go2llm API documentation

Models

GET /v1/models and the table below are built from the same published snapshot. The catalog is available without an API key and contains only the enabled public models. Always take the exact IDs, prices and endpoints from this table, not from an older guide.

ModelCapabilitiesEndpointsBilling unitPrice
Qwen3.8 Max
qwen3.8-max
text → text, toolchat.completions, messages1M tokensinput $0.166 · output $0.498 · cache read $0.014 · cache write $0.208
Claude Haiku 4.5
claude-haiku-4-5
text → text, toolchat.completions, messages1M tokensinput $0.13 · output $0.65 · cache read $0.013 · cache write $0.163
DeepSeek V4 Flash Vision
deepseek-v4-flash-vision-exp
text → text, toolchat.completions, messages1M tokensinput $0.04 · output $0.161 · cache read $0.0008 · cache write $0.05
DeepSeek V4 Pro
deepseek-v4-pro
text → text, toolchat.completions, messages1M tokensinput $0.066 · output $0.198 · cache read $0.0022 · cache write $0.083
Gemini 3.1 Flash Image
gemini-3.1-flash-image
text, image → imageimages.generations, images.editsimagesize=1024x1024;quality=standard: $0.024
Gemini 3.5 Flash Lite
gemini-3.5-flash-lite
text → text, toolchat.completions, messages1M tokensinput $0.07 · output $0.583 · cache read $0.007 · cache write $0.088
Grok Imagine Image
grok-imagine-image
text → imageimages.generationsimagesize=1024x1024;quality=standard: $0.0049
Grok Imagine Image Pro
grok-imagine-image-pro
text → imageimages.generationsimagesize=1024x1024;quality=standard: $0.049
MiniMax M3
minimax-m3
text → text, toolchat.completions, messages1M tokensinput $0.04 · output $0.158 · cache read $0.0079 · cache write $0.049
Kimi K2.7 Code
kimi-k2.7-code
text → text, toolchat.completions, messages1M tokensinput $0.095 · output $0.402 · cache read $0.019 · cache write $0.119
Kimi K3
kimi-k3
text → text, toolchat.completions, messages1M tokensinput $0.302 · output $1.51 · cache read $0.03 · cache write $0.378
Nano Banana 2
nano-banana-2
text, image → imageimages.generations, images.editsimagesize=1024x1024;quality=standard: $0.041
Nano Banana Pro
nano-banana-pro
text, image → imageimages.generations, images.editsimagesize=1024x1024;quality=standard: $0.034
GPT-5.3 Codex
gpt-5.3-codex
text → text, toolchat.completions, messages1M tokensinput $0.519 · output $4.15 · cache read $0.052 · cache write $0.649
GPT-5.6 Luna
gpt-5.6-luna
text → text, toolchat.completions, messages1M tokensinput $0.04 · output $0.24 · cache read $0.004 · cache write $0.05
GPT Image 2
gpt-image-2
text, image → imageimages.generations, images.editsimagesize=1024x1024;quality=standard: $0.0058
Grok 4.20 Multi-Agent
grok-4.20-multi-agent
text → text, toolchat.completions, messages1M tokensinput $0.286 · output $0.573 · cache read $0.046 · cache write $0.358
Grok 4.6
grok-4.6
text → text, toolchat.completions, messages1M tokensinput $0.2 · output $0.601 · cache read $0.05 · cache write $0.25
MiMo v2.5 Pro
mimo-v2.5-pro
text → text, toolchat.completions, messages1M tokensinput $0.077 · output $0.153 · cache read $0.0006 · cache write $0.096
GLM 5.1
glm-5.1
text → text, toolchat.completions, messages1M tokensinput $0.171 · output $0.537 · cache read $0.032 · cache write $0.214
GLM 5.2
glm-5.2
text → text, toolchat.completions, messages1M tokensinput $0.141 · output $0.442 · cache read $0.026 · cache write $0.176
GLM 5.3
glm-5.3
text → text, toolchat.completions, messages1M tokensinput $0.141 · output $0.442 · cache read $0.026 · cache write $0.176
Claude Fable 5
claude-fable-5
text → text, toolchat.completions1M tokensinput $1.01 · output $5.03 · cache read $0.101 · cache write $1.26
Claude Fable 5.1
claude-fable-5-1
text → text, toolchat.completions1M tokensinput $4.5 · output $22.5 · cache read $0.113 · cache write $5.63
Claude Opus 4.8
claude-opus-4-8
text → text, toolchat.completions, messages1M tokensinput $0.503 · output $2.51 · cache read $0.05 · cache write $0.629
Qwen3.8 Flash
qwen3.8-flash
text → text, toolchat.completions, messages1M tokensinput $0.013 · output $0.045 · cache read $0.0017 · cache write $0.017
GPT-5.6 Terra
gpt-5.6-terra
text → text, toolchat.completions, messages1M tokensinput $0.201 · output $1.21 · cache read $0.02 · cache write $0.251
Kimi K2.6
kimi-k2.6
text → text, toolchat.completions, messages1M tokensinput $0.129 · output $0.542 · cache read $0.022 · cache write $0.161
Gemini 3.8 Flash
gemini-3.8-flash
text → text, toolchat.completions, messages1M tokensinput $0.106 · output $0.531 · cache read $0.011 · cache write $0.133
GPT-5.6 Sol
gpt-5.6-sol
text → text, toolchat.completions, messages1M tokensinput $0.402 · output $2.01 · cache read $0.04 · cache write $0.503
GPT-5.5
gpt-5.5
text → text, toolchat.completions, messages1M tokensinput $0.503 · output $3.02 · cache read $0.05 · cache write $0.629
Claude Opus 5
claude-opus-5
text → text, toolchat.completions, messages1M tokensinput $0.503 · output $2.51 · cache read $0.05 · cache write $0.629
Codex Auto Review
codex-auto-review
text → text, toolchat.completions, messages1M tokensinput $0.503 · output $3.02 · cache read $0.05 · cache write $0.629
MiMo v2.5
mimo-v2.5
text → text, toolchat.completions, messages1M tokensinput $0.056 · output $0.112 · cache read $0.0011 · cache write $0.07
MiMo v2.6 Flash
mimo-v2.6-flash
text → text, toolchat.completions, messages1M tokensinput $0.042 · output $0.084 · cache read $0.0008 · cache write $0.052
Gemini 3.8 Flash Tiered
gemini-3.8-flash-tiered
text → text, toolchat.completions, messages1M tokensinput $0.3 · output $1.5 · cache read $0.03 · cache write $0.375
Gemini 3.7 Flash Tiered
gemini-3.7-flash-tiered
text → text, toolchat.completions, messages1M tokensinput $0.3 · output $1.5 · cache read $0.03 · cache write $0.375
GPT-6 Astra
gpt-6-astra
text → text, toolchat.completions, messages1M tokensinput $1.01 · output $5.03 · cache read $0.101 · cache write $1.26
Gemini 3.5 Flash Low
gemini-3.5-flash-low
text → text, toolchat.completions, messages1M tokensinput $0.211 · output $1.05 · cache read $0.021 · cache write $0.264
Gemini 3.6 Flash High
gemini-3.6-flash-high
text → text, toolchat.completions, messages1M tokensinput $0.225 · output $1.13 · cache read $0.022 · cache write $0.281
Claude Sonnet 5
claude-sonnet-5
text → text, toolchat.completions, messages1M tokensinput $0.329 · output $1.64 · cache read $0.033 · cache write $0.411
Claude Sonnet 5.5
claude-sonnet-5-5
text → text, toolchat.completions, messages1M tokensinput $1.5 · output $7.5 · cache read $0.075 · cache write $1.88
Claude Opus 4.7
claude-opus-4-7
text → text, toolchat.completions, messages1M tokensinput $0.649 · output $3.25 · cache read $0.065 · cache write $0.811
DeepSeek V4 Flash
deepseek-v4-flash
text → text, toolchat.completions, messages1M tokensinput $0.023 · output $0.068 · cache read $0.0007 · cache write $0.028
DeepSeek V4.1 Flash
deepseek-v4.1-flash
text → text, toolchat.completions, messages1M tokensinput $0.045 · output $0.18 · cache read $0.0009 · cache write $0.056
Claude Opus 4.6
claude-opus-4-6
text → text, toolchat.completions, messages1M tokensinput $0.503 · output $2.51 · cache read $0.05 · cache write $0.629
Claude Sonnet 4.6
claude-sonnet-4-6
text → text, toolchat.completions, messages1M tokensinput $0.344 · output $1.72 · cache read $0.034 · cache write $0.43
Gemini 2.5 Flash
gemini-2.5-flash
text → text, toolchat.completions, messages1M tokensinput $0.036 · output $0.3 · cache read $0.0036 · cache write $0.045
Gemini 2.5 Pro
gemini-2.5-pro
text → text, toolchat.completions, messages1M tokensinput $0.212 · output $1.7 · cache read $0.021 · cache write $0.265
Gemini 3 Flash Preview
gemini-3-flash-preview
text → text, toolchat.completions, messages1M tokensinput $0.094 · output $0.562 · cache read $0.0094 · cache write $0.117
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
text → text, toolchat.completions, messages1M tokensinput $0.3 · output $1.8 · cache read $0.03 · cache write $0.375
Gemini 3.6 Flash
gemini-3.6-flash
text → text, toolchat.completions, messages1M tokensinput $0.128 · output $0.638 · cache read $0.013 · cache write $0.16
GLM 5.3 Flash
glm-5.3-flash
text → text, toolchat.completions, messages1M tokensinput $0.018 · output $0.06 · cache read $0.0036 · cache write $0.022
GPT-5.4
gpt-5.4
text → text, toolchat.completions, messages1M tokensinput $0.348 · output $2.09 · cache read $0.035 · cache write $0.435
Grok 4.3
grok-4.3
text → text, toolchat.completions, messages1M tokensinput $0.178 · output $0.356 · cache read $0.028 · cache write $0.222
Grok 4.5
grok-4.5
text → text, toolchat.completions, messages1M tokensinput $0.201 · output $0.603 · cache read $0.03 · cache write $0.251
Qwen3.7 Max
qwen3.7-max
text → text, toolchat.completions, messages1M tokensinput $0.166 · output $0.498 · cache read $0.017 · cache write $0.208
Qwen3.7 Plus
qwen3.7-plus
text → text, toolchat.completions, messages1M tokensinput $0.03 · output $0.121 · cache read $0.0031 · cache write $0.038
GPT Image 2.5
gpt-image-2.5
text, image → imageimages.generations, images.editsimagesize=1024x1024;quality=standard: $0.019
GPT-6 Luna
gpt-6-luna
text → text, toolchat.completions, messages1M tokensinput $0.028 · output $0.14 · cache read $0.0028 · cache write $0.035
GPT-6 Sol
gpt-6-sol
text → text, toolchat.completions, messages1M tokensinput $0.35 · output $1.75 · cache read $0.035 · cache write $0.438
GPT-6.1 Sol
gpt-6.1-sol
text → text, toolchat.completions, messages1M tokensinput $0.3 · output $1.5 · cache read $0.015 · cache write $0.375
Claude Opus 5.5
claude-opus-5-5
text → text, toolchat.completions, messages1M tokensinput $2.57 · output $12.85 · cache read $0.15 · cache write $3.21
Grok 4.7
grok-4.7
text → text, toolchat.completions, messages1M tokensinput $0.2 · output $0.601 · cache read $0.05 · cache write $0.25
GLM 5.3 FlashX
glm-5.3-flashx
text → text, toolchat.completions, messages1M tokensinput $0.046 · output $0.154 · cache read $0.0075 · cache write $0.058
  1. Copy the exact id into the model field.
  2. Use only the endpoint listed on that model's row.
  3. For images, stick to the published size, quality and result-count limits.
  4. For image understanding, pick a model with image in modalities.input; for text-only models use vision_companion.

If a model is not in this table and not in /v1/models, it is not available for use yet.