Skip to content

Models & Pricing

Find the right model.
Know the price.

Only models currently published by the live gateway. Rates are per 1M tokens; input, output, cache-read, and cache-write usage are shown separately.

85 live models · refreshed on page load

See plans
GPT-6 Sol
gpt-6-sol

OpenAI GPT-6 Sol — reasoning model with tools, vision and structured output. 1M-token context.

Input$0.6
Output$3
Cache write$0.75
Cache read$0.06
Context1.1M
GPT-6.1 Sol
gpt-6.1-sol

OpenAI GPT-6.1 Sol — reasoning model with tools, vision and structured output. 1M-token context.

Input$0.6
Output$3
Cache write$0.75
Cache read$0.03
Context1.1M
Qwen3.8 Max
qwen3.8-max

Alibaba Qwen3.8 Max flagship

Input$0.2
Output$0.6
Cache write—
Cache read$0.025
Context1M
GPT-6 Luna
gpt-6-luna

OpenAI GPT-6 Luna — fastest, lowest-cost GPT-6 tier for high-volume work. 1M-token context.

Input$0.03
Output$0.15
Cache write$0.037
Cache read$0.003
Context1.1M
Grok 4.7
grok-4.7

xAI Grok 4.7 — xAI's latest reasoning model. 500K-token context.

Input$0.6
Output$1.80
Cache write—
Cache read$0.15
Context500K
Claude Fable 5
claude-fable-5

Anthropic Claude Fable 5 — strong reasoning, writing and tool use. 1M-token context.

Input$3
Output$15
Cache write$3.75
Cache read$0.3
Context1M
GPT Image 2.5 FlareImage
gpt-image-2.5-flare

GPT Image 2.5 Flare — fast image generation/edit, native multimodal (OpenAI).

Input$0.8
Output$3
Cache write—
Cache read$0.2
Context200K
GPT Image 2.5 SunburstImage
gpt-image-2.5-sunburst

GPT Image 2.5 Sunburst — precise, high-control image editing (OpenAI).

Input$0.8
Output$3
Cache write—
Cache read$0.2
Context200K
DeepSeek V4.1 Flash
deepseek-v4.1-flash

DeepSeek V4.1 Flash — fast 552B MoE model with native image input and a 1M-token context window.

Input$0.013
Output$0.09
Cache write—
Cache read$0.002
Context1.0M
Qwen 3.8 27B Uncensored
qwen-3-8-27b-uncensored

Qwen3.8 27B uncensored (HauhauCS Aggressive), self-hosted.

Input$0.4
Output$1.20
Cache write—
Cache read—
Context262K
Gemini 3.8 Flash
gemini-3.8-flash

Google Gemini 3.8 Flash — newest fast thinking model with multimodal input. 1M-token context.

Input$0.225
Output$1.13
Cache write$0.013
Cache read$0.022
Context1M
GPT-6 Astra
gpt-6-astra

OpenAI GPT-6 Astra — OpenAI's most capable reasoning model. 1M-token context. Tool calling via /v1/responses; leave temperature at default.

Input$3
Output$15
Cache write$3.75
Cache read$0.3
Context1.1M
GLM-5.3 Flash
glm-5.3-flash

Z.ai GLM-5.3 Flash — fast, very low-cost GLM model.

Input$0.011
Output$0.27
Cache write—
Cache read$0.003
Context200K
Claude Opus 5
claude-opus-5

Anthropic Claude Opus 5 — flagship reasoning and coding model for complex, multi-step work. 1M-token context.

Input$1.50
Output$7.50
Cache write$1.88
Cache read$0.15
Context1M
Gemini 3.7 Flash
gemini-3.7-flash

Google Gemini 3.7 Flash — fast, low-cost multimodal model. 1M-token context.

Input$0.225
Output$1.13
Cache write$0.013
Cache read$0.022
Context1M
Grok 4.6
grok-4.6
Input$0.6
Output$1.80
Cache write—
Cache read$0.15
Context200K
GPT-OSS 20B (NVIDIA)
openai/gpt-oss-20b

OpenAI gpt-oss-20b — small open-weight model; very low cost.

Input$0.005
Output$0.027
Cache write—
Cache read$0.003
Context131K
GPT-5.6 Luna
gpt-5.6-luna

OpenAI GPT-5.6 Luna — fast, low-cost GPT-5.6 tier. 1M-token context.

Input$0.06
Output$0.36
Cache write$0.075
Cache read$0.006
Context1.1M
gemini 3.5 flash lite
gemini-3.5-flash-lite
Input$0.09
Output$0.75
Cache write$0.025
Cache read$0.009
Context1M
gemini 3.6 flash
gemini-3.6-flash
Input$0.225
Output$1.13
Cache write$0.013
Cache read$0.022
Context1M
GPT-5.6 Terra
gpt-5.6-terra

OpenAI GPT-5.6 Terra — GPT-5.6 reasoning model. 1M-token context.

Input$0.6
Output$3.60
Cache write$0.75
Cache read$0.06
Context1.1M
Gemini Flash Latest
gemini-flash-latest
Input$0.225
Output$1.13
Cache write$0.013
Cache read$0.022
Context200K
Codestral EmbedEmbedding
codestral-embed
Input$0.045
Output$0
Cache write—
Cache read—
Context200K
Mistral EmbedEmbedding
mistral-embed
Input$0.03
Output$0
Cache write—
Cache read—
Context200K
Qwen Text Embedding v4Embedding
text-embedding-v4

Alibaba Qwen text-embedding-v4 — multilingual text embeddings.

Input$0.006
Output$0
Cache write—
Cache read—
Context200K
Kimi K2.7 Code
kimi-k2.7-code

Moonshot Kimi K2.7 Code — coding-tuned Kimi model. 256K-token context.

Input$0.201
Output$1
Cache write—
Cache read$0.054
Context262K
Kimi K3
kimi-k3

Moonshot Kimi K3 — open-weight flagship for agentic coding and long context. 1M-token context.

Input$0.15
Output$4.50
Cache write—
Cache read$0.084
Context1.0M
MiniMax M2
minimax-m2
Input$0.076
Output$0.306
Cache write—
Cache read—
Context200K
Qwen Flash
qwen-flash
Input$0.025
Output$0.1
Cache write—
Cache read—
Context200K
Qwen3 Coder Plus
qwen3-coder-plus

Alibaba Qwen3 Coder Plus — coding-specialised Qwen model.

Input$0.195
Output$0.975
Cache write$0.244
Cache read$0.039
Context200K
Qwen3 Max
qwen3-max
Input$0.234
Output$1.17
Cache write$0.292
Cache read$0.047
Context200K
Qwen3 VL Plus
qwen3-vl-plus

Alibaba Qwen3 VL Plus — vision-language model for images and documents.

Input$0.1
Output$0.3
Cache write—
Cache read—
Context200K
Qwen3.6 Plus
qwen3.6-plus
Input$0.098
Output$0.585
Cache write$0.122
Cache read—
Context200K
Qwen3.7 Max
qwen3.7-max
Input$0.443
Output$1.33
Cache write$0.553
Cache read$0.088
Context200K
Qwen3.7 Plus
qwen3.7-plus
Input$0.096
Output$0.384
Cache write$0.12
Cache read$0.019
Context200K
QwQ Plus
qwq-plus
Input$0.1
Output$0.3
Cache write—
Cache read—
Context200K
GPT-5.6 Sol
gpt-5.6-sol

OpenAI GPT-5.6 Sol — balanced GPT-5.6 reasoning model; a strong default for Codex and agents. 1M-token context.

Input$1.20
Output$6
Cache write$1.50
Cache read$0.12
Context1.1M
Gemini 2.5 Flash Lite
gemini-2.5-flash-lite
Input$0.03
Output$0.12
Cache write$0.025
Cache read$0.003
Context200K
Gemini 3.1 Flash Lite
gemini-3.1-flash-lite
Input$0.075
Output$0.45
Cache write$0.025
Cache read$0.007
Context200K
Codestral
codestral
Input$0.09
Output$0.27
Cache write—
Cache read$0.009
Context200K
Devstral
devstral
Input$0.12
Output$0.6
Cache write—
Cache read$0.012
Context200K
Devstral Medium
devstral-medium
Input$0.12
Output$0.6
Cache write—
Cache read$0.012
Context200K
Magistral Small
magistral-small
Input$0.25
Output$0.75
Cache write—
Cache read—
Context200K
Ministral 14B
ministral-14b
Input$0.06
Output$0.06
Cache write—
Cache read$0.006
Context200K
Ministral 3B
ministral-3b
Input$0.03
Output$0.03
Cache write—
Cache read$0.003
Context200K
Ministral 8B
ministral-8b
Input$0.045
Output$0.045
Cache write—
Cache read$0.004
Context200K
Mistral Medium
mistral-medium
Input$0.12
Output$0.6
Cache write—
Cache read$0.012
Context200K
Mistral Medium 3.5
mistral-medium-3.5
Input$0.45
Output$2.25
Cache write—
Cache read—
Context200K
Mistral Small
mistral-small
Input$0.045
Output$0.18
Cache write—
Cache read$0.004
Context200K
Mistral Tiny
mistral-tiny
Input$0.015
Output$0.015
Cache write—
Cache read—
Context200K
Open Mistral Nemo
open-mistral-nemo
Input$0.009
Output$0.009
Cache write—
Cache read—
Context200K
Voxtral Small
voxtral-small
Input$0.03
Output$0.09
Cache write—
Cache read$0.003
Context200K
Claude Opus 4.6
claude-opus-4-6

Anthropic Claude Opus 4.6 — previous-generation Opus. 1M-token context.

Input$1.50
Output$7.50
Cache write$1.88
Cache read$0.15
Context1M
Claude Opus 4.7
claude-opus-4-7

Anthropic Claude Opus 4.7 — previous-generation Opus. 1M-token context.

Input$1.50
Output$7.50
Cache write$1.88
Cache read$0.15
Context1M
GLM 4.7 (dot)
glm-4.7

GLM-4.7 — Z.ai general-purpose model.

Input$0.18
Output$0.66
Cache write—
Cache read$0.033
Context200K
GLM-5.2
glm-5.2

GLM-5.2 — Z.ai general-purpose model with reasoning.

Input$0.012
Output$2.10
Cache write—
Cache read$0.012
Context200K
GLM-5.3
glm-5.3

GLM-5.3 — Z.ai latest general-purpose model with reasoning.

Input$0.024
Output$1.44
Cache write—
Cache read$0.018
Context200K
Claude Opus 4.8
claude-opus-4-8

Anthropic Claude Opus 4.8 — previous-generation Opus; dependable for coding and analysis. 1M-token context.

Input$1.50
Output$7.50
Cache write$1.88
Cache read$0.15
Context1M
Kimi K2.7
kimi-k2.7
Input$0.075
Output$0.35
Cache write—
Cache read$0.015
Context200K
MiniMax M3
minimax-m3

MiniMax M3 — low-cost model with a 1M-token context.

Input$0.09
Output$0.36
Cache write—
Cache read$0.018
Context1M
Grok 4.20 Fast
grok-4.20-fast
Input$0.375
Output$0.75
Cache write—
Cache read$0.06
Context256K
DeepSeek V4 Flash
deepseek-v4-flash

DeepSeek V4 Flash — fast, low-cost general-purpose model (current generation).

Input$0.027
Output$0.055
Cache write—
Cache read$0.005
Context200K
DeepSeek V4 Pro
deepseek-v4-pro

DeepSeek V4 Pro — DeepSeek's most capable model for complex reasoning, math and code.

Input$0.111
Output$0.221
Cache write—
Cache read$0.009
Context1.0M
Kimi K2.6
kimi-k2.6
Input$0.195
Output$1.02
Cache write—
Cache read$0.045
Context33K
MiniMax M2.7
minimax-m2.7

MiniMax M2.7 — open-weight reasoning model.

Input$0.09
Output$0.36
Cache write—
Cache read$0.018
Context128K
GPT-4.1
gpt-4.1

OpenAI GPT-4.1 — non-reasoning model with a 1M-token context; fast for simple tasks.

Input$0.6
Output$2.40
Cache write—
Cache read$0.15
Context1.0M
GPT-5.1
gpt-5.1

OpenAI GPT-5.1 — previous-generation general-purpose model.

Input$0.375
Output$3
Cache write—
Cache read$0.037
Context272K
GPT-5.4
gpt-5.4

OpenAI GPT-5.4 — general-purpose model. 1M-token context.

Input$0.75
Output$4.50
Cache write—
Cache read$0.075
Context1.1M
Mistral Large
mistral-large
Input$0.15
Output$0.45
Cache write—
Cache read$0.015
Context128K
Grok 4.1 Fast
grok-4-1-fast

Grok 4.1 fast — balanced speed and quality

Input$0.02
Output$0.05
Cache write—
Cache read$0.005
Context128K
MiniMax M2.5
minimax-m2.5

MiniMax M2.5 — reasoning model

Input$0.081
Output$0.324
Cache write—
Cache read$0.008
Context200K
Grok 4.20 (Legacy)
grok-4.20-0309-non-reasoning
Input$0.375
Output$0.75
Cache write—
Cache read$0.06
Context131K
Grok 4.20 Reasoning (Legacy)
grok-4.20-0309-reasoning
Input$0.375
Output$0.75
Cache write—
Cache read$0.06
Context131K
Gemini 2.5 Flash
gemini-2.5-flash
Input$0.09
Output$0.75
Cache write$0.025
Cache read$0.009
Context200K
Gemini 2.5 Flash Image (Vision)
gemini-2.5-flash-image-vision
Input$0.15
Output$0.9
Cache write—
Cache read—
Context66K
GLM 5.1
glm-5.1

GLM-5.1 — Z.ai general-purpose model.

Input$0.399
Output$1.25
Cache write—
Cache read$0.074
Context200K
Qwen3 Coder Next (Regular Chat)
qwen3-coder-next
Input$0.036
Output$0.24
Cache write—
Cache read$0.021
Context200K
GPT-OSS 120B
openai/gpt-oss-120b

OpenAI gpt-oss-120b — open-weight reasoning model; very low cost.

Input$0.011
Output$0.051
Cache write—
Cache read—
Context131K
GLM 5
glm-5

GLM-5 — Z.ai flagship general-purpose model.

Input$0.18
Output$0.576
Cache write—
Cache read$0.036
Context33K
qwen max
qwen-max
Input$0.8
Output$3.20
Cache write—
Cache read—
Context33K
qwen plus
qwen-plus
Input$0.078
Output$0.234
Cache write$0.098
Cache read$0.016
Context33K
qwen turbo
qwen-turbo
Input$0.025
Output$0.1
Cache write—
Cache read—
Context33K
gemini 3 flash
gemini-3-flash
Input$0.15
Output$0.9
Cache write$0.025
Cache read$0.015
Context33K
MiniMax M2.1
minimax-m2.1
Input$0.09
Output$0.36
Cache write—
Cache read$0.009
Context33K
bge m3Embedding
bge-m3-q4_k_m
Input$0.003
Output$0
Cache write—
Cache read—
Context8K

This directory shows currently published models. Cache rates do not guarantee cache hits. Subscriptions have separate five-hour allowances and monthly caps — see plans.