Model pricing compared

Model pricing, compared across hosts

The same open or multi-host model, priced on every host we parse. Cheapest input/output highlighted per model. Matching is an explicit alias table plus an identical normalized name — never fuzzy guessing (see below for names that didn't match). $ / 1M tokens, primary tier per host. JSON · full pricing reference.

GLM 5.2 priced on 3 hosts

Host	Input	Output	Context	Link
Fireworks AI	$1.4	—	—	provider page
Mistral AI	$1.4	$4.4	—	provider page
Together AI	$1.4	$4.4	—	provider page

GLM 5.3 priced on 3 hosts

Host	Input	Output	Context	Link
Fireworks AI	$1.4	$4.4	—	provider page
Mistral AI	$1.4	$4.4	—	provider page
Together AI	$1.4	$4.4	—	provider page

DeepSeek V4 Flash (0731) priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.22	$0.66	—	provider page
Together AI	$0.14	$0.28	—	provider page

DeepSeek V4 Pro (0813) priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$1.32	$3.96	—	provider page
Together AI	$1.32	$3.96	—	provider page

DeepSeek V4.1 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.3	$1.2	—	provider page
Together AI	$0.3	$1.2	—	provider page

DeepSeek V4.1 Flash 1017 priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.3	$1.2	—	provider page
Together AI	$0.3	$1.2	—	provider page

Gemini 3 Flash Preview priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.5	$3	—	provider page
Vertex AI	$0.5	—	—	provider page

Gemini 3 Pro Image (Nano Banana Pro) 🍌 priced on 2 hosts

Host	Input	Output	Context	Link
Google	$2	$12	—	provider page
Vertex AI	$2	$12	—	provider page

Gemini 3.1 Flash Image (Nano Banana 2) 🍌 priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.5	$3	—	provider page
Vertex AI	$0.5	$3	—	provider page

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 🍌 priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.25	$1.5	—	provider page
Vertex AI	$0.25	$1.5	—	provider page

Gemini 3.1 Flash-Lite priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.25	$1.5	—	provider page
Vertex AI	$0.25	$1.5	—	provider page

Gemini 3.1 Pro Preview priced on 2 hosts

Host	Input	Output	Context	Link
Google	$2	$12	—	provider page
Vertex AI	$2	$12	—	provider page

Gemini 3.5 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Google	$1.5	$9	—	provider page
Vertex AI	$1.5	$9	—	provider page

Gemini 3.5 Flash-Lite priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.3	$2.5	—	provider page
Vertex AI	$0.3	$2.5	—	provider page

Gemini 3.6 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.75	$3.75	—	provider page
Vertex AI	$0.75	$3.75	—	provider page

Gemini 3.7 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.75	$3.75	—	provider page
Vertex AI	$0.75	$3.75	—	provider page

Gemini 3.8 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Google	$0.75	$3.75	—	provider page
Vertex AI	$0.75	$3.75	—	provider page

GLM 5.3 Flash priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.15	$0.5	—	provider page
Together AI	$0.15	$0.5	—	provider page

Kimi K3 priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$3	$15	—	provider page
Together AI	$3	$15	—	provider page

MiniMax M3 priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.3	$1.2	—	provider page
Together AI	$0.3	$1.2	—	provider page

Muse Glimmer 30B priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.35	$1.5	—	provider page
Together AI	$0.35	$1.5	—	provider page

Muse Spark Open priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$1.25	$4.25	—	provider page
Together AI	$1.25	$4.25	—	provider page

OpenAI GPT OSS 120B priced on 2 hosts

Host	Input	Output	Context	Link
Fireworks AI	$0.15	$0.6	—	provider page
Together AI	$0.15	$0.6	—	provider page

Priced on one host only

Same-model matching only merges an explicit alias or an identical normalized name — never a guess. These didn't match anything on another host, so they're listed on their own rather than force-merged.

Classifier API model (3B) (Mistral AI only)
Classifier API model (8B) (Mistral AI only)
Claude 3.5 Sonnet (AWS Bedrock only)
Claude 3.5 Sonnet v2 (AWS Bedrock only)
Claude Fable 5 (Anthropic only)
Claude Fable 5.1 (Anthropic only)
Claude Haiku 3.5 (Anthropic only)
Claude Haiku 4.5 (Anthropic only)
Claude Mythos 5 (Anthropic only)
Claude Mythos 5.1 (Anthropic only)
Claude Opus 4 (Anthropic only)
Claude Opus 4.1 (Anthropic only)
Claude Opus 4.5 (Anthropic only)
Claude Opus 4.6 (Anthropic only)
Claude Opus 4.7 (Anthropic only)
Claude Opus 4.8 (Anthropic only)
Claude Opus 5 (Anthropic only)
Claude Opus 5.5 (Anthropic only)
Claude Sonnet 4 (Anthropic only)
Claude Sonnet 4.5 (Anthropic only)
Claude Sonnet 4.6 (Anthropic only)
Claude Sonnet 5 (Anthropic only)
Codestral (Mistral AI only)
Cogito v2.1 671B (Together AI only)
DeepSeek V4 Flash Vision Exp (Fireworks AI only)
DeepSeek V4.1 Flash (US) (Fireworks AI only)
DeepSeek V4.1 Flash 1017 (US) (Fireworks AI only)
DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) (Fireworks AI only)
deepseek-flash (DeepSeek only)
deepseek-v4-pro (DeepSeek only)
Ember-1 (Fireworks AI only)
Gemini 2.5 Computer Use Preview (Google only)
Gemini 2.5 Flash (Google only)
Gemini 2.5 Flash Image (Nano Banana) 🍌 (Google only)
Gemini 2.5 Flash Native Audio (Live API) (Google only)
Gemini 2.5 Flash Preview TTS (Google only)
Gemini 2.5 Flash-Lite (Google only)
Gemini 2.5 Pro (Google only)
Gemini 2.5 Pro Preview TTS (Google only)
Gemini 3.1 Flash TTS Preview (Google only)
Gemini 3.5 Live Translate (Google only)
Gemini 3.5 Transcribe (Google only)
Gemini 3.5 Transcribe Live (Google only)
Gemini 3.8 Flash Cyber (Vertex AI only)
Gemini 3.8 Flash TTS (Google only)
Gemini 3.8 Flash-Lite TTS (Google only)
Gemini 3.8 Live, Gemini 3.8 Live Extended Thinking, and Gemini 3.1 Flash Live Preview (Google only)
Gemini 4 Argon (Google only)
Gemini Embedding (Google only)
Gemini Nano Banana 2.1 🍌 (Google only)
Gemini Omni Flash (Google only)
Gemini Omni Flash Preview (Google only)
Gemini Robotics ER 2 Preview (Google only)
Gemini Robotics ER 2 Streaming Preview (Google only)
Gemma 4 31B (Together AI only)
GLM 5.2 Fast (Fireworks AI only)
GLM 5.2 Fast US (Fireworks AI only)
GLM 5.2 Fast USGLM 5.2 Fast US (Fireworks AI only)
GLM 5.3 (US) (Fireworks AI only)
GLM 5.3 Fast (Fireworks AI only)
GLM 5.3 Fast3 Fast (Fireworks AI only)
GLM 5.3 Flash (US) (Fireworks AI only)
gpt-5.6-cyber (OpenAI only)
gpt-5.6-luna (OpenAI only)
gpt-5.6-sol (OpenAI only)
gpt-5.6-terra (OpenAI only)
gpt-6-astra (OpenAI only)
gpt-6-luna (OpenAI only)
gpt-6-sol (OpenAI only)
gpt-6.1-sol (OpenAI only)
Grok 4.6 (xAI only)
Grok 4.7 (xAI only)
Inkling (Together AI only)
Kimi K2.6 (Fireworks AI only)
Kimi K2.7 Code (Fireworks AI only)
Kimi K3 (US) (Fireworks AI only)
Kimi K3 Fast (Fireworks AI only)
Llama 3 8B Instruct Lite (Together AI only)
Llama 3.3 70B (Together AI only)
MiniMax M2.7 (Together AI only)
MiniMax M3.1 Flash (Together AI only)
Ministral 3 (14B) (Mistral AI only)
Ministral 3 (3B) (Mistral AI only)
Ministral 3 (8B) (Mistral AI only)
Mistral Large 3 (Mistral AI only)
Mistral Medium 3.5 (Mistral AI only)
Mistral Small 4 (Mistral AI only)
Muse Spark Open (Free for limited time) (Together AI only)
NVIDIA Nemotron 3 Ultra (Preview) (Fireworks AI only)
NVIDIA Nemotron 3.5 Lightning 30B A3B (Fireworks AI only)
NVIDIA Nemotron 3.5 Super VL (Together AI only)
Qwen 3.8 Max (Fireworks AI only)
Qwen2.5 7B Instruct Turbo (Together AI only)
Qwen3 235B A22B Instruct 2507 FP8 Throughput (Together AI only)
Qwen3.5 9B (Together AI only)
Qwen3.5-397B-A17B (Together AI only)
Qwen3.6-Plus (Together AI only)
Qwen3.7-Max (Together AI only)
Qwen3.7-Plus (Together AI only)
Qwen3.8 Flash (Together AI only)
Qwen3.8-2.4T-A95B (Together AI only)
Reflection Beam (Together AI only)
Rnj-1 Instruct (Together AI only)
Sonar (Perplexity only)
Sonar Deep Research (Perplexity only)
Sonar Pro (Perplexity only)
Sonar Reasoning Pro (Perplexity only)
Ternary Bonsai 27B (Together AI only)
Ultramarine 1 Flash (US) (Fireworks AI only)