: Qwen3 VL 8B Instruct | 262K | $0.123 | $0.478 |
| qwen/qwen3-14bQwen: Qwen3 14B | 131K | $0.126 | $0.252 |
| qwen/qwen3-30b-a3bQwen: Qwen3 30B A3B | 131K | $0.126 | $0.525 |
| qwen/qwen3-coder-nextQwen: Qwen3 Coder Next | 262K | $0.126 | $0.840 |
| z-ai/glm-4.5-airZ.ai: GLM 4.5 Air | 131K | $0.137 | $0.892 |
| tencent/hunyuan-a13b-instructTencent: Hunyuan A13B Instruct | 131K | $0.147 | $0.599 |
| xiaomi/mimo-v2.5Xiaomi: MiMo-V2.5 | 1.1M | $0.147 | $0.294 |
| cohere/command-r-08-2024Cohere: Command R (08-2024) | 128K | $0.158 | $0.630 |
| deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash | 1M | $0.158 | $0.630 |
| mistralai/ministral-8b-2512Mistral: Ministral 3 8B 2512 | 262K | $0.158 | $0.158 |
| mistralai/mistral-small-2603Mistral: Mistral Small 4 | 262K | $0.158 | $0.630 |
| openai/gpt-4o-miniOpenAI: GPT-4o-mini | 128K | $0.158 | $0.630 |
| openai/gpt-4o-mini-2024-07-18OpenAI: GPT-4o-mini (2024-07-18) | 128K | $0.158 | $0.630 |
| perceptron/perceptron-mk1Perceptron: Perceptron Mk1 | 33K | $0.158 | $1.57 |
| qwen/qwen3-next-80b-a3b-thinkingQwen: Qwen3 Next 80B A3B Thinking | 262K | $0.158 | $1.26 |
| qwen/qwen3-vl-30b-a3b-instructQwen: Qwen3 VL 30B A3B Instruct | 262K | $0.158 | $0.630 |
| qwen/qwen3.8-flashQwen: Qwen3.8 Flash | 1M | $0.158 | $0.493 |
| upstage/solar-pro-3Upstage: Solar Pro 3 | 131K | $0.158 | $0.630 |
| qwen/qwen3.5-35b-a3bQwen: Qwen3.5-35B-A3B | 262K | $0.171 | $1.36 |
| meta-llama/llama-guard-4-12bMeta: Llama Guard 4 12B | 164K | $0.189 | $0.189 |
| qwen/qwen3-vl-8b-thinkingQwen: Qwen3 VL 8B Thinking | 131K | $0.189 | $2.21 |
| tencent/hy3-previewTencent: Hy3 preview | 262K | $0.189 | $0.630 |
| meta-llama/llama-4-maverickMeta: Llama 4 Maverick | 1M | $0.197 | $0.685 |
| qwen/qwen3.6-flashQwen: Qwen3.6 Flash | 1M | $0.197 | $1.18 |
| qwen/qwen3-coder-flashQwen: Qwen3 Coder Flash | 1M | $0.205 | $1.02 |
| qwen/qwen3.5-27bQwen: Qwen3.5-27B | 262K | $0.205 | $1.64 |
| cognitivecomputations/dolphin-mistral-24b-venice-editionVenice: Uncensored | 128K | $0.210 | $0.945 |
| minimax/minimax-01MiniMax: MiniMax-01 | 1M | $0.210 | $1.16 |
| mistralai/ministral-14b-2512Mistral: Ministral 3 14B 2512 | 262K | $0.210 | $0.210 |
| mistralai/mistral-sabaMistral: Saba | 33K | $0.210 | $0.630 |
| nvidia/nemotron-3.5-content-safetyNVIDIA: Nemotron 3.5 Content Safety | 131K | $0.210 | $0.210 |
| openai/gpt-5.4-nanoOpenAI: GPT-5.4 Nano | 400K | $0.210 | $1.31 |
| openai/gpt-5.6-luna-proOpenAI: GPT-5.6 Luna Pro | 1.1M | $0.210 | $1.26 |
| qwen/qwen3-30b-a3b-thinking-2507Qwen: Qwen3 30B A3B Thinking 2507 | 82K | $0.210 | $2.52 |
| qwen/qwen3-vl-30b-a3b-thinkingQwen: Qwen3 VL 30B A3B Thinking | 262K | $0.210 | $2.52 |
| stepfun/step-3.7-flashStepFun: Step 3.7 Flash | 262K | $0.210 | $1.21 |
| qwen/qwen3-vl-235b-a22b-instructQwen: Qwen3 VL 235B A22B Instruct | 262K | $0.221 | $2.00 |
| qwen/qwen3.8-27bQwen: Qwen3.8 27B | 1M | $0.225 | $2.68 |
| deepseek/deepseek-v4-flash-vision-expDeepSeek: DeepSeek V4 Flash Vision Exp | 1M | $0.231 | $0.693 |
| qwen/qwen3-235b-a22b-thinking-2507Qwen: Qwen3 235B A22B Thinking 2507 | 131K | $0.241 | $2.42 |
| anthropic/claude-3-haikuAnthropic: Claude 3 Haiku | 200K | $0.263 | $1.31 |
| arcee-ai/trinity-large-thinkingArcee AI: Trinity Large Thinking | 262K | $0.263 | $0.840 |
| bytedance-seed/seed-1.6ByteDance Seed: Seed 1.6 | 262K | $0.263 | $2.10 |
| bytedance-seed/seed-2.0-liteByteDance Seed: Seed-2.0-Lite | 262K | $0.263 | $2.10 |
| deepseek/deepseek-chat-v3-0324DeepSeek: DeepSeek V3 0324 | 164K | $0.263 | $1.05 |
| deepseek/deepseek-chat-v3.1DeepSeek: DeepSeek V3.1 | 164K | $0.263 | $0.998 |
| google/gemini-3.1-flash-liteGoogle: Gemini 3.1 Flash Lite | 1M | $0.263 | $1.57 |
| google/gemini-3.1-flash-lite-imageGoogle: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 66K | $0.263 | $1.57 |
| google/gemini-3.1-flash-lite-previewGoogle: Gemini 3.1 Flash Lite Preview | 1M | $0.263 | $1.57 |
| inception/mercury-2Inception: Mercury 2 | 128K | $0.263 | $0.787 |
| openai/gpt-5-miniOpenAI: GPT-5 Mini | 400K | $0.263 | $2.10 |
| openai/gpt-5.1-codex-miniOpenAI: GPT-5.1-Codex-Mini | 400K | $0.263 | $2.10 |
| minimax/minimax-m2MiniMax: MiniMax M2 | 205K | $0.268 | $1.07 |
| deepseek/deepseek-chatDeepSeek: DeepSeek V3 | 164K | $0.270 | $1.08 |
| qwen/qwen-plusQwen: Qwen-Plus | 1M | $0.273 | $0.819 |
| qwen/qwen-plus-2025-07-28Qwen: Qwen Plus 0728 | 1M | $0.273 | $0.819 |
| qwen/qwen3.5-122b-a10bQwen: Qwen3.5-122B-A10B | 262K | $0.273 | $2.18 |
| qwen/qwen3.5-plus-02-15Qwen: Qwen3.5 Plus 2026-02-15 | 1M | $0.273 | $1.64 |
| deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 | 164K | $0.282 | $0.420 |
| deepseek/deepseek-v3.1-terminusDeepSeek: DeepSeek V3.1 Terminus | 164K | $0.283 | $1.05 |
| deepseek/deepseek-v3.2-expDeepSeek: DeepSeek V3.2 Exp | 164K | $0.283 | $0.430 |
| minimax/minimax-m2.5MiniMax: MiniMax M2.5 | 205K | $0.283 | $1.13 |
| amazon/nova-2-lite-v1Amazon: Nova 2 Lite | 1M | $0.315 | $2.63 |
| google/gemini-2.5-flashGoogle: Gemini 2.5 Flash | 1M | $0.315 | $2.63 |
| google/gemini-2.5-flash-imageGoogle: Nano Banana (Gemini 2.5 Flash Image) | 33K | $0.315 | $2.63 |
| google/gemini-3.5-flash-liteGoogle: Gemini 3.5 Flash Lite | 1M | $0.315 | $2.63 |
| kwaipilot/kat-coder-pro-v2Kwaipilot: KAT-Coder-Pro V2 | 262K | $0.315 | $1.26 |
| meituan/longcat-2.0Meituan: LongCat 2.0 | 1M | $0.315 | $1.26 |
| minimax/minimax-m2-herMiniMax: MiniMax M2-her | 66K | $0.315 | $1.26 |
| minimax/minimax-m2.1MiniMax: MiniMax M2.1 | 205K | $0.315 | $1.26 |
| minimax/minimax-m2.7MiniMax: MiniMax M2.7 | 205K | $0.315 | $1.26 |
| minimax/minimax-m3MiniMax: MiniMax M3 | 1M | $0.315 | $1.26 |
| mistralai/codestral-2508Mistral: Codestral 2508 | 256K | $0.315 | $0.945 |
| qwen/qwen3-coderQwen: Qwen3 Coder 480B A35B | 262K | $0.315 | $1.05 |
| qwen/qwen3.5-plus-20260420Qwen: Qwen3.5 Plus 2026-04-20 | 1M | $0.315 | $1.89 |
| qwen/qwen3.6-27bQwen: Qwen3.6 27B | 262K | $0.315 | $2.10 |
| thedrummer/cydonia-24b-v4.1TheDrummer: Cydonia 24B V4.1 | 131K | $0.315 | $0.525 |
| z-ai/glm-4.6vZ.ai: GLM 4.6V | 131K | $0.315 | $0.945 |
| qwen/qwen3.7-plusQwen: Qwen3.7 Plus | 1M | $0.336 | $1.34 |
| qwen/qwen3.6-plusQwen: Qwen3.6 Plus | 1M | $0.341 | $2.05 |
| meta/muse-glimmer-30bMeta: Muse Glimmer 30B | 131K | $0.367 | $1.57 |
| undi95/remm-slerp-l2-13bReMM SLERP 13B | 6K | $0.367 | $0.682 |
| mistralai/mistral-small-3.1-24b-instructMistral: Mistral Small 3.1 24B | 128K | $0.369 | $0.583 |
| qwen/qwen-2.5-72b-instructQwen2.5 72B Instruct | 33K | $0.378 | $0.420 |
| mancer/weaverMancer: Weaver (alpha) | 8K | $0.420 | $0.787 |
| meta-llama/llama-3.1-70b-instructMeta: Llama 3.1 70B Instruct | 131K | $0.420 | $0.420 |
| mistralai/devstral-2512Mistral: Devstral 2 2512 | 262K | $0.420 | $2.10 |
| mistralai/mistral-medium-3Mistral: Mistral Medium 3 | 131K | $0.420 | $2.10 |
| mistralai/mistral-medium-3.1Mistral: Mistral Medium 3.1 | 131K | $0.420 | $2.10 |
| openai/gpt-4.1-miniOpenAI: GPT-4.1 Mini | 1M | $0.420 | $1.68 |
| qwen/qwen3-vl-235b-a22b-thinkingQwen: Qwen3 VL 235B A22B Thinking | 131K | $0.420 | $4.20 |
| thedrummer/unslopnemo-12bTheDrummer: UnslopNemo 12B | 1M | $0.420 | $0.420 |
| z-ai/glm-4.7Z.ai: GLM 4.7 | 205K | $0.420 | $1.84 |
| baidu/ernie-4.5-vl-424b-a47bBaidu: ERNIE 4.5 VL 424B A47B | 123K | $0.441 | $1.31 |
| z-ai/glm-4.6Z.ai: GLM 4.6 | 205K | $0.452 | $1.84 |
| xiaomi/mimo-v2.5-proXiaomi: MiMo-V2.5-Pro | 1.1M | $0.457 | $0.913 |
| moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 | 262K | $0.472 | $2.36 |
| thinkingmachines/inkling-smallThinking Machines: Inkling Small | 1M | $0.472 | $1.26 |
| qwen/qwen3-235b-a22bQwen: Qwen3 235B A22B | 131K | $0.478 | $1.91 |
| bytedance-seed/seed-2-1-turboByteDance Seed: Seed 2.1 Turbo | 262K | $0.525 | $2.63 |
| bytedance-seed/seed-2.0-codeByteDance Seed: Seed-2.0-Code | 262K | $0.525 | $3.15 |
| deepseek/deepseek-r1-0528DeepSeek: R1 0528 | 164K | $0.525 | $2.26 |
| google/gemini-3-flash-previewGoogle: Gemini 3 Flash Preview | 1M | $0.525 | $3.15 |
| google/gemini-3.1-flash-imageGoogle: Nano Banana 2 (Gemini 3.1 Flash Image) | 131K | $0.525 | $3.15 |
| google/gemini-3.1-flash-image-previewGoogle: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 66K | $0.525 | $3.15 |
| mistralai/mistral-large-2512Mistral: Mistral Large 3 2512 | 262K | $0.525 | $1.57 |
| openai/gpt-3.5-turboOpenAI: GPT-3.5 Turbo | 16K | $0.525 | $1.57 |
| Standard99 | |||
| minimax/minimax-m1MiniMax: MiniMax M1 | 1M | $0.578 | $2.31 |
| qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B | 262K | $0.578 | $3.67 |
| thedrummer/skyfall-36b-v2TheDrummer: Skyfall 36B V2 | 33K | $0.578 | $0.840 |
| moonshotai/kimi-k2MoonshotAI: Kimi K2 0711 | 131K | $0.599 | $2.42 |
| deepseek/deepseek-v4-pro-0813DeepSeek: DeepSeek V4 Pro 0813 | 1M | $0.608 | $1.83 |
| moonshotai/kimi-k2-0905MoonshotAI: Kimi K2 0905 | 262K | $0.630 | $2.63 |
| moonshotai/kimi-k2-thinkingMoonshotAI: Kimi K2 Thinking | 262K | $0.630 | $2.63 |
| nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra | 262K | $0.630 | $2.52 |
| openai/gpt-audio-miniOpenAI: GPT Audio Mini | 128K | $0.630 | $2.52 |
| writer/palmyra-x5Writer: Palmyra X5 | 1M | $0.630 | $6.30 |
| z-ai/glm-4.5Z.ai: GLM 4.5 | 131K | $0.630 | $2.31 |
| z-ai/glm-4.5vZ.ai: GLM 4.5V | 66K | $0.630 | $1.89 |
| z-ai/glm-5Z.ai: GLM 5 | 205K | $0.630 | $2.02 |
| microsoft/wizardlm-2-8x22bWizardLM-2 8x22B | 66K | $0.651 | $0.651 |
| google/gemma-2-27b-itGoogle: Gemma 2 27B | 8K | $0.682 | $0.682 |
| qwen/qwen3-coder-plusQwen: Qwen3 Coder Plus | 1M | $0.682 | $3.41 |
| sao10k/l3.3-euryale-70bSao10K: Llama 3.3 Euryale 70B | 131K | $0.682 | $0.787 |
| qwen/qwen-2.5-coder-32b-instructQwen2.5 Coder 32B Instruct | 33K | $0.693 | $1.05 |
| aion-labs/aion-3.0-miniAionLabs: Aion-3.0-Mini | 131K | $0.735 | $1.47 |
| deepseek/deepseek-r1DeepSeek: R1 | 64K | $0.735 | $2.63 |
| nousresearch/hermes-3-llama-3.1-70bNous: Hermes 3 70B Instruct | 131K | $0.735 | $0.735 |
| moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code | 262K | $0.746 | $3.67 |
| kwaipilot/kat-coder-pro-v2.5Kwaipilot: KAT-Coder-Pro V2.5 | 262K | $0.777 | $3.11 |
| google/gemini-3.6-flashGoogle: Gemini 3.6 Flash | 1M | $0.787 | $3.94 |
| google/gemini-3.7-flashGoogle: Gemini 3.7 Flash | 1M | $0.787 | $3.94 |
| google/gemini-3.8-flashGoogle: Gemini 3.8 Flash | 1M | $0.787 | $3.94 |
| openai/gpt-5.4-miniOpenAI: GPT-5.4 Mini | 400K | $0.787 | $4.72 |
| qwen/qwen3-maxQwen: Qwen3 Max | 262K | $0.819 | $4.09 |
| qwen/qwen3-max-thinkingQwen: Qwen3 Max Thinking | 262K | $0.819 | $4.09 |
| aion-labs/aion-2.0AionLabs: Aion-2.0 | 131K | $0.840 | $1.68 |
| aion-labs/aion-rp-llama-3.1-8bAionLabs: Aion-RP 1.0 (8B) | 33K | $0.840 | $1.68 |
| amazon/nova-pro-v1Amazon: Nova Pro 1.0 | 300K | $0.840 | $3.36 |
| deepseek/deepseek-r1-distill-llama-70bDeepSeek: R1 Distill Llama 70B | 8K | $0.840 | $0.840 |
| morph/morph-v3-fastMorph: Morph V3 Fast | 82K | $0.840 | $1.26 |
| qwen/qwen2.5-vl-72b-instructQwen: Qwen2.5 VL 72B Instruct | 128K | $0.840 | $1.05 |
| tencent/hy4-previewTencent: Hy4 preview | 1M | $0.876 | $2.63 |
| relace/relace-apply-3Relace: Relace Apply 3 | 256K | $0.892 | $1.31 |
| sao10k/l3.1-euryale-70bSao10K: Llama 3.1 Euryale 70B v2.2 | 131K | $0.892 | $0.892 |
| morph/morph-v3-largeMorph: Morph V3 Large | 262K | $0.945 | $2.00 |
| moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 | 262K | $0.998 | $4.20 |
| sakana/sakana-namazuSakana: Sakana Namazu | 262K | $0.998 | $4.20 |
| z-ai/glm-5.1Z.ai: GLM 5.1 | 205K | $1.01 | $3.19 |
| anthropic/claude-haiku-4.5Anthropic: Claude Haiku 4.5 | 200K | $1.05 | $5.25 |
| nousresearch/hermes-3-llama-3.1-405bNous: Hermes 3 405B Instruct | 131K | $1.05 | $1.05 |
| nousresearch/hermes-4-405bNous: Hermes 4 405B | 131K | $1.05 | $3.15 |
| openai/gpt-3.5-turbo-0613OpenAI: GPT-3.5 Turbo (older v0613) | 4K | $1.05 | $2.10 |
| perplexity/sonarPerplexity: Sonar | 127K | $1.05 | $1.05 |
| relace/relace-searchRelace: Relace Search | 256K | $1.05 | $3.15 |
| thinkingmachines/inklingThinking Machines: Inkling | 1M | $1.05 | $4.25 |
| x-ai/grok-build-0.1SpaceXAI: Grok Build 0.1 | 256K | $1.05 | $2.10 |
| qwen/qwen3.6-max-previewQwen: Qwen3.6 Max Preview | 262K | $1.08 | $6.47 |
| openai/o3-miniOpenAI: o3 Mini | 200K | $1.16 | $4.62 |
| openai/o3-mini-highOpenAI: o3 Mini High | 200K | $1.16 | $4.62 |
| openai/o4-miniOpenAI: o4 Mini | 200K | $1.16 | $4.62 |
| openai/o4-mini-highOpenAI: o4 Mini High | 200K | $1.16 | $4.62 |
| z-ai/glm-5-turboZ.ai: GLM 5 Turbo | 203K | $1.26 | $4.20 |
| z-ai/glm-5v-turboZ.ai: GLM 5V Turbo | 203K | $1.26 | $4.20 |
| google/gemini-2.5-proGoogle: Gemini 2.5 Pro | 1M | $1.31 | $10.50 |
| google/gemini-2.5-pro-previewGoogle: Gemini 2.5 Pro Preview 06-05 | 1M | $1.31 | $10.50 |
| meta/muse-spark-1.1Meta: Muse Spark 1.1 | 1M | $1.31 | $4.46 |
| meta/muse-spark-1.2Meta: Muse Spark 1.2 | 1M | $1.31 | $4.46 |
| meta/muse-spark-1.3Meta: Muse Spark 1.3 | 1M | $1.31 | $4.46 |
| openai/gpt-5OpenAI: GPT-5 | 400K | $1.31 | $10.50 |
| openai/gpt-5.1OpenAI: GPT-5.1 | 400K | $1.31 | $10.50 |
| openai/gpt-5.1-codexOpenAI: GPT-5.1-Codex | 400K | $1.31 | $10.50 |
| openai/gpt-5.1-codex-maxOpenAI: GPT-5.1-Codex-Max | 400K | $1.31 | $10.50 |
| x-ai/grok-4.20SpaceXAI: Grok 4.20 | 2M | $1.31 | $2.63 |
| x-ai/grok-4.20-multi-agentSpaceXAI: Grok 4.20 Multi-Agent | 2M | $1.31 | $2.63 |
| x-ai/grok-4.3SpaceXAI: Grok 4.3 | 1M | $1.31 | $2.63 |
| z-ai/glm-5.2Z.ai: GLM 5.2 | 1M | $1.47 | $4.62 |
| z-ai/glm-5.3Z.ai: GLM 5.3 | 1.3M | $1.47 | $4.62 |
| qwen/qwen3.7-maxQwen: Qwen3.7 Max | 1M | $1.55 | $4.65 |
| google/gemini-3.5-flashGoogle: Gemini 3.5 Flash | 1M | $1.57 | $9.45 |
| mistralai/mistral-medium-3-5Mistral: Mistral Medium 3.5 | 262K | $1.57 | $7.88 |
| openai/gpt-3.5-turbo-instructOpenAI: GPT-3.5 Turbo Instruct | 4K | $1.57 | $2.10 |
| deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 | 1M | $1.68 | $3.36 |
| openai/gpt-5.2OpenAI: GPT-5.2 | 400K | $1.84 | $14.70 |
| openai/gpt-5.2-chatOpenAI: GPT-5.2 Chat | 128K | $1.84 | $14.70 |
| openai/gpt-5.2-codexOpenAI: GPT-5.2-Codex | 400K | $1.84 | $14.70 |
| openai/gpt-5.3-codexOpenAI: GPT-5.3-Codex | 400K | $1.84 | $14.70 |
| gpt-5.6-terra | 1M | $2.10 | $12.60 |
| google/gemini-3-pro-imageGoogle: Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2.10 | $12.60 |
| google/gemini-3-pro-image-previewGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | $2.10 | $12.60 |
| google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview | 1M | $2.10 | $12.60 |
| google/gemini-3.1-pro-preview-customtoolsGoogle: Gemini 3.1 Pro Preview Custom Tools | 1M | $2.10 | $12.60 |
| mistralai/mistral-largeMistral Large | 128K | $2.10 | $6.30 |
| mistralai/mistral-large-2407Mistral Large 2407 | 131K | $2.10 | $6.30 |
| mistralai/mixtral-8x22b-instructMistral: Mixtral 8x22B Instruct | 66K | $2.10 | $6.30 |
| openai/gpt-4.1OpenAI: GPT-4.1 | 1M | $2.10 | $8.40 |
| openai/gpt-5.6-sol-proOpenAI: GPT-5.6 Sol Pro | 1.1M | $2.10 | $10.50 |
| openai/gpt-5.6-terra-proOpenAI: GPT-5.6 Terra Pro | 1.1M | $2.10 | $12.60 |
| openai/o3OpenAI: o3 | 200K | $2.10 | $8.40 |
| perplexity/sonar-deep-researchPerplexity: Sonar Deep Research | 128K | $2.10 | $8.40 |
| perplexity/sonar-reasoning-proPerplexity: Sonar Reasoning Pro | 128K | $2.10 | $8.40 |
| qwen/qwen3.8-2.4t-a95bQwen: Qwen3.8 2.4T A95B | 1M | $2.10 | $6.30 |
| qwen/qwen3.8-max-0902Qwen: Qwen3.8 Max (0902) | 1M | $2.10 | $6.30 |
| sakana/fugu-maxSakana: Fugu Max | 1M | $2.10 | $6.30 |
| x-ai/grok-4.5SpaceXAI: Grok 4.5 | 500K | $2.10 | $6.30 |
| x-ai/grok-4.6SpaceXAI: Grok 4.6 | 500K | $2.10 | $6.30 |
| Premium30 | |||
| amazon/nova-premier-v1Amazon: Nova Premier 1.0 | 1M | $2.63 | $13.13 |
| anthracite-org/magnum-v4-72bMagnum v4 72B | 33K | $2.63 | $5.25 |
| cohere/command-aCohere: Command A | 256K | $2.63 | $10.50 |
| cohere/command-r-plus-08-2024Cohere: Command R+ (08-2024) | 128K | $2.63 | $10.50 |
| openai/gpt-4oOpenAI: GPT-4o | 128K | $2.63 | $10.50 |
| openai/gpt-4o-2024-08-06OpenAI: GPT-4o (2024-08-06) | 128K | $2.63 | $10.50 |
| openai/gpt-4o-2024-11-20OpenAI: GPT-4o (2024-11-20) | 128K | $2.63 | $10.50 |
| openai/gpt-5-image-miniOpenAI: GPT-5 Image Mini | 400K | $2.63 | $2.10 |
| openai/gpt-5.4OpenAI: GPT-5.4 | 1.1M | $2.63 | $15.75 |
| openai/gpt-audioOpenAI: GPT Audio | 128K | $2.63 | $10.50 |
| moonshotai/kimi-k3MoonshotAI: Kimi K3 | 1M | $2.78 | $13.95 |
| claude-sonnet-5 | 1M | $3.15 | $15.75 |
| aion-labs/aion-3.0AionLabs: Aion-3.0 | 131K | $3.15 | $6.30 |
| anthropic/claude-sonnet-4Anthropic: Claude Sonnet 4 | 1M | $3.15 | $15.75 |
| anthropic/claude-sonnet-4.5Anthropic: Claude Sonnet 4.5 | 1M | $3.15 | $15.75 |
| anthropic/claude-sonnet-4.6Anthropic: Claude Sonnet 4.6 | 1M | $3.15 | $15.75 |
| openai/gpt-3.5-turbo-16kOpenAI: GPT-3.5 Turbo 16k | 16K | $3.15 | $4.20 |
| perplexity/sonar-proPerplexity: Sonar Pro | 200K | $3.15 | $15.75 |
| perplexity/sonar-pro-searchPerplexity: Sonar Pro Search | 200K | $3.15 | $15.75 |
| gpt-5.6-sol | 1M | $4.20 | $21.00 |
| claude-opus-5 | 1M | $5.25 | $26.25 |
| anthropic/claude-opus-4.5Anthropic: Claude Opus 4.5 | 200K | $5.25 | $26.25 |
| anthropic/claude-opus-4.6Anthropic: Claude Opus 4.6 | 1M | $5.25 | $26.25 |
| anthropic/claude-opus-4.7Anthropic: Claude Opus 4.7 | 1M | $5.25 | $26.25 |
| anthropic/claude-opus-4.8Anthropic: Claude Opus 4.8 | 1M | $5.25 | $26.25 |
| openai/gpt-4o-2024-05-13OpenAI: GPT-4o (2024-05-13) | 128K | $5.25 | $15.75 |
| openai/gpt-5.5OpenAI: GPT-5.5 | 1.1M | $5.25 | $31.50 |
| openai/gpt-chat-latestOpenAI: GPT Chat Latest | 400K | $5.25 | $31.50 |
| sakana/fugu-ultraSakana: Fugu Ultra | 1M | $5.25 | $31.50 |
| sakana/fugu-ultra-v2Sakana: Fugu Ultra v2 | 1M | $5.25 | $31.50 |
| Frontier17 | |||
| openai/gpt-5.4-image-2OpenAI: GPT-5.4 Image 2 | 272K | $8.40 | $15.75 |
| claude-fable-5 | 1M | $10.50 | $52.50 |
| claude-fable-5-1 | 1M | $10.50 | $52.50 |
| gpt-6-astra | 1.1M | $10.50 | $52.50 |
| openai/gpt-4-turboOpenAI: GPT-4 Turbo | 128K | $10.50 | $31.50 |
| openai/gpt-5-imageOpenAI: GPT-5 Image | 400K | $10.50 | $10.50 |
| openai/gpt-6-astra-proOpenAI: GPT-6 Astra Pro | 1.1M | $10.50 | $52.50 |
| anthropic/claude-opus-4Anthropic: Claude Opus 4 | 200K | $15.75 | $78.75 |
| anthropic/claude-opus-4.1Anthropic: Claude Opus 4.1 | 200K | $15.75 | $78.75 |
| openai/gpt-5-proOpenAI: GPT-5 Pro | 400K | $15.75 | $126 |
| openai/o1OpenAI: o1 | 200K | $15.75 | $63.00 |
| openai/o3-proOpenAI: o3 Pro | 200K | $21.00 | $84.00 |
| openai/gpt-5.2-proOpenAI: GPT-5.2 Pro | 400K | $22.05 | $176 |
| openai/gpt-4OpenAI: GPT-4 | 8K | $31.50 | $63.00 |
| openai/gpt-5.4-proOpenAI: GPT-5.4 Pro | 1.1M | $31.50 | $189 |
| openai/gpt-5.5-proOpenAI: GPT-5.5 Pro | 1.1M | $31.50 | $189 |
| openai/o1-proOpenAI: o1-pro | 200K | $158 | $630 |
- Long context: past a model own short-context boundary a higher vendor rate applies, on the tokens actually sent rather than on the context limit selected.
- Priority tier: 1.75x the standard rate, and only when a request asks for it.
- Nothing here is a monthly fee and no credit expires. Credit is drawn down per request, at the same figures the usage and logs pages report.