tokenstat
tokenstat

Model catalog

Models and list rates

Published API list rates (USD per million tokens), who lists each model, and whether it can do tools, vision, or reasoning. Recommended order is newer first; among similarly new models, larger context wins. Free/$0 rows stay hidden unless you ask. Not a bill: measure real sessions with the CLI.

3,231 models in the merged catalog · as of . Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,231 matches · page 58 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Gpt Oss:120b Cloudollama/gpt-oss:120b-cloud
$0LiteLLM$0N/A2
Gpt Oss:20b Cloudollama/gpt-oss:20b-cloud
$0LiteLLM$0N/A2
Gpt Realtimegpt-realtime
$4LiteLLM$16N/A1
Gpt Realtime 1.5 2026 02 23azure/gpt-realtime-1.5-2026-02-23
$4LiteLLM$16N/A2
Gpt Realtime 2.1 Minigpt-realtime-2.1-mini
$0.6LiteLLM$2.40N/A1
Gpt Realtime 2025 08 28azure/gpt-realtime-2025-08-28
$4LiteLLM$16N/A2
Gpt Realtime Mini 2025 10 06azure/gpt-realtime-mini-2025-10-06
$0.6LiteLLM$2.40N/A2
Gpt Realtime Mini 2025 12 15gpt-realtime-mini-2025-12-15
$0.6LiteLLM$2.40N/A1
Granite 13b Chat V2ibm/granite-13b-chat-v2
$0.6LiteLLM$0.6N/A3
Granite 13b Instruct V2ibm/granite-13b-instruct-v2
$0.6LiteLLM$0.6N/A3
Granite 4 H Smallibm/granite-4-h-small
$0.06LiteLLM$0.25N/A3
Granite Guardian 3 2 2bibm/granite-guardian-3-2-2b
$0.1LiteLLM$0.1N/A3
Granite Ttm 1024 96 R2ibm/granite-ttm-1024-96-r2
$0.38LiteLLM$0.38N/A3
Granite Ttm 1536 96 R2ibm/granite-ttm-1536-96-r2
$0.38LiteLLM$0.38N/A3
Granite Ttm 512 96 R2ibm/granite-ttm-512-96-r2
$0.38LiteLLM$0.38N/A3
Granite Vision 3 2 2bibm/granite-vision-3-2-2b
$0.1LiteLLM$0.1N/A3
Grok Imagine Videox-ai/grok-imagine-video
vision
$0OpenRouter$0N/A1
Grok Imagine Video 1.5x-ai/grok-imagine-video-1.5
vision
$0OpenRouter$0N/A1
Grok STT 1.0x-ai/grok-stt-1.0
$100000OpenRouter$0N/A1
Hermes3 405blambda_ai/hermes3-405b
$0.8LiteLLM$0.8N/A2
Hermes3 70blambda_ai/hermes3-70b
$0.12LiteLLM$0.3N/A2
Internlm2_5 20b Chatollama/internlm2_5-20b-chat
$0LiteLLM$0N/A2
Internvl3 38baccounts/fireworks/models/internvl3-38b
$0.9LiteLLM$0.9N/A3
Internvl3 78baccounts/fireworks/models/internvl3-78b
$0.9LiteLLM$0.9N/A3
J2 Lightj2-light
$3LiteLLM$3N/A1
J2 Midj2-mid
$10LiteLLM$10N/A1
J2 Ultraj2-ultra
$15LiteLLM$15N/A1
Jais 13b Chatcore42/jais-13b-chat
$500LiteLLM$2000N/A3
Jamba 1.5vertex_ai/jamba-1.5
$0.2LiteLLM$0.4N/A2
Jamba 1.5 Largevertex_ai/jamba-1.5-large
$2LiteLLM$8N/A2
Jamba 1.5 Large@001vertex_ai/jamba-1.5-large@001
$2LiteLLM$8N/A2
Jamba 1.5 Minivertex_ai/jamba-1.5-mini
$0.2LiteLLM$0.4N/A2
Jamba 1.5 Mini@001vertex_ai/jamba-1.5-mini@001
$0.2LiteLLM$0.4N/A2
Jamba Instructazure_ai/jamba-instruct
$0.5LiteLLM$0.7N/A2
Japanese Stable Diffusion Xlaccounts/fireworks/models/japanese-stable-diffusion-xl
$0.0001LiteLLM$0.0001N/A3
Jina Reranker V2 Base Multilingualjina-reranker-v2-base-multilingual
$0.018LiteLLM$0.018N/A1
Kat Coderaccounts/fireworks/models/kat-coder
$0.9LiteLLM$0.9N/A3
Kat Dev 32baccounts/fireworks/models/kat-dev-32b
$0.9LiteLLM$0.9N/A3
Kat Dev 72b Expaccounts/fireworks/models/kat-dev-72b-exp
$0.9LiteLLM$0.9N/A3
Lfm 40blambda_ai/lfm-40b
$0.1LiteLLM$0.2N/A2
Llama Guard 4 12Bdeepinfra/meta-llama/Llama-Guard-4-12B
$0.18LiteLLM$0.18N/A1
Llama Guard 4 12BLlama-Guard-4-12B
$0.18LiteLLM$0.18N/A2
Llama V2 13baccounts/fireworks/models/llama-v2-13b
$0.2LiteLLM$0.2N/A3
Llama V2 13b Chataccounts/fireworks/models/llama-v2-13b-chat
$0.2LiteLLM$0.2N/A3
Llama V2 70baccounts/fireworks/models/llama-v2-70b
$0.1LiteLLM$0.1N/A3
Llama V2 70b Chataccounts/fireworks/models/llama-v2-70b-chat
$0.9LiteLLM$0.9N/A3
Llama V3 70b Instructaccounts/fireworks/models/llama-v3-70b-instruct
$0.9LiteLLM$0.9N/A3
Llama V3 70b Instruct Hfaccounts/fireworks/models/llama-v3-70b-instruct-hf
$0.9LiteLLM$0.9N/A3

Price this against your own usage

List rates are only half the story. The CLI reads the session logs your coding harnesses already write and shows tokens, cache share, and usage value on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash